diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..4e71b5c14cebc0648c5d8549cd67844cfa4e648b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,175 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +Assassin/example_videos/dog_assassin.gif filter=lfs diff=lfs merge=lfs -text +Assassin/example_videos/dog_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +Assassin/example_videos/man1_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +Assassin/example_videos/man2_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +Assassin/example_videos/rabbit_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +Assassin/example_videos/thanos_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +Baby/example_videos/goku_baby.gif filter=lfs diff=lfs merge=lfs -text +Baby/example_videos/goku_baby.mp4 filter=lfs diff=lfs merge=lfs -text +Baby/example_videos/man_baby.mp4 filter=lfs diff=lfs merge=lfs -text +Baby/example_videos/woman_baby.mp4 filter=lfs diff=lfs merge=lfs -text +Bride/example_videos/man_bride.mp4 filter=lfs diff=lfs merge=lfs -text +Bride/example_videos/rabbit_bride.gif filter=lfs diff=lfs merge=lfs -text +Bride/example_videos/rabbit_bride.mp4 filter=lfs diff=lfs merge=lfs -text +Bride/example_videos/rodent_bride.mp4 filter=lfs diff=lfs merge=lfs -text +Cakeify/example_gifs/cat_cakeify.gif filter=lfs diff=lfs merge=lfs -text +Cakeify/example_gifs/puppy_cakeify.gif filter=lfs diff=lfs merge=lfs -text +Cakeify/example_gifs/timberland_cakeify.gif filter=lfs diff=lfs merge=lfs -text +Cakeify/example_gifs/woman_cakeify.gif filter=lfs diff=lfs merge=lfs -text +Cakeify/example_videos/cat_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +Cakeify/example_videos/puppy_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +Cakeify/example_videos/timberland_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +Cakeify/example_videos/woman_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +Cakeify/workflow/cakeify_workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Cartoon_Jaw_Drop/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Cartoon_Jaw_Drop/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Cartoon_Jaw_Drop/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +Cartoon_Jaw_Drop/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Classy/example_videos/man1_classy.mp4 filter=lfs diff=lfs merge=lfs -text +Classy/example_videos/man2_classy.mp4 filter=lfs diff=lfs merge=lfs -text +Crush/example_videos/chicken_crush.mp4 filter=lfs diff=lfs merge=lfs -text +Crush/example_videos/coke_crush.mp4 filter=lfs diff=lfs merge=lfs -text +Crush/example_videos/man_crush.mp4 filter=lfs diff=lfs merge=lfs -text +Crush/example_videos/tank_crush.mp4 filter=lfs diff=lfs merge=lfs -text +Crush/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Deflate/example_videos/balloon_deflate.mp4 filter=lfs diff=lfs merge=lfs -text +Deflate/example_videos/cat_deflate.mp4 filter=lfs diff=lfs merge=lfs -text +Deflate/example_videos/lamp_deflate.mp4 filter=lfs diff=lfs merge=lfs -text +Deflate/example_videos/man_deflate.mp4 filter=lfs diff=lfs merge=lfs -text +Deflate/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Disney-Princess/example_videos/man_disney_princess.mp4 filter=lfs diff=lfs merge=lfs -text +Disney-Princess/example_videos/rabbit_disney_princess.mp4 filter=lfs diff=lfs merge=lfs -text +Dolly-Effect/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Dolly-Effect/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Dolly-Effect/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +Dolly-Effect/example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text +Dolly-Effect/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Electrify/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Electrify/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Electrify/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +Electrify/example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text +Electrify/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Explode/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Explode/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Explode/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +Explode/example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text +Explode/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Fus-Ro-Dah/example_videos/fus1.mp4 filter=lfs diff=lfs merge=lfs -text +Fus-Ro-Dah/example_videos/fus2.mp4 filter=lfs diff=lfs merge=lfs -text +Fus-Ro-Dah/example_videos/fus3.mp4 filter=lfs diff=lfs merge=lfs -text +Fus-Ro-Dah/example_videos/fus4.mp4 filter=lfs diff=lfs merge=lfs -text +Fus-Ro-Dah/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Gun-Shooting/example_videos/luffy_gun.mp4 filter=lfs diff=lfs merge=lfs -text +Gun-Shooting/example_videos/neymar_gun.mp4 filter=lfs diff=lfs merge=lfs -text +Gun-Shooting/example_videos/pika_gun.mp4 filter=lfs diff=lfs merge=lfs -text +Gun-Shooting/example_videos/woman_gun.mp4 filter=lfs diff=lfs merge=lfs -text +Gun-Shooting/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Hug-Jesus/example_videos/hug1.mp4 filter=lfs diff=lfs merge=lfs -text +Hug-Jesus/example_videos/hug2.mp4 filter=lfs diff=lfs merge=lfs -text +Hug-Jesus/example_videos/hug3.mp4 filter=lfs diff=lfs merge=lfs -text +Hug-Jesus/example_videos/hug4.mp4 filter=lfs diff=lfs merge=lfs -text +Hug-Jesus/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Hulk-Transformation/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Hulk-Transformation/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Hulk-Transformation/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +Hulk-Transformation/example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text +Hulk-Transformation/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Inflate/example_videos/apple_inflate.mp4 filter=lfs diff=lfs merge=lfs -text +Inflate/example_videos/cartoon_inflate.mp4 filter=lfs diff=lfs merge=lfs -text +Inflate/example_videos/man_inflate.mp4 filter=lfs diff=lfs merge=lfs -text +Inflate/example_videos/woman_inflate.mp4 filter=lfs diff=lfs merge=lfs -text +Inflate/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Jumpscare/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Jumpscare/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Jumpscare/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Jungle/example_videos/man1_jungle.gif filter=lfs diff=lfs merge=lfs -text +Jungle/example_videos/man1_jungle.mp4 filter=lfs diff=lfs merge=lfs -text +Jungle/example_videos/man2_jungle.mp4 filter=lfs diff=lfs merge=lfs -text +Laughing/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Laughing/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Laughing/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +Laughing/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Mona-Lisa/example_videos/man_mona_lisa.mp4 filter=lfs diff=lfs merge=lfs -text +Mona-Lisa/example_videos/woman_mona_lisa.mp4 filter=lfs diff=lfs merge=lfs -text +Muscle/example_videos/elon_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +Muscle/example_videos/man1_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +Muscle/example_videos/man2_muscle.gif filter=lfs diff=lfs merge=lfs -text +Muscle/example_videos/man2_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +Muscle/example_videos/trump_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +Muscle/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Painting/example_videos/dog_painting.mp4 filter=lfs diff=lfs merge=lfs -text +Painting/example_videos/man_painting.mp4 filter=lfs diff=lfs merge=lfs -text +Painting/example_videos/woman_painting.mp4 filter=lfs diff=lfs merge=lfs -text +Pirate-Captain/example_videos/cat_example.gif.gif filter=lfs diff=lfs merge=lfs -text +Pirate-Captain/example_videos/cat_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +Pirate-Captain/example_videos/goku_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +Pirate-Captain/example_videos/man_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +Pirate-Captain/example_videos/rabbit_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +Princess/example_videos/man_princess.mp4 filter=lfs diff=lfs merge=lfs -text +Princess/example_videos/woman_princess.mp4 filter=lfs diff=lfs merge=lfs -text +Puppy/example_videos/man1_puppy.mp4 filter=lfs diff=lfs merge=lfs -text +Puppy/example_videos/man2_puppy.mp4 filter=lfs diff=lfs merge=lfs -text +Puppy/example_videos/man3_puppy.mp4 filter=lfs diff=lfs merge=lfs -text +Robot-Face-Reveal/example_videos/robot1.mp4 filter=lfs diff=lfs merge=lfs -text +Robot-Face-Reveal/example_videos/robot2.mp4 filter=lfs diff=lfs merge=lfs -text +Robot-Face-Reveal/example_videos/robot3.mp4 filter=lfs diff=lfs merge=lfs -text +Robot-Face-Reveal/example_videos/robot4.mp4 filter=lfs diff=lfs merge=lfs -text +Robot-Face-Reveal/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Rotate/example_videos/bike_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +Rotate/example_videos/chair-rotate.gif filter=lfs diff=lfs merge=lfs -text +Rotate/example_videos/chair_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +Rotate/example_videos/figure_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +Rotate/example_videos/man_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +Rotate/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Samurai/example_videos/man_samurai.mp4 filter=lfs diff=lfs merge=lfs -text +Samurai/example_videos/rabbit_samurai.gif filter=lfs diff=lfs merge=lfs -text +Samurai/example_videos/rabbit_samurai.mp4 filter=lfs diff=lfs merge=lfs -text +Selfie-With-Younger-Self/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +Selfie-With-Younger-Self/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +Selfie-With-Younger-Self/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +Selfie-With-Younger-Self/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Snow-White/example_videos/man1_snow_white.mp4 filter=lfs diff=lfs merge=lfs -text +Snow-White/example_videos/man2_snow_white.mp4 filter=lfs diff=lfs merge=lfs -text +Squish/example_gifs/balloon_squish.gif filter=lfs diff=lfs merge=lfs -text +Squish/example_gifs/dog_squish.gif filter=lfs diff=lfs merge=lfs -text +Squish/example_gifs/person_squish.gif filter=lfs diff=lfs merge=lfs -text +Squish/example_gifs/rodent_squish.gif filter=lfs diff=lfs merge=lfs -text +Squish/example_gifs/tank_squish.gif filter=lfs diff=lfs merge=lfs -text +Squish/example_videos/balloon_squish.mp4 filter=lfs diff=lfs merge=lfs -text +Squish/example_videos/dog_squish.mp4 filter=lfs diff=lfs merge=lfs -text +Squish/example_videos/person_squish.mp4 filter=lfs diff=lfs merge=lfs -text +Squish/example_videos/rodent_squish.mp4 filter=lfs diff=lfs merge=lfs -text +Squish/example_videos/tank_squish.mp4 filter=lfs diff=lfs merge=lfs -text +Squish/squish_compilation_mmaudio.mp4 filter=lfs diff=lfs merge=lfs -text +Squish/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +Super-Saiyan/example_videos/super1.mp4 filter=lfs diff=lfs merge=lfs -text +Super-Saiyan/example_videos/super2.mp4 filter=lfs diff=lfs merge=lfs -text +Super-Saiyan/example_videos/super3.mp4 filter=lfs diff=lfs merge=lfs -text +Super-Saiyan/example_videos/super4.mp4 filter=lfs diff=lfs merge=lfs -text +Super-Saiyan/workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +VIP/example_videos/man_vip.mp4 filter=lfs diff=lfs merge=lfs -text +VIP/example_videos/thanos_vip.gif filter=lfs diff=lfs merge=lfs -text +VIP/example_videos/thanos_vip.mp4 filter=lfs diff=lfs merge=lfs -text +Warrior/example_videos/dog_warrior.gif filter=lfs diff=lfs merge=lfs -text +Warrior/example_videos/dog_warrior.mp4 filter=lfs diff=lfs merge=lfs -text +Warrior/example_videos/man1_warrior.mp4 filter=lfs diff=lfs merge=lfs -text +Warrior/example_videos/man2_warrior.mp4 filter=lfs diff=lfs merge=lfs -text +Zen/example_videos/man_zen.gif filter=lfs diff=lfs merge=lfs -text +Zen/example_videos/man_zen.mp4 filter=lfs diff=lfs merge=lfs -text +Zen/example_videos/rodent_zen.mp4 filter=lfs diff=lfs merge=lfs -text +Zen/example_videos/thanos_zen.mp4 filter=lfs diff=lfs merge=lfs -text +angry-face/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +angry-face/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +angry-face/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +angry-face/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +crying/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +crying/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +crying/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +crying/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +kissing/example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +kissing/example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +kissing/example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +kissing/workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Assassin/.gitattributes b/Assassin/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..bf280b0a53223230a7c51c982c2a950d37f62a28 --- /dev/null +++ b/Assassin/.gitattributes @@ -0,0 +1,41 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/dog_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man1_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rabbit_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/thanos_assassin.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/dog_assassin.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Assassin/README.md b/Assassin/README.md new file mode 100644 index 0000000000000000000000000000000000000000..6b532b0ed1aaf7540484089c40859ac31839b501 --- /dev/null +++ b/Assassin/README.md @@ -0,0 +1,127 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a portrait of a dog. Then, the 3p1c epic transformation starts. The dog is wearing a red coat, and the 3p1c epic transformation is complete. The dog is holding a gun in each hand. The dog has white hair and black gloves. + output: + url: example_videos/dog_assassin.mp4 +- text: >- + The video starts with a portrait of a man. Then, the 3p1c epic transformation starts. The man is wearing a red coat, and the 3p1c epic transformation is complete. The man is holding a gun in each hand. The man has white hair and black gloves. + output: + url: example_videos/man1_assassin.mp4 +- text: >- + The video starts with a portrait of a man. Then, the 3p1c epic transformation starts. The man is wearing a red coat, and the 3p1c epic transformation is complete. The man is holding a gun in each hand. The man has white hair and black gloves. + output: + url: example_videos/man2_assassin.mp4 +- text: >- + The video starts with a portrait of a rabbit. Then, the 3p1c epic transformation starts. The rabbit is wearing a red coat, and the 3p1c epic transformation is complete. The rabbit is holding a gun in each hand. The rabbit has white hair and black gloves. + output: + url: example_videos/rabbit_assassin.mp4 +- text: >- + The video starts with a portrait of purple Thanos from Marvel. Then, the 3p1c epic transformation starts. Thanos is wearing a red coat, and the 3p1c epic transformation is complete. Thanos is holding a gun in each hand. Thanos has white hair and black gloves. + output: + url: example_videos/thanos_assassin.mp4 +--- + +
+

Assassin Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become an assassin version of themselves!

+
+ +
+

Features

+ +
+ +
+

Community

+ +
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [assassin_45_epochs.safetensors](./assassin_45_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 3p1c epic transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into an assassin!
  • +
  • Epochs: 45
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Assassin/assassin_45_epochs.safetensors b/Assassin/assassin_45_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92f11c092d9dd880d6bd47bc6b3e6ffef9722a29 --- /dev/null +++ b/Assassin/assassin_45_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60c4d5dee5000a2bed2482911f17c26e4ba6d8e21af5ce29e20f5dea177016a +size 359257680 diff --git a/Assassin/example_videos/dog_assassin.gif b/Assassin/example_videos/dog_assassin.gif new file mode 100644 index 0000000000000000000000000000000000000000..314e588478ae3a800a515eb8036cbca599eedf80 --- /dev/null +++ b/Assassin/example_videos/dog_assassin.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9aceb16bc50da627f100f308e6a4f8fb37dc6aab2e397f02b14a6d148e27c3 +size 10216360 diff --git a/Assassin/example_videos/dog_assassin.mp4 b/Assassin/example_videos/dog_assassin.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e4d4f4ba3d649efea11318ba01d7492cd1068140 --- /dev/null +++ b/Assassin/example_videos/dog_assassin.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c344853b0e217a1c0cc278b07f6e1070a13f32d6d3bc6d98187de0751d1bce4 +size 794303 diff --git a/Assassin/example_videos/man1_assassin.mp4 b/Assassin/example_videos/man1_assassin.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cfdde99d9594e3d219241e65d0b5d492d838ade8 --- /dev/null +++ b/Assassin/example_videos/man1_assassin.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ec0b860393f64de1a9eeea065dcee1f2a61911ec92a478e3c09fa0ad3a3ce2 +size 551375 diff --git a/Assassin/example_videos/man2_assassin.mp4 b/Assassin/example_videos/man2_assassin.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..eadcd90b6ba4f660ca955e4b17541b0a5adcb1c0 --- /dev/null +++ b/Assassin/example_videos/man2_assassin.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37c00be11b226094ae35ce61e2be097464a13398751f32df423e30701ad7b36 +size 570323 diff --git a/Assassin/example_videos/rabbit_assassin.mp4 b/Assassin/example_videos/rabbit_assassin.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1df6ed5245f6c46580553283436de4d46f35bad4 --- /dev/null +++ b/Assassin/example_videos/rabbit_assassin.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ca77ae7c2d87fb616d1333feeaa69be924e68429ff46f11ea3c2382502c892c +size 405240 diff --git a/Assassin/example_videos/thanos_assassin.mp4 b/Assassin/example_videos/thanos_assassin.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0e95fa5f576ce6915a55586e25f222ad1f125134 --- /dev/null +++ b/Assassin/example_videos/thanos_assassin.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959db5d32c3a26c71bc2db87bceec9cd3bde70672f44959ccd1ec70ec1c37141 +size 851592 diff --git a/Assassin/wan_I2V_LoRA_workflow.json b/Assassin/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Assassin/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Baby/.gitattributes b/Baby/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..f42d4977e2c1df525158877866b6a4ce8ca6c384 --- /dev/null +++ b/Baby/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/goku_baby.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man_baby.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/woman_baby.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/goku_baby.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Baby/README.md b/Baby/README.md new file mode 100644 index 0000000000000000000000000000000000000000..de03d20cb5bc15b2eb2528d6ebd69f5749441988 --- /dev/null +++ b/Baby/README.md @@ -0,0 +1,123 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a studio portrait of Goku. Then the image shifts to the 848y baby effect, Goku is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of Goku is in the crib and seems excited and amused. + output: + url: example_videos/goku_baby.mp4 +- text: >- + The video starts with a studio portrait of an Asian man. Then the image shifts to the 848y baby effect, the man is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of the man is in the crib and seems excited and amused. + output: + url: example_videos/man_baby.mp4 +- text: >- + The video starts with a studio portrait of a woman. Then the image shifts to the 848y baby effect, the woman is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of the woman is in the crib and seems excited and amused. + output: + url: example_videos/woman_baby.mp4 +--- + +
+

Baby Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image into a baby!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a baby!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [baby_50_epochs.safetensors](./baby_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 848y baby effect

+
+ +
+

Prompt Template

+

For best results, use this prompt structure:

+
+ The video starts with a studio portrait of a [object]. Then the image shifts to the 848y baby effect, the [object] is in front of a crib, surrounded by toys. Finally, the 848y baby effect is shown again in a different location. The 848y baby version of the [object] is in the crib and seems excited and amused. +
+

Simply replace [object] with whatever you want to see as a baby!

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people becoming a baby!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Baby/baby_50_epochs.safetensors b/Baby/baby_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca89a70b4c271cff5b6ac09f4f72fce0bef8b0c2 --- /dev/null +++ b/Baby/baby_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8592c6fdb63e937e8d9a22ed1b73b7e84acc82931a537f5e5bf7ac8a68d57e +size 359257680 diff --git a/Baby/example_videos/goku_baby.gif b/Baby/example_videos/goku_baby.gif new file mode 100644 index 0000000000000000000000000000000000000000..604ff4570e85cd77c04c3225d3f4e304e18611f3 --- /dev/null +++ b/Baby/example_videos/goku_baby.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b02cb9ab9fc986fc4dbf08febbffdf14ca42ad55e8f44d61e12836aa4c81cc +size 11609604 diff --git a/Baby/example_videos/goku_baby.mp4 b/Baby/example_videos/goku_baby.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1105a52ec9b1b6180e62306725f2480521845bc6 --- /dev/null +++ b/Baby/example_videos/goku_baby.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b942842569a73eac10e7796090abe09edcedc944ae8cc7079b20715f445b921b +size 1495837 diff --git a/Baby/example_videos/man_baby.mp4 b/Baby/example_videos/man_baby.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c593306a366ed379768996d5f591011c5fb08c17 --- /dev/null +++ b/Baby/example_videos/man_baby.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdbb9750fd55aa5aaf8dba3ba934d7fa49f497452e9f7c1e9c6e8e28179375b +size 408642 diff --git a/Baby/example_videos/woman_baby.mp4 b/Baby/example_videos/woman_baby.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..083e11b1c6cacf279f9994f9776d8fb5b3c8d30e --- /dev/null +++ b/Baby/example_videos/woman_baby.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827858c45bbafefc47d6e164e32c04a44bbcfc4cb691346a40ccb3d15dbe3378 +size 445881 diff --git a/Baby/wan_I2V_LoRA_workflow.json b/Baby/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..2018b1627d9ae9f2c4ace5d911dff8e55637abf8 --- /dev/null +++ b/Baby/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000004, + "offset": { + "0": 38.08346176147461, + "1": 477.617919921875 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Bride/.gitattributes b/Bride/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..32aaeeb0b2c3477a56f10d777dd8d000a4042d95 --- /dev/null +++ b/Bride/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man_bride.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rabbit_bride.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rodent_bride.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rabbit_bride.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Bride/README.md b/Bride/README.md new file mode 100644 index 0000000000000000000000000000000000000000..5e1aca60d19e3eea4994e0c6a65b1d5cffeb1b86 --- /dev/null +++ b/Bride/README.md @@ -0,0 +1,123 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a close-up of a smiling man in a blue button-down shirt, then the 8r1d3 bride effect happens. The man is now in a white lace wedding dress, smiling, with a bouquet of white flowers in front of a blurred wooden background. + output: + url: example_videos/man_bride.mp4 +- text: >- + The video begins with a portrait of a rodent, then the 8r1d3 bride effect occurs. The rodent is now in a white wedding dress, holding a bouquet, with a sunny, warm beige background. + output: + url: example_videos/rodent_bride.mp4 +- text: >- + The video begins with a portrait of a bunny rabbit, then the 8r1d3 bride effect occurs. The bunny rabbit is now in a white wedding dress, holding a bouquet, with a sunny, warm beige background. + output: + url: example_videos/rabbit_bride.mp4 +--- + +
+

Bride Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image to become a bride. The effect works on a wide variety of objects, from animals to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a bride!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [bride_50_epochs.safetensors](./bride_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 8r1d3 bride effect.

+
+ +
+

Prompt Template

+

For best results, use this prompt structure:

+
+ The video begins with a portrait of a [object], then the 8r1d3 bride effect occurs. The [object] is now in a white wedding dress, holding a bouquet, with a sunny, warm beige background. +
+

Simply replace [object] with whatever you want to see as a bride!

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people becoming a bride!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Bride/bride_50_epochs.safetensors b/Bride/bride_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e341a4f75912a827599953791ba2d3afeec2a9ef --- /dev/null +++ b/Bride/bride_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e7ce29d8a4faa527f0860b737e79de6340a99cef8549772abd0f4a13612da3 +size 359257680 diff --git a/Bride/example_videos/man_bride.mp4 b/Bride/example_videos/man_bride.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0ffe5b1eac7a56739bd99bb223e854489641ebd2 --- /dev/null +++ b/Bride/example_videos/man_bride.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c9708acbdbb5ad5130b61defc990890ebed0cfa50fd967563da8878e7c18186 +size 650695 diff --git a/Bride/example_videos/rabbit_bride.gif b/Bride/example_videos/rabbit_bride.gif new file mode 100644 index 0000000000000000000000000000000000000000..0990c9b7e6370b02e39731c28b1b68c95ddb87d5 --- /dev/null +++ b/Bride/example_videos/rabbit_bride.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77929494f5c5bcd7bed6c61e4f41d3f47dac65b7b64c6d0279d6f8fa4b1a7b9 +size 5344368 diff --git a/Bride/example_videos/rabbit_bride.mp4 b/Bride/example_videos/rabbit_bride.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8596ab28fc8f05cca72b5db609fdb6a0c5a0ca49 --- /dev/null +++ b/Bride/example_videos/rabbit_bride.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6081ea25ab3b0b790097e73c5b1efee1dd748e067789154ae1bb1c38e27162fd +size 486353 diff --git a/Bride/example_videos/rodent_bride.mp4 b/Bride/example_videos/rodent_bride.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..916d86bbc6e896884cbb45ac521b00ea0c7df85b --- /dev/null +++ b/Bride/example_videos/rodent_bride.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0540fdd0c68a8fcd1d0143390e7ea9b009fde879765341f653ebd5ef01874575 +size 1084275 diff --git a/Bride/wan_I2V_LoRA_workflow.json b/Bride/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..2018b1627d9ae9f2c4ace5d911dff8e55637abf8 --- /dev/null +++ b/Bride/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000004, + "offset": { + "0": 38.08346176147461, + "1": 477.617919921875 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Cakeify/.gitattributes b/Cakeify/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..1652f67c0525851547f64db40e0724f80622749c --- /dev/null +++ b/Cakeify/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow/Screenshot[[:space:]]2025-03-11[[:space:]]140112.png filter=lfs diff=lfs merge=lfs -text +workflow/cakeify_workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example[[:space:]]videos/cat_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example[[:space:]]videos/puppy_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example[[:space:]]videos/timeberland_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example[[:space:]]videos/woman_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example[[:space:]]gifs/cat_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example[[:space:]]gifs/puppy_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example[[:space:]]gifs/timberland_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example[[:space:]]gifs/woman_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/cat_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/puppy_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/timberland_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/woman_cakeify.gif filter=lfs diff=lfs merge=lfs -text +example_videos/cat_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/puppy_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/timeberland_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/woman_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/timberland_cakeify.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Cakeify/README.md b/Cakeify/README.md new file mode 100644 index 0000000000000000000000000000000000000000..1cea6aa5a574d9133b17f4b281889cbb53cd737b --- /dev/null +++ b/Cakeify/README.md @@ -0,0 +1,145 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video opens on a puppy. A knife, held by a hand, is coming into frame + and hovering over the puppy. The knife then begins cutting into the puppy to + c4k3 cakeify it. As the knife slices the puppy open, the inside of the puppy + is revealed to be cake with chocolate layers. The knife cuts through and the + contents of the puppy are revealed. + output: + url: example_videos/puppy_cakeify.mp4 +- text: >- + The video opens on a woman. A knife, held by a hand, is coming into frame + and hovering over the woman. The knife then begins cutting into the woman to + c4k3 cakeify it. As the knife slices the woman open, the inside of the woman + is revealed to be cake with chocolate layers. The knife cuts through and the + contents of the woman are revealed. + output: + url: example_videos/woman_cakeify.mp4 +- text: >- + The video opens on a timberland boot. A knife, held by a hand, is coming + into frame and hovering over the timberland boot. The knife then begins + cutting into the timberland boot to c4k3 cakeify it. As the knife slices the + timberland boot open, the inside of the timberland boot is revealed to be + cake with chocolate layers. The knife cuts through and the contents of the + timberland boot are revealed. + output: + url: example_videos/timberland_cakeify.mp4 +- text: >- + The video opens on a cat. A knife, held by a hand, is coming into frame and + hovering over the cat. The knife then begins cutting into the cat to c4k3 + cakeify it. As the knife slices the cat open, the inside of the cat is + revealed to be cake with chocolate layers. The knife cuts through and the + contents of the cat are revealed. + output: + url: example_videos/cat_cakeify.mp4 +--- + +
+

Cakeify Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to cakeify any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of it being cakeified
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [cakeify_16_epochs.safetensors](./cakeify_16_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: c4k3 cakeify it

+
+ +
+

Prompt Template

+

For best results, use this prompt structure:

+
+ The video opens on a [object]. A knife, held by a hand, is coming into frame and hovering over the [object]. The knife then begins cutting into the [object] to c4k3 cakeify it. As the knife slices the [object] open, the inside of the [object] is revealed to be cake with chocolate layers. The knife cuts through and the contents of the [object] are revealed. +
+

Simply replace [object] with whatever you want to see cakeified!

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: 1 minute of video (13 short clips of things being cakeified, each clip captioned separately)
  • +
  • Epochs: 16
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Cakeify/cakeify_16_epochs.safetensors b/Cakeify/cakeify_16_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2dc604ddcd212e15030358247e325c90bc770562 --- /dev/null +++ b/Cakeify/cakeify_16_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4078cd32c45ad6f0206b87bd8de7e25700bd8419b9c0e0267bb828aec7eb6bf1 +size 359257680 diff --git a/Cakeify/example_gifs/cat_cakeify.gif b/Cakeify/example_gifs/cat_cakeify.gif new file mode 100644 index 0000000000000000000000000000000000000000..4ec71a583e5e69019639fb52a92c3cb047c59e39 --- /dev/null +++ b/Cakeify/example_gifs/cat_cakeify.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92819e20e2994f40073a5d094816de944557440dff72a106ae97374e90d18c0f +size 4330732 diff --git a/Cakeify/example_gifs/puppy_cakeify.gif b/Cakeify/example_gifs/puppy_cakeify.gif new file mode 100644 index 0000000000000000000000000000000000000000..6b54da00626cc4820d5bf7fc281f83e34759282f --- /dev/null +++ b/Cakeify/example_gifs/puppy_cakeify.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5725b690d0adedaed02dc3755cc1d72c6291bcb0a52857b243fc2d28e088b069 +size 3943007 diff --git a/Cakeify/example_gifs/timberland_cakeify.gif b/Cakeify/example_gifs/timberland_cakeify.gif new file mode 100644 index 0000000000000000000000000000000000000000..9072b2b4bdfda2ed6231c0c06af2ac83569dec6f --- /dev/null +++ b/Cakeify/example_gifs/timberland_cakeify.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffb68dd50d1e19cdd7649dfdf328f1ff34a78648b3d72629d4defab19afc106 +size 2543156 diff --git a/Cakeify/example_gifs/woman_cakeify.gif b/Cakeify/example_gifs/woman_cakeify.gif new file mode 100644 index 0000000000000000000000000000000000000000..d5f3093bec08b7fbcfd70c1f0a8ce3e064600089 --- /dev/null +++ b/Cakeify/example_gifs/woman_cakeify.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04320f23c217877acbb232190ca17fcd58b2d7cfb2b52f1afd98da5681d9330 +size 3215680 diff --git a/Cakeify/example_videos/cat_cakeify.mp4 b/Cakeify/example_videos/cat_cakeify.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f51f42f375c186d989e52740c2b05310ebe0447b --- /dev/null +++ b/Cakeify/example_videos/cat_cakeify.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7cebaeb01207d7cdb928a5a0046ff410623fa8c59ba3f3525317347572a67e4 +size 608660 diff --git a/Cakeify/example_videos/puppy_cakeify.mp4 b/Cakeify/example_videos/puppy_cakeify.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..55c63f398733b241231fe94376f92df8647922d3 --- /dev/null +++ b/Cakeify/example_videos/puppy_cakeify.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeeaeb90a4d2c3d3ea13016ac197dc03412ba83ed0ce7091ff7ddf1bc9f40570 +size 479155 diff --git a/Cakeify/example_videos/timberland_cakeify.mp4 b/Cakeify/example_videos/timberland_cakeify.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1802df4d0e624748bd596f8a18efb740556ae6c2 --- /dev/null +++ b/Cakeify/example_videos/timberland_cakeify.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a73e25c08f7e5a642197071334e0e5e332f3b2a2f57a8a512755c8b02320659 +size 513042 diff --git a/Cakeify/example_videos/woman_cakeify.mp4 b/Cakeify/example_videos/woman_cakeify.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4eb867d2cd10b23ffad3540428210276dd5d62e7 --- /dev/null +++ b/Cakeify/example_videos/woman_cakeify.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae053ce22dd1fd64586c2616dfcd93ea7c1dfb277faa7181026d4b0dfadf61c +size 268669 diff --git a/Cakeify/workflow/cakeify_workflow_screenshot.png b/Cakeify/workflow/cakeify_workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..eef00c5750d49891a68d7a44d1d8770675cea325 --- /dev/null +++ b/Cakeify/workflow/cakeify_workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06654fbc6ebabd50173d1cdad89566f7706326fd447f97be38d3fe1955d47a9d +size 717382 diff --git a/Cakeify/workflow/wan_img2vid_lora_workflow.json b/Cakeify/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Cakeify/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Cartoon_Jaw_Drop/.gitattributes b/Cartoon_Jaw_Drop/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..b2ef8347a4eaa53aab5388ff3daf6161f58e7937 --- /dev/null +++ b/Cartoon_Jaw_Drop/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Cartoon_Jaw_Drop/README.md b/Cartoon_Jaw_Drop/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0237481038aecde9831ab31431511f9f32665da9 --- /dev/null +++ b/Cartoon_Jaw_Drop/README.md @@ -0,0 +1,118 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video shows Pluto the dog, wearing a red collar, who is smiling wide, then his mouth transforms into a dr0p_j88 comical jaw drop, extending down in a long, rectangular shape, and revealing his tongue and teeth. + output: + url: example_videos/1.mp4 +- text: >- + The video shows a man with a neutral expression. Suddenly his jaw extremely widens to create a dr0p_j88 comical jaw drop. + output: + url: example_videos/2.mp4 +- text: >- + The video shows the man with a subtle smile, then suddenly his mouth drops open wide in a dr0p_j88 comical jaw drop, showing his teeth and tongue. + output: + url: example_videos/3.mp4 +--- + +
+

Cartoon Jaw Drop LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to apply the Cartoon Jaw Drop effect to images!

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [cartoon_jaw_drop_50_epochs.safetensors](./lcartoon_jaw_drop_50_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: dr0p_j88 comical jaw drop

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 50 seconds of video comprised of 12 short clips (each clip captioned separately) of cartoon jaw drops.
  • +
  • Epochs: 5
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Cartoon_Jaw_Drop/cartoon_jaw_drop_50_epochs.safetensors b/Cartoon_Jaw_Drop/cartoon_jaw_drop_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e55d67412fe06a5d1b8590ab6052a74cc100ca16 --- /dev/null +++ b/Cartoon_Jaw_Drop/cartoon_jaw_drop_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5cfc7fca88afbae04ef03b3d72455b28b226b81448639e3f18d779978c30fb +size 359257680 diff --git a/Cartoon_Jaw_Drop/example_videos/.DS_Store b/Cartoon_Jaw_Drop/example_videos/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6 Binary files /dev/null and b/Cartoon_Jaw_Drop/example_videos/.DS_Store differ diff --git a/Cartoon_Jaw_Drop/example_videos/1.mp4 b/Cartoon_Jaw_Drop/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9d81177c1a9248f4f3b605eb8f6681aff03439aa --- /dev/null +++ b/Cartoon_Jaw_Drop/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65aad27670e4ce97cdd447626385cb5f3cafc05469f739de89bae04f3abda060 +size 270311 diff --git a/Cartoon_Jaw_Drop/example_videos/2.mp4 b/Cartoon_Jaw_Drop/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..84df623f431875ee2762092aa35bd873afa764d7 --- /dev/null +++ b/Cartoon_Jaw_Drop/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43b9d8fd344621b1273166ccf20f6bf02df2171be13f09e3a5dd3585a66a262 +size 301389 diff --git a/Cartoon_Jaw_Drop/example_videos/3.mp4 b/Cartoon_Jaw_Drop/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..edffedfabdf3e8a8a881a91d3bdfd63cad243bb9 --- /dev/null +++ b/Cartoon_Jaw_Drop/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9adfa7efdbda9403937ff2ee7212ac66be180cf560bd80eced41a80346d40845 +size 286028 diff --git a/Cartoon_Jaw_Drop/workflow_I2V/wan_img2vid_lora_workflow.json b/Cartoon_Jaw_Drop/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Cartoon_Jaw_Drop/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Cartoon_Jaw_Drop/workflow_I2V/workflow_screenshot.png b/Cartoon_Jaw_Drop/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Cartoon_Jaw_Drop/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Classy/.gitattributes b/Classy/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..1c9e86d7c3cf025f0d1abf6308a814828ecb2fcf --- /dev/null +++ b/Classy/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man1_classy.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_classy.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Classy/README.md b/Classy/README.md new file mode 100644 index 0000000000000000000000000000000000000000..590ff89707a6aaf8d113f363403068bf69694eb3 --- /dev/null +++ b/Classy/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a man. The c1455y classy transformation occurs and the man is now wearing a light blue dress with spaghetti straps. He is holding a small white envelope and a flower in his hands. The man is smiling, and looking at the camera. His arm is resting on a wooden table, and the background is gold and brown. The man is seated. + output: + url: example_videos/man1_classy.mp4 +- text: >- + The video starts with a man wearing a suit. The c1455y classy transformation occurs and the man is now wearing a light blue dress with spaghetti straps. He is holding a small white envelope and a flower in his hands. The man is smiling, and looking at the camera. His arm is resting on a wooden table, and the background is gold and brown. The man is seated. + output: + url: example_videos/man2_classy.mp4 +--- + +
+

Classy Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become classy!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a female classy version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [classy_45_epochs.safetensors](./classy_45_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: c1455y classy transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a classy woman!
  • +
  • Epochs: 45
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Classy/classy_45_epochs.safetensors b/Classy/classy_45_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a694cf5ca1814f9706a91a4bc23445f7514a10c --- /dev/null +++ b/Classy/classy_45_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af0d25174d99f4d93691bd1e1d027c337541f1b9428f1d78ff494e489576732 +size 359257680 diff --git a/Classy/example_videos/man1_classy.mp4 b/Classy/example_videos/man1_classy.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ea4e8939c41eb925579d50405c5f2db41181dd5f --- /dev/null +++ b/Classy/example_videos/man1_classy.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7525bdc21d9b98ea3c5344943f122d8cb532b65f190605293106dcd5ce6d5857 +size 876934 diff --git a/Classy/example_videos/man2_classy.mp4 b/Classy/example_videos/man2_classy.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ce9ece511c353eb4829b7a84d40f44fcd2865dea --- /dev/null +++ b/Classy/example_videos/man2_classy.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9c5bcf88ac3264ea9f1075d7bf79b657291d158ae3eb167b917b5a69101769 +size 616508 diff --git a/Classy/wan_I2V_LoRA_workflow.json b/Classy/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Classy/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Crush/.gitattributes b/Crush/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..873cc5dbb79b4d2cc63e531a06157c59faae4ac8 --- /dev/null +++ b/Crush/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/chicken_crush.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/coke_crush.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man_crush.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/tank_crush.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Crush/README.md b/Crush/README.md new file mode 100644 index 0000000000000000000000000000000000000000..3673435a7d4e178d4dd9b5246fb734fe261e0fa6 --- /dev/null +++ b/Crush/README.md @@ -0,0 +1,140 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with a tank. A hydraulic press positioned above slowly + descends towards the tank. Upon contact, the hydraulic press c5us4 crushes + it, deforming and flattening the tank, causing the tank to collapse inward + until the tank is no longer recognizable. + output: + url: example_videos/tank_crush.mp4 +- text: >- + The video begins with a man. A hydraulic press positioned above slowly + descends towards the man. Upon contact, the hydraulic press c5us4 crushes + it, deforming and flattening the man, causing the man to collapse inward + until the man is no longer recognizable. + output: + url: example_videos/man_crush.mp4 +- text: >- + The video begins with a chicken. A hydraulic press positioned above slowly + descends towards the chicken. Upon contact, the hydraulic press c5us4 + crushes it, deforming and flattening the chicken, causing the chicken to + collapse inward until the chicken is no longer recognizable. + output: + url: example_videos/chicken_crush.mp4 +- text: >- + The video begins with a coke. A hydraulic press positioned above slowly + descends towards the coke. Upon contact, the hydraulic press c5us4 crushes + it, deforming and flattening the coke, causing the coke to collapse inward + until the coke is no longer recognizable. + output: + url: example_videos/coke_crush.mp4 +--- + +
+

Crush Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to crush any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of it being crushed
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [crush_20_epochs.safetensors](./crush_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: c5us4 crushes it

+
+ +
+

Prompt Template

+

For best results, use this prompt structure:

+
+ The video begins with a [object]. A hydraulic press positioned above slowly descends towards the [object]. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the [object], causing the [object] to collapse inward until the [object] is no longer recognizable. +
+

Simply replace [object] with whatever you want to see crushed!

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 1.5 minutes of video comprised of 20 short clips (each clip captioned separately) of things being crushed by a hydraulic press
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Crush/crush_20_epochs.safetensors b/Crush/crush_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1db44b52dfaa03724fa2f398f4e9aa3c21640731 --- /dev/null +++ b/Crush/crush_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d67e9600edbd0be40febcdb262a0fe145a5962767ac23c644c4a42df2e4ec3 +size 359257680 diff --git a/Crush/example_videos/chicken_crush.mp4 b/Crush/example_videos/chicken_crush.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ba4b9ff5b1186215cc8493c4f59eb21112c295a6 --- /dev/null +++ b/Crush/example_videos/chicken_crush.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ce5602e718205709885df78f36add49d70edece8bc7779b421ea91a198c1ec +size 436848 diff --git a/Crush/example_videos/coke_crush.mp4 b/Crush/example_videos/coke_crush.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..53d8a8c450a7cc0682144bb33e0338ba46d3b26b --- /dev/null +++ b/Crush/example_videos/coke_crush.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5458ee3287847addc56d9703936566c426971021c4604f01db8c329039b4f380 +size 786568 diff --git a/Crush/example_videos/man_crush.mp4 b/Crush/example_videos/man_crush.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5141c3fdfce0176e4bfa69948688e314d9c388e4 --- /dev/null +++ b/Crush/example_videos/man_crush.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3f72a2f9d48fe043034c2839fdc9926c42baa2eece66c906ff0c4ec5a14e61 +size 365523 diff --git a/Crush/example_videos/tank_crush.mp4 b/Crush/example_videos/tank_crush.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7ea7aa699061aac7ec6065b39ba33eaedb04fbca --- /dev/null +++ b/Crush/example_videos/tank_crush.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c6f91f1e58a914775e0ca1e1603dd85c7cc6f9165e2db18d48a55086aab163d +size 690710 diff --git a/Crush/workflow/wan_img2vid_lora_workflow.json b/Crush/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Crush/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Crush/workflow/workflow_screenshot.png b/Crush/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..36e2eaebbdb885d6705a3ce34910172889fd4cbf --- /dev/null +++ b/Crush/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99c8ec95a0e9f735dbbbfa3fd5886a6886f52a1b97385ebbb9bef36e95033ba +size 609890 diff --git a/Deflate/.gitattributes b/Deflate/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..a6d18521bd3f23fbecd99210b5de671cdb4db4b8 --- /dev/null +++ b/Deflate/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/balloon_deflate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/cat_deflate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/lamp_deflate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man_deflate.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Deflate/README.md b/Deflate/README.md new file mode 100644 index 0000000000000000000000000000000000000000..5941bf61a8d928509a6d800336c9b155b3eff66e --- /dev/null +++ b/Deflate/README.md @@ -0,0 +1,136 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video opens with a man. As the video progresses, the man begins to + d3d1at3 deflate it, gradually shrinking and losing shape, eventually + flattening completely into a lifeless, deflated mass on the ground. + output: + url: example_videos/man_deflate.mp4 +- text: >- + The video opens with a lamp. As the video progresses, the lamp begins to + d3d1at3 deflate it, gradually shrinking and losing shape, eventually + flattening completely into a lifeless, deflated mass on the ground. + output: + url: example_videos/lamp_deflate.mp4 +- text: >- + The video opens with a balloon. As the video progresses, the balloon begins + to d3d1at3 deflate it, gradually shrinking and losing shape, eventually + flattening completely into a lifeless, deflated mass on the ground. + output: + url: example_videos/balloon_deflate.mp4 +- text: >- + The video opens with a cat. As the video progresses, the cat begins to + d3d1at3 deflate it, gradually shrinking and losing shape, eventually + flattening completely into a lifeless, deflated mass on the ground. + output: + url: example_videos/cat_deflate.mp4 +--- + +
+

Deflate Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to deflate any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of it being deflated
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [deflate_20_epochs.safetensors](./deflate_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: d3d1at3 deflate it

+
+ +
+

Prompt Template

+

For best results, use this prompt structure:

+
+ The video opens with a [object]. As the video progresses, the [object] begins to d3d1at3 deflate it, gradually shrinking and losing shape, eventually flattening completely into a lifeless, deflated mass on the ground. +
+

Simply replace [object] with whatever you want to see deflated!

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 1.5 minutes of video comprised of 20 short clips (each clip captioned separately) of things being deflated
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Deflate/deflate_20_epochs.safetensors b/Deflate/deflate_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ae860815059a48adaadf4ec6fc9e05c51216b46 --- /dev/null +++ b/Deflate/deflate_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb4107dea9966b3533613fb3bc625d8b6bfa7cbf68985f37a33c04aebe53e46 +size 359257680 diff --git a/Deflate/example_videos/balloon_deflate.mp4 b/Deflate/example_videos/balloon_deflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..da65ecacb4b168d454b9030db4e31bd06ef58a6c --- /dev/null +++ b/Deflate/example_videos/balloon_deflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cd084e6eac0611709874a4a2af51ddacd7911bb6f632ef1f1e31ffa394d68db +size 565095 diff --git a/Deflate/example_videos/cat_deflate.mp4 b/Deflate/example_videos/cat_deflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..db64a1ea6e48ac185e1428d830c351d91042b2aa --- /dev/null +++ b/Deflate/example_videos/cat_deflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8392c3addd2cb230e33ffc29a61a2413610fd40129607b2befa6665fd64a681 +size 650407 diff --git a/Deflate/example_videos/lamp_deflate.mp4 b/Deflate/example_videos/lamp_deflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..905634caaf97ba92a3a3b187f3ecebeb1a0dad4f --- /dev/null +++ b/Deflate/example_videos/lamp_deflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3228c757cb2e7d19e9c659d0f7e7597f59552d820bda496f36791ab8eba78682 +size 809201 diff --git a/Deflate/example_videos/man_deflate.mp4 b/Deflate/example_videos/man_deflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1dad9cc50a5d42f76d6debcd8ab46b929c0c0a21 --- /dev/null +++ b/Deflate/example_videos/man_deflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16642cf2d919a77e1e19f840c8d4b461e7f49bdc254d415a492664cd3cc944dd +size 321210 diff --git a/Deflate/workflow/wan_img2vid_lora_workflow.json b/Deflate/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Deflate/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Deflate/workflow/workflow_screenshot.png b/Deflate/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..bd484e5663803de085dd9a804d39079b2a50bf92 --- /dev/null +++ b/Deflate/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:496185e04690b7d9267054026faa8fa570bc8a3662d9418063683383d6f0ff6a +size 479255 diff --git a/Disney-Princess/.gitattributes b/Disney-Princess/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..04f00114ae89f56b59ee4bb3e7d13c9c1548e46a --- /dev/null +++ b/Disney-Princess/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man_disney_princess.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rabbit_disney_princess.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Disney-Princess/README.md b/Disney-Princess/README.md new file mode 100644 index 0000000000000000000000000000000000000000..1c335db847374d303cd0231b946ac133e0e5c2ab --- /dev/null +++ b/Disney-Princess/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a portrait of a rabbit There's a d15n3y Disney princess transformation, the rabbit is now wearing a blue dress. The camera pans out to reveal the background as a brown, classical style hallway. There are white butterflies that appear to be falling. The rabbit still wears the dress from the d15n3y Disney princess transformation. + output: + url: example_videos/rabbit_disney_princess.mp4 +- text: >- + The video starts with a portrait of a man. There's a d15n3y Disney princess transformation, the man is now wearing a blue dress. The camera pans out to reveal the background as a brown, classical style hallway. There are white butterflies that appear to be falling. The man still wears the dress from the d15n3y Disney princess transformation. + output: + url: example_videos/man_disney_princess.mp4 +--- + +
+

Disney Princess Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a Disney Princess version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a Disney Princess version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [disney_princess_45_epochs.safetensors](./disney_princess_45_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: d15n3y Disney princess transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a Disney princess!
  • +
  • Epochs: 45
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Disney-Princess/disney_princess_45_epochs.safetensors b/Disney-Princess/disney_princess_45_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c115f9326d9a5477ab7481112717783c5df02610 --- /dev/null +++ b/Disney-Princess/disney_princess_45_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8776f9172e5e600c39b849a970ce5732b4a73083af233d6337cd3fbcb0792228 +size 359257680 diff --git a/Disney-Princess/example_videos/man_disney_princess.mp4 b/Disney-Princess/example_videos/man_disney_princess.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b698ac5cd03f0462ae94220cc7f152739135eb5e --- /dev/null +++ b/Disney-Princess/example_videos/man_disney_princess.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff700a0a8cb99ecf2262b801d70c1235473f0226186f1789d1420c26a6c3ae4e +size 630558 diff --git a/Disney-Princess/example_videos/rabbit_disney_princess.mp4 b/Disney-Princess/example_videos/rabbit_disney_princess.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fbae61144ee232ce0d83f51dc62fb98fa6632e93 --- /dev/null +++ b/Disney-Princess/example_videos/rabbit_disney_princess.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92482ba765424807ced47b38de45957ab3456066f1af8edfb08395a5efbc9488 +size 637558 diff --git a/Disney-Princess/wan_I2V_LoRA_workflow.json b/Disney-Princess/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Disney-Princess/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Dolly-Effect/.gitattributes b/Dolly-Effect/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..69eecd3645ecf7956ddcc3b1aa85a43fdedc6d53 --- /dev/null +++ b/Dolly-Effect/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Dolly-Effect/README.md b/Dolly-Effect/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e4b77c9d2c3c727cd665187d88d8abc34d2cd4d0 --- /dev/null +++ b/Dolly-Effect/README.md @@ -0,0 +1,122 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + d011Ye33ect dolly effect. The video begins with a close-up of the man’s steely gaze as he stands in a dusty cemetery, a cigar clenched in his mouth. The camera slowly zooms out, keeping his face centered while the background stretches—revealing crosses, gravestones, and the wide open desert behind him. The dolly effect intensifies the tension of the western standoff. + output: + url: example_videos/1.mp4 +- text: >- + d011Ye33ect dolly effect. The video begins with a close-up of the woman's face, her expression calm and confident. As the camera zooms out slowly, her poised figure in the iconic seated position is revealed. The background — a sterile, cold interrogation room — subtly distorts with the dolly effect, enhancing the intensity and drawing focus to her unwavering gaze. + output: + url: example_videos/2.mp4 +- text: >- + d011Ye33ect dolly effect. The video begins with a close-up of the man’s intense expression, his mouth open mid-shout. As the camera slowly zooms out, his battle stance and outstretched arms are revealed in full. The dolly effect causes the background of the ancient coliseum to shift and distort slightly, emphasizing the tension and power of the moment. + output: + url: example_videos/3.mp4 +- text: >- + d011Ye33ect dolly effect. The video starts with a close-up of the dogs’ faces as they share a single strand of spaghetti. The camera slowly zooms out, revealing the candlelit table, checkered tablecloth, and surrounding alleyway. The dolly effect keeps the dogs centered as the background stretches subtly, enhancing the intimacy of the moment. + output: + url: example_videos/4.mp4 +--- + +
+

Dolly Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to apply a Dolly zoom camera effect on any image subject! This model also works on T2V, with a very similar prompting style, although the I2V application is more robust.

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [dolly_25_epochs.safetensors](./dolly_25_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: d011Ye33ect dolly effect

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 2 minutes of video comprised of 40 short clips (each clip captioned separately) of various dolly effect scenes
  • +
  • Epochs: 25
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Dolly-Effect/dolly_25_epochs.safetensors b/Dolly-Effect/dolly_25_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7d9a8f08e21f93582d06df41633dbb330dd517f --- /dev/null +++ b/Dolly-Effect/dolly_25_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:045011e6abf53e66b901fe4811046c568563f5dc8f41cafec181ffd86032b85b +size 359257680 diff --git a/Dolly-Effect/example_videos/1.mp4 b/Dolly-Effect/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d5546ed2edbb317b7657a4efeaae9a1753cef1f1 --- /dev/null +++ b/Dolly-Effect/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137bec4d3cdebcf0cdf30f0a2b8165eddeed82264c2d61b37116a7a4507ecfc7 +size 984819 diff --git a/Dolly-Effect/example_videos/2.mp4 b/Dolly-Effect/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f642a2db0ad93a110a31a0f02d7476aa6b2050b3 --- /dev/null +++ b/Dolly-Effect/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a4d20776922a498b892114f370d9b1f67078f56e8932ecb63a090b0a548a9e +size 446743 diff --git a/Dolly-Effect/example_videos/3.mp4 b/Dolly-Effect/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f7a1987ff73a90cf191a617365ad63f365f7d424 --- /dev/null +++ b/Dolly-Effect/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c0211b40575cd3d4128df9476e821d15524603713bf4f2fb24ccdcb23c2306 +size 1167350 diff --git a/Dolly-Effect/example_videos/4.mp4 b/Dolly-Effect/example_videos/4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..db730266fc1a88fb55772c6b4d73021ecf9c5714 --- /dev/null +++ b/Dolly-Effect/example_videos/4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df1c3ca453d6740bbd865ec3fed2690ba70344f7d9cddca4baeaf1529e23983 +size 886414 diff --git a/Dolly-Effect/workflow_I2V/wan_img2vid_lora_workflow.json b/Dolly-Effect/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Dolly-Effect/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Dolly-Effect/workflow_I2V/workflow_screenshot.png b/Dolly-Effect/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Dolly-Effect/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Electrify/.gitattributes b/Electrify/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..69eecd3645ecf7956ddcc3b1aa85a43fdedc6d53 --- /dev/null +++ b/Electrify/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Electrify/README.md b/Electrify/README.md new file mode 100644 index 0000000000000000000000000000000000000000..13d0064d1115800885145a35a9baa3e7abd0735b --- /dev/null +++ b/Electrify/README.md @@ -0,0 +1,122 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + E13c7r1c electricity effect streaks through a swirling storm cloud, revealing the shadowy outline of a massive, winged beast. Each lightning strike illuminates its glowing blue eyes, and for a brief moment, its metal-plated wings shimmer before vanishing back into the storm. + output: + url: example_videos/1.mp4 +- text: >- + The video begins with a close-up shot of a young man's face. His eyes are glowing blue, and there is a bright blue e13c7r1c electricity effect emanating from his body. The e13c7r1c electricity effect grows more intense, covering his body, and the man starts to levitate. The background is dark and blurry. + output: + url: example_videos/2.mp4 +- text: >- + The video begins with a close-up shot of a man's face. His eyes are glowing blue and there is a blue e13c7r1c electricity effect emanating from his shoulders. He is in front of a dark, foggy background. The man has a determined look on his face. + output: + url: example_videos/3.mp4 +- text: >- + The video begins with a wide shot of Thor holding his hammer. He is surrounded by a bright blue e13c7r1c electricity effect that looks like lightning bolts emanating from the hammer. The electricity effect is so intense it seems to be crackling and pulsating. Thor looks determined. The background is a forest. + output: + url: example_videos/4.mp4 +--- + +
+

Electrify LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to electrify anything! This model also works on T2V, with a very similar prompting style.

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [electrify_50_epochs.safetensors](./electrify_50_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: e13c7r1c electricity effect

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 25 seconds of video comprised of 13 short clips (each clip captioned separately) of various electricity clips
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Electrify/electrify_50_epochs.safetensors b/Electrify/electrify_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44d93f7abfaa15104e099386a24c5c8892af2cdf --- /dev/null +++ b/Electrify/electrify_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb8712b03377c5f8d7eace7332c2afec3252cc14f86a6ccd24ae06676588e4b +size 359257680 diff --git a/Electrify/example_videos/1.mp4 b/Electrify/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4daf51292b51e4f125c3c3e2eacb93f1599dcf0f --- /dev/null +++ b/Electrify/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe0fdb6fff0d559d69762e91098559052f76326017501a0cf6a890ba51540bb +size 1109419 diff --git a/Electrify/example_videos/2.mp4 b/Electrify/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..41574716a4043cca54f173209e42bbd42cfd3044 --- /dev/null +++ b/Electrify/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a530b594aa2e1c09dc477d89968f4e01e5697ae031742365dca626581cc958f +size 634642 diff --git a/Electrify/example_videos/3.mp4 b/Electrify/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..679eabbd6c6348eec279f231c5d15c7f0e350cf0 --- /dev/null +++ b/Electrify/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6fd882dcda680bd46a170a9f75f7d8d5d566357742839611f21875eec1c1caa +size 869117 diff --git a/Electrify/example_videos/4.mp4 b/Electrify/example_videos/4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..62ebbcea61b148977da02e5f1c6ccf813e5d4092 --- /dev/null +++ b/Electrify/example_videos/4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba87e50f8e1839d9bc7f25b767bc357f72b513efb43351ab3e386272c7842518 +size 855934 diff --git a/Electrify/workflow_I2V/wan_img2vid_lora_workflow.json b/Electrify/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Electrify/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Electrify/workflow_I2V/workflow_screenshot.png b/Electrify/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Electrify/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Explode/.gitattributes b/Explode/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..69eecd3645ecf7956ddcc3b1aa85a43fdedc6d53 --- /dev/null +++ b/Explode/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Explode/README.md b/Explode/README.md new file mode 100644 index 0000000000000000000000000000000000000000..283526d3237b7e34683776b9b79bfccc20933687 --- /dev/null +++ b/Explode/README.md @@ -0,0 +1,122 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video opens with a close-up of a smiling man, with curly hair, in a light-colored sweater. The man is smiling and looking up. The man is in front of a background with green hills and a bright sky. Then, the face of the smiling man 3xp105ion huge explosion that engulfs the entire screen with a bright light. The light is so bright that it obscures the man and his surroundings. + output: + url: example_videos/1.mp4 +- text: >- + The video shows a close-up of a 3xp105ion huge explosion on a snowy mountain, with ice and snow being thrown into the air. + output: + url: example_videos/2.mp4 +- text: >- + The video shows a 3xp105ion huge explosion in the middle of the ocean, creating a massive wave of water and a huge cloud of steam. + output: + url: example_videos/3.mp4 +- text: >- + The video opens on a grassy field, with a large 3xp105ion huge explosion sending debris and smoke high into the air. + output: + url: example_videos/4.mp4 +--- + +
+

Explosion LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to generate videos of an explosion in any scene! This model also works on T2V, with a very similar prompting style.

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [explode_30_epochs.safetensors](./explode_30_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 3xp105ion huge explosion

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 56 seconds of video comprised of 16 short clips (each clip captioned separately) of various explosions
  • +
  • Epochs: 30
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Explode/example_videos/1.mp4 b/Explode/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..00dc4874f1059514b51b1dcadab38c3f13d65d92 --- /dev/null +++ b/Explode/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26d9551fc5208cba0f5ef4ae6f9d48b71bbe2245b088e3c2f8b7afb2020fda0 +size 611001 diff --git a/Explode/example_videos/2.mp4 b/Explode/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..03e710bfc96d91389545a3b6fb89d57f8815272d --- /dev/null +++ b/Explode/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f8ec81bbde804da01796471d499c44023b49f691b50bb11bbcef8e7b32a4e9 +size 1405390 diff --git a/Explode/example_videos/3.mp4 b/Explode/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..77c6759ae7020ad704a7dd5591eb7b385d924abf --- /dev/null +++ b/Explode/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c16a7df611964ce31717651a1ecbfd587e3e6956571832cc012c53d906c5352 +size 1377560 diff --git a/Explode/example_videos/4.mp4 b/Explode/example_videos/4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cf938a1db7ad307a70379934dfbaa4d3ee515402 --- /dev/null +++ b/Explode/example_videos/4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3e990bee6e884d35cf578e0619a8a2ed5cb08b449cf6b556abdf0833b173eb +size 1609363 diff --git a/Explode/explode_30_epochs.safetensors b/Explode/explode_30_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f9c3482fed3d1460821532465763e8f53e19691 --- /dev/null +++ b/Explode/explode_30_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040dfee5d106acd4e027b6a493b2f228cef2adf090c23fb2040ff6ce016eccc5 +size 359257680 diff --git a/Explode/workflow_I2V/wan_img2vid_lora_workflow.json b/Explode/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Explode/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Explode/workflow_I2V/workflow_screenshot.png b/Explode/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Explode/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Fus-Ro-Dah/.gitattributes b/Fus-Ro-Dah/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..fa6fbc15279c3fa2b2f8c8c6c0be44320c7c1b23 --- /dev/null +++ b/Fus-Ro-Dah/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/fus1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/fus2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/fus3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/fus4.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Fus-Ro-Dah/README.md b/Fus-Ro-Dah/README.md new file mode 100644 index 0000000000000000000000000000000000000000..3d3812a90471a78ad5a4daff9bc8ce4fe99d224d --- /dev/null +++ b/Fus-Ro-Dah/README.md @@ -0,0 +1,123 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + A large man on a white donkey trots across a desert, kicking up dust, then is suddenly flung backwards by the fus_r0_d4h force push effect, flying over a utility pole and into the sky. + output: + url: example_videos/fus1.mp4 +- text: >- + A knight is charging forward, and then he is hit by a fus_r0_d4h force push effect and sent flying backward into a wall. + output: + url: example_videos/fus2.mp4 +- text: >- + A fearsome hybrid creature stands in murky water, then is flung backwards by the fus_r0_d4h force push effect, and disappearing into the swamp. + output: + url: example_videos/fus3.mp4 +- text: >- + A tank moves across a desert landscape, kicks up a dust cloud, then suddenly experiences the fus_r0_d4h force push effect, being flung backward over low hills and into the sky. + output: + url: example_videos/fus4.mp4 +--- + +
+

Skyrim Fus-Ro-Dah LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to apply the Fus-Ro-Dah spell on any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of it taking on a Fus-Ro-Dah spell!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [fus_ro_dah_20_epochs.safetensors](./fus_ro_dah_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: fus_r0_d4h force push effect

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 2 minutes of video comprised of 32 short clips (each clip captioned separately) of the Fus-Ro-Dah effect in action!
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Fus-Ro-Dah/example_videos/fus1.mp4 b/Fus-Ro-Dah/example_videos/fus1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6262f3fe9722896192229af22f6e281892faab1c --- /dev/null +++ b/Fus-Ro-Dah/example_videos/fus1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264f4beea1f23819f193c7cedc63dc4ba4fd87f3194f9cee8c0e2bb21cb379e6 +size 488153 diff --git a/Fus-Ro-Dah/example_videos/fus2.mp4 b/Fus-Ro-Dah/example_videos/fus2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..09e46d967fcd268e9c464a4ebce650b2810a3555 --- /dev/null +++ b/Fus-Ro-Dah/example_videos/fus2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda8e612ba8807849df175936bb5fc4e9f16703ac3854c9f4e92ad181e6d06b5 +size 1424934 diff --git a/Fus-Ro-Dah/example_videos/fus3.mp4 b/Fus-Ro-Dah/example_videos/fus3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e28862401cc305ac6f5b107e5a64c93a55baab25 --- /dev/null +++ b/Fus-Ro-Dah/example_videos/fus3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4c50371e61e140c29eff86bab9e9a919864893f29542b8940dcb1c42c36f77 +size 632230 diff --git a/Fus-Ro-Dah/example_videos/fus4.mp4 b/Fus-Ro-Dah/example_videos/fus4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9e4b5ba615379e6678c5bbd0abc5e2b1d5e98a5a --- /dev/null +++ b/Fus-Ro-Dah/example_videos/fus4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe223d5474e48be35215fa06879deb0d325570a7abfc233a600bbf047ddb65e +size 532732 diff --git a/Fus-Ro-Dah/fus_ro_dah_20_epochs.safetensors b/Fus-Ro-Dah/fus_ro_dah_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e4ccedd695d15ca06a1a30ca86037a0e6fa0716 --- /dev/null +++ b/Fus-Ro-Dah/fus_ro_dah_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3cb1d10399e8424952e336092e288c634d077b484491ed0206cd0dfac90b1e +size 359257680 diff --git a/Fus-Ro-Dah/workflow/wan_img2vid_lora_workflow.json b/Fus-Ro-Dah/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Fus-Ro-Dah/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Fus-Ro-Dah/workflow/workflow_screenshot.png b/Fus-Ro-Dah/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..bd7eec1c79fda3216ad688e2b68558568a39a152 --- /dev/null +++ b/Fus-Ro-Dah/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7062552eeeb70a6803e3e1a0c622845033a271d2cdd25ee1fd970c3b66fa6ab4 +size 493898 diff --git a/Gun-Shooting/.gitattributes b/Gun-Shooting/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..e75e36b6139120513496e23d8707f51e0bcc302d --- /dev/null +++ b/Gun-Shooting/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/luffy_gun.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/neymar_gun.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/pika_gun.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/woman_gun.mp4 filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Gun-Shooting/README.md b/Gun-Shooting/README.md new file mode 100644 index 0000000000000000000000000000000000000000..7a78844a35aab4b78893b52b26e062eadae51e17 --- /dev/null +++ b/Gun-Shooting/README.md @@ -0,0 +1,132 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + Luffy looks intently off-camera and the camera zooms out as Luffy p5lls g4un + pulls a gun and starts shooting. + output: + url: example_videos/luffy_gun.mp4 +- text: >- + Neymar looks intently off-camera in the rain, rain drops begin to fall and + the camera zooms out as he p5lls g4un pulls a gun and starts shooting. + output: + url: example_videos/neymar_gun.mp4 +- text: >- + A rodent looks intently off-camera and the camera zooms out as the rodent + p5lls g4un pulls a gun and starts shooting. + output: + url: example_videos/pika_gun.mp4 +- text: >- + A woman looks intently off-camera and the camera zooms out as she p5lls g4un + pulls a gun and starts shooting. + output: + url: example_videos/woman_gun.mp4 +--- + +
+

Gun Shooting Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image shoot a gun. The effect works on a wide variety of objects, from animals to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject pulling out and shooting a gun
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [gun_20_epochs.safetensors](./gun_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: p5lls g4un pulls a gun and starts shooting.

+
+ +
+

Prompt Template

+

For best results, use this prompt structure:

+
+ A [object] looks intently off-camera and the camera zooms out as the [object] p5lls g4un pulls a gun and starts shooting. +
+

Simply replace [object] with whatever you want to see pulling a gun out and shooting!

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 1 minute of video comprised of 10 short clips (each clip captioned separately) of people pulling up a gun and starting to shoot
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Gun-Shooting/example_videos/luffy_gun.mp4 b/Gun-Shooting/example_videos/luffy_gun.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1b13170a95d06eed31c878ae9b8d2afe2db22d8a --- /dev/null +++ b/Gun-Shooting/example_videos/luffy_gun.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a18d252176a227f631f583872818f42bad7c145a8d39ad2c270ce56da94c2e +size 897159 diff --git a/Gun-Shooting/example_videos/neymar_gun.mp4 b/Gun-Shooting/example_videos/neymar_gun.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fb9ba492ef891b7fe876878f7f96efe8107ad14d --- /dev/null +++ b/Gun-Shooting/example_videos/neymar_gun.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14db3954040a7f8c3126a94667e44146ea4f4ba1d63140fb6c222e652944d7c2 +size 690182 diff --git a/Gun-Shooting/example_videos/pika_gun.mp4 b/Gun-Shooting/example_videos/pika_gun.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c1bf96f0d9d72770cee0e5ff898b84db80687319 --- /dev/null +++ b/Gun-Shooting/example_videos/pika_gun.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7747ff38b9eaed3ce8f83757f804295e56755d985e3f999dd28e303f9874bee0 +size 676043 diff --git a/Gun-Shooting/example_videos/woman_gun.mp4 b/Gun-Shooting/example_videos/woman_gun.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..16e4fb03e402d998bc43d03eb6c79ee7512e935c --- /dev/null +++ b/Gun-Shooting/example_videos/woman_gun.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eab77fb0a231ebabae3eb4807341e3d46b4e0dae470e2826980f2af5f39e31a +size 317449 diff --git a/Gun-Shooting/gun_20_epochs.safetensors b/Gun-Shooting/gun_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e352c35c5c65a2f41ba4c984f0ce8b235f8ce98 --- /dev/null +++ b/Gun-Shooting/gun_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d88be3206aa7af10de7258fca3769635b8c003495d78185a5557a9348b9fee +size 359257680 diff --git a/Gun-Shooting/workflow/wan_img2vid_lora_workflow.json b/Gun-Shooting/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Gun-Shooting/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Gun-Shooting/workflow/workflow_screenshot.png b/Gun-Shooting/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..90dc37eb6f9d1737b953c3d6dfe28c6a1395ea50 --- /dev/null +++ b/Gun-Shooting/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44563b8de1f6dcf16d4ae833a2c9f2b92b578aebc0ac28bd1ae1a2edf000ebe7 +size 632437 diff --git a/Hug-Jesus/.gitattributes b/Hug-Jesus/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..228611790a8650868dce5413bee1941847337866 --- /dev/null +++ b/Hug-Jesus/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/hug1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/hug2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/hug3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/hug4.mp4 filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Hug-Jesus/README.md b/Hug-Jesus/README.md new file mode 100644 index 0000000000000000000000000000000000000000..541681ee165df8094a4e3ac7cb7072acc19c769d --- /dev/null +++ b/Hug-Jesus/README.md @@ -0,0 +1,123 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + A studio portrait of a young black man is smiling at the camera while in a bright mustard-yellow t-shirt. He is holding the face of Jesus. Then, h54g hugs jesus in a loving embrace as they are smiling. The background subtly changes as they begin to hug. + output: + url: example_videos/hug1.mp4 +- text: >- + A close-up portrait of a young woman is presented, with her eyes, smiling. Then, Jesus appears and embraces the woman. h54g hugs jesus and they are both smiling. + output: + url: example_videos/hug2.mp4 +- text: >- + The video features a close-up of a tabby cat lying down. Then, a smiling Jesus appears behind the cat, and he hugs the cat. The cat and Jesus are hugging. + output: + url: example_videos/hug3.mp4 +- text: >- + The video begins with Pepe the Frog, his eyes slowly looking around, then the mouth starts to subtly twitch as he looks at a light blue backdrop. Suddenly, Jesus appears behind him, and his face changes, and he begins to show emotion. The two begin to look at each other and h54g hugs jesus, while smiling. + output: + url: example_videos/hug4.mp4 +--- + +
+

Hug Jesus LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and makes Jesus hug any object in an image. The effect works on a wide variety of objects, from animals to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of Jesus hugging the image subject
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt examples that are easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [hug_jesus_20_epochs.safetensors](./hug_jesus_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: h54g hugs jesus

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 40 seconds of video comprised of 8 short clips (each clip captioned separately) of people hugging Jesus
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Hug-Jesus/example_videos/hug1.mp4 b/Hug-Jesus/example_videos/hug1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..6917c31d1456b1dc4c901f743ae3dad1d081505e --- /dev/null +++ b/Hug-Jesus/example_videos/hug1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b62b22cd3962ef2101e32edaba3d1b3cb762f05e699e959ab66e6e237d2a261 +size 758037 diff --git a/Hug-Jesus/example_videos/hug2.mp4 b/Hug-Jesus/example_videos/hug2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..48c8a8addf7abceb243d0ebc6240bc4e0c41ae24 --- /dev/null +++ b/Hug-Jesus/example_videos/hug2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e17bfdd67dc06aac4c395d1fabd1596c365b36f887840552586ade0bac5fe47 +size 842997 diff --git a/Hug-Jesus/example_videos/hug3.mp4 b/Hug-Jesus/example_videos/hug3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..85c9c74e6039d69fa3d5294421fe1049a2a37d6c --- /dev/null +++ b/Hug-Jesus/example_videos/hug3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739777910096b2d727d3bce1ba3b738b730dc303c0d3d172e2941fa31779c6d7 +size 1017152 diff --git a/Hug-Jesus/example_videos/hug4.mp4 b/Hug-Jesus/example_videos/hug4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..1f7919c0e09415fb1894f64aefcbe536702e08f9 --- /dev/null +++ b/Hug-Jesus/example_videos/hug4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f121b447ad3e9c325f8a37a92b5585ff7361a0799d3a5f04b1f6ea52e2634f +size 822774 diff --git a/Hug-Jesus/hug_jesus_20_epochs.safetensors b/Hug-Jesus/hug_jesus_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93e9b56096df199cdf5e1d4197d9a7d99111c7ba --- /dev/null +++ b/Hug-Jesus/hug_jesus_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea48f6742c7bc2fb74cbb80dc4bf39b4412da6d90efc75f673676d28211b9bf3 +size 359257680 diff --git a/Hug-Jesus/workflow/wan_img2vid_lora_workflow.json b/Hug-Jesus/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Hug-Jesus/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Hug-Jesus/workflow/workflow_screenshot.png b/Hug-Jesus/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..7d4530878e0409b588b557d69f8884bee68cc071 --- /dev/null +++ b/Hug-Jesus/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e6f2a4323484a61e49cfa149f27e4af6df42465857db068132f167c3e281c9 +size 479771 diff --git a/Hulk-Transformation/.gitattributes b/Hulk-Transformation/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..69eecd3645ecf7956ddcc3b1aa85a43fdedc6d53 --- /dev/null +++ b/Hulk-Transformation/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/4.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Hulk-Transformation/README.md b/Hulk-Transformation/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ed4159ba14e6277770ffac95f3b90b0715ac97e7 --- /dev/null +++ b/Hulk-Transformation/README.md @@ -0,0 +1,122 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video shows a man looking forward. Slowly, the h01k green hulk transformation begins. His muscles start to swell, veins bulge beneath his skin, and his face tightens with strain. His skin gradually shifts to green as his body continues to grow. His clothes begin to tear apart under the pressure. The transformation completes as the Hulk emerges, standing tall and roaring. + output: + url: example_videos/1.mp4 +- text: >- + The video shows a small puppy standing on a concrete surface, looking upward. Slowly, the h01k green hulk transformation begins. The puppy’s body expands, paws grow massive, and its fur gradually shifts to a deep green. Its stance widens as the transformation continues, and the ground beneath begins to crack slightly. The puppy finishes fully transformed into a powerful, green hulking figure, while still holding its playful pose. + output: + url: example_videos/2.mp4 +- text: >- + The video shows a man looking forward. Slowly, the h01k green hulk transformation begins. His muscles start to swell, veins bulge beneath his skin, and his face tightens with strain. His skin gradually shifts to green as his body continues to grow. His clothes begin to tear apart under the pressure. The transformation completes as the Hulk emerges, standing tall and roaring. + output: + url: example_videos/3.mp4 +- text: >- + The video shows an Asian man looking forward. Slowly, the h01k green hulk transformation begins. His muscles start to swell, veins bulge beneath his skin, and his face tightens with strain. His skin gradually shifts to green as his body continues to grow. His clothes begin to tear apart under the pressure. The transformation completes as the Hulk emerges, standing tall and roaring. + output: + url: example_videos/4.mp4 +--- + +
+

Hulk Transformation LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to apply a Hulk transformation on any image subject!

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [hulk_35_epochs.safetensors](./hulk_35_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: h01k green hulk transformation

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 40 seconds of video comprised of 8 short clips (each clip captioned separately) of various Hulk transformations
  • +
  • Epochs: 35
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Hulk-Transformation/example_videos/1.mp4 b/Hulk-Transformation/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..800df0083c5104ad40e7808a71c509534de0270c --- /dev/null +++ b/Hulk-Transformation/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ff23eb52709c7b0ca9a49ef3f0b07b94f77fe32d4c2e8c7f0833686c55b97f +size 823908 diff --git a/Hulk-Transformation/example_videos/2.mp4 b/Hulk-Transformation/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c7ee193134b6b863933d8224ca51a3bf18b7a01e --- /dev/null +++ b/Hulk-Transformation/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:785ce62e77c3d49aada78525830cf42a44999c355aa8b64cb63e1ce1650a8f0e +size 705285 diff --git a/Hulk-Transformation/example_videos/3.mp4 b/Hulk-Transformation/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..385fb3392f401752d1333b538eb760ae45891a3f --- /dev/null +++ b/Hulk-Transformation/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b5b12184e8099f86aa34283b5d39b714c77a46042cf3278eb57da40d76be63d +size 984282 diff --git a/Hulk-Transformation/example_videos/4.mp4 b/Hulk-Transformation/example_videos/4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a071a55b3f51a968246fcc13847b4f6bb14909ba --- /dev/null +++ b/Hulk-Transformation/example_videos/4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820c924fc36df719d620c491e38c524a5a82f3627523f528a6586b3a6278a4c8 +size 682191 diff --git a/Hulk-Transformation/hulk_35_epochs.safetensors b/Hulk-Transformation/hulk_35_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b863736f6a58c063794e2ed9fd870f42ef98113 --- /dev/null +++ b/Hulk-Transformation/hulk_35_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d9ccd9b2662932795e2883ef2c63e7105e322160af7ba30a426eb631e3284e +size 359257680 diff --git a/Hulk-Transformation/workflow_I2V/wan_img2vid_lora_workflow.json b/Hulk-Transformation/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Hulk-Transformation/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Hulk-Transformation/workflow_I2V/workflow_screenshot.png b/Hulk-Transformation/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Hulk-Transformation/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Inflate/.gitattributes b/Inflate/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..42cfaa2a53945252636d7dad3e6652aa403a21c3 --- /dev/null +++ b/Inflate/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/apple_inflate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/cartoon_inflate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man_inflate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/woman_inflate.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Inflate/README.md b/Inflate/README.md new file mode 100644 index 0000000000000000000000000000000000000000..3671100a0173bdcf6d0d9eaab2256a87352a8ad1 --- /dev/null +++ b/Inflate/README.md @@ -0,0 +1,131 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The large, bald man rides a gray donkey, then infl4t3 inflates it, both the + man and the donkey expanding into giant, inflated figures against the desert + landscape. + output: + url: example_videos/man_inflate.mp4 +- text: >- + The stylish woman in a white pantsuit smiles, then infl4t3 inflates it, her + form expanding, and her suit balloons around her in a chic, air-filled + design. + output: + url: example_videos/woman_inflate.mp4 +- text: >- + The young boy riding a bicycle down the dirt road is surprised, then infl4t3 + inflates it, his body and bike inflating together like a whimsical, + cartoonish balloon. + output: + url: example_videos/cartoon_inflate.mp4 +- text: >- + The red apple sits on a light gray surface, then infl4t3 inflates it, its + skin becoming taut and glossy as it transforms into a perfect, inflated + sphere. + output: + url: example_videos/apple_inflate.mp4 +--- + +
+

Inflate Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to inflate any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of it being inflated
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [inflate_20_epochs.safetensors](./inflate_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: infl4t3 inflates it

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 30 seconds of video comprised of 9 short clips (each clip captioned separately) of things being inflated
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Inflate/example_videos/apple_inflate.mp4 b/Inflate/example_videos/apple_inflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..05a417c66b85eba6b97ec4ff3e7232522ad82af2 --- /dev/null +++ b/Inflate/example_videos/apple_inflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7b225dcb2b9058693babd1daa0910d7b19bb11d92dc540f5593fd9d23251e0 +size 275345 diff --git a/Inflate/example_videos/cartoon_inflate.mp4 b/Inflate/example_videos/cartoon_inflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..42c97b425f63775d8dc9f1102cc6f664d8ca2d51 --- /dev/null +++ b/Inflate/example_videos/cartoon_inflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5c7bb764261c9b4f10c7e5c2e240f6457c979288ad33f0142ca69e4828cd2f +size 455882 diff --git a/Inflate/example_videos/man_inflate.mp4 b/Inflate/example_videos/man_inflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..eef81377117fc0dff93402b823f4212dae957eda --- /dev/null +++ b/Inflate/example_videos/man_inflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d6121bc5a357b966c02f6dbd1e71125bc3f281de566bcfe330d7f796e6a645b +size 599475 diff --git a/Inflate/example_videos/woman_inflate.mp4 b/Inflate/example_videos/woman_inflate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3b2300f9311c5d1dc79b2b6fb0bae0b56e1c7b1d --- /dev/null +++ b/Inflate/example_videos/woman_inflate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb45ec6af026a878e070d72057d1f95b5c3468521a8cbf50a871205cd490dc9f +size 321851 diff --git a/Inflate/inflate_20_epochs.safetensors b/Inflate/inflate_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8f00bcdc284d6e8760cf71c2e7a36f593dfed22 --- /dev/null +++ b/Inflate/inflate_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:978f493aec4b98ed910abfb9963522d05092c264c69182e5462514cee043eb96 +size 359257680 diff --git a/Inflate/workflow/wan_img2vid_lora_workflow.json b/Inflate/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Inflate/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Inflate/workflow/workflow_screenshot.png b/Inflate/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..45b9549712ee144475626e46369fb1bc98cbaebc --- /dev/null +++ b/Inflate/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3338aa0853c58162a34c0215e83fdc8d4a465c044ef6b0fb4e001d80277c4cb6 +size 599048 diff --git a/Jumpscare/.gitattributes b/Jumpscare/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..6651dc1100607740f540e1892356c96c87ac82ee --- /dev/null +++ b/Jumpscare/.gitattributes @@ -0,0 +1,38 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Jumpscare/README.md b/Jumpscare/README.md new file mode 100644 index 0000000000000000000000000000000000000000..1ec9d2fdd1b490e63e2d0dcf928d15e5cbaf3141 --- /dev/null +++ b/Jumpscare/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video shows a man with a slight smile, then the j432mpscare jumpscare occurs, revealing a distorted and monstrous face with glowing red eyes, filling the frame and accompanied by a loud scream. + output: + url: example_videos/1.mp4 +- text: >- + The video shows a person dressed in a white outfit with gold embellishments, gently touching the delicate pink flowers on a tree branch. The serene, peaceful atmosphere is further heightened by the soft-focus green foliage in the background. Suddenly, the j432mpscare jumpscare occurs and the tranquil scene is abruptly replaced by a monstrous creature's face, disrupting the serenity and replacing it with a sense of terror. + output: + url: example_videos/2.mp4 + +--- + +
+

Jumpscare LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to Jumpscare your friends

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [jumpscare_35_epochs.safetensors](./jumpscare_35_epochssafetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: j432mpscare jumpscare

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 60 seconds of video comprised of 12 short clips (each clip captioned separately) of jumpscares.
  • +
  • Epochs: 35
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Jumpscare/example_videos/.DS_Store b/Jumpscare/example_videos/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6 Binary files /dev/null and b/Jumpscare/example_videos/.DS_Store differ diff --git a/Jumpscare/example_videos/1.mp4 b/Jumpscare/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..527ffe53802cfb386b5a85e8034cf1ecbcc47fca --- /dev/null +++ b/Jumpscare/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3712f8236a60b674286d0c1008ec4a63ff5cd6cbea4f0b83d312a9ce031fab5e +size 490262 diff --git a/Jumpscare/example_videos/2.mp4 b/Jumpscare/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f44a7be4ff399c45ede9e050746f3f0cb0895f9a --- /dev/null +++ b/Jumpscare/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e066a6b6ee77dbc0e35ccbcdcbab19571120ecde8fd1886637e0de63c32d0ec4 +size 644423 diff --git a/Jumpscare/jumpscare_35_epochs.safetensors b/Jumpscare/jumpscare_35_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74f61d3bac75f29482a2a633d64933c8ba8d8480 --- /dev/null +++ b/Jumpscare/jumpscare_35_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076ba4d20ee3c7e298fd7be2e9f546652f29b76d4c6273ebc149d937cc2b50c9 +size 359257680 diff --git a/Jumpscare/workflow_I2V/wan_img2vid_lora_workflow.json b/Jumpscare/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Jumpscare/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Jumpscare/workflow_I2V/workflow_screenshot.png b/Jumpscare/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Jumpscare/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Jungle/.gitattributes b/Jungle/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..4279506fde81816d4d8be0f18c56a9e6eaadd1e4 --- /dev/null +++ b/Jungle/.gitattributes @@ -0,0 +1,38 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man1_jungle.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_jungle.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man1_jungle.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Jungle/README.md b/Jungle/README.md new file mode 100644 index 0000000000000000000000000000000000000000..bf8acf514eea7659cd3fdff5ddfd3d4e61b429e5 --- /dev/null +++ b/Jungle/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with a portrait of a man. The background is blurry, with shades of grey and green. Next, the 1ung13 jungle transformation occurs. The man is now in a jungle setting, bathed in sunlight. His hair is longer, and his hair is up. He is shirtless, with tribal markings on his chest. He wears jungle-like shorts. The man is swinging from a vine, posing in a dynamic, action-oriented manner. A dark panther-like figure is in the background. The scene evokes a sense of adventure and the wild. + output: + url: example_videos/man2_jungle.mp4 +- text: >- + The video begins with a portrait of a man. The background is blurry, with shades of grey and green. Next, the 1ung13 jungle transformation occurs. The man is now in a jungle setting, bathed in sunlight. His hair is longer, and his hair is up. He is shirtless, with tribal markings on his chest. He wears jungle-like shorts. The man is swinging from a vine, posing in a dynamic, action-oriented manner. A dark panther-like figure is in the background. The scene evokes a sense of adventure and the wild. + output: + url: example_videos/man1_jungle.mp4 +--- + +
+

Jungle Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a jungle version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a jungle Tarzan version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [jungle_50_epochs.safetensors](./jungle_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 1ung13 jungle transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into their jungle version!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Jungle/example_videos/man1_jungle.gif b/Jungle/example_videos/man1_jungle.gif new file mode 100644 index 0000000000000000000000000000000000000000..e5457c80c5dd5f600b3b8e97a9548065f93c9cb1 --- /dev/null +++ b/Jungle/example_videos/man1_jungle.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78fe3ac7ae1669c7796ca9a3fb69a87ddbc5ed69becf82e6398a98fe70902be1 +size 13470824 diff --git a/Jungle/example_videos/man1_jungle.mp4 b/Jungle/example_videos/man1_jungle.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..db9c3df8babf4aed27be5f4c2fe5aa0e35066382 --- /dev/null +++ b/Jungle/example_videos/man1_jungle.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69bc6f1c67d743be72ea297654abe046547e5dbe705e83c74a5907ce04664912 +size 1224344 diff --git a/Jungle/example_videos/man2_jungle.mp4 b/Jungle/example_videos/man2_jungle.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..769fcc8fff100cdf904cd96a1d5cf1b192a1039b --- /dev/null +++ b/Jungle/example_videos/man2_jungle.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdb785c5198a8b10c90d547332fe6405311cf3f1a6238867f719594fec9c214 +size 1365202 diff --git a/Jungle/jungle_50_epochs.safetensors b/Jungle/jungle_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82b11db839e89e8cd71e93c5cc5dab7516c892c7 --- /dev/null +++ b/Jungle/jungle_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d739abdabd68b6f849ebc55618d7c91855283a8884f1bc65db34f219008685 +size 359257680 diff --git a/Jungle/wan_I2V_LoRA_workflow.json b/Jungle/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Jungle/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Laughing/.gitattributes b/Laughing/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..07ebe4fbd69e49895d6a386a8a78459249e744ab --- /dev/null +++ b/Laughing/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Laughing/README.md b/Laughing/README.md new file mode 100644 index 0000000000000000000000000000000000000000..5366ba202ba901cad03180f5617926e8da091d32 --- /dev/null +++ b/Laughing/README.md @@ -0,0 +1,118 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + A man with dark hair wearing an orange jacket is shown in front of a brown background. He starts by looking into the camera and smiling and then he starts l4a6ing laughing. He's still l4a6ing laughing at the end. + output: + url: example_videos/1.mp4 +- text: >- + A man with dark hair is looking into the camera smiling and then he starts l4a6ing laughing. He's still l4a6ing laughing at the end. + output: + url: example_videos/2.mp4 +- text: >- + A man with gray hair and a gray t-shirt is smiling at the camera. He then begins l4a6ing laughing. + output: + url: example_videos/3.mp4 +--- + +
+

Laughing LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make yourself or your friends laugh!

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [laughing_15_epochs.safetensors](./laughing_15_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: l4a6ing laughing

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 55 seconds of video comprised of 12 short clips (each clip captioned separately) of people laughing.
  • +
  • Epochs: 15
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Laughing/example_videos/.DS_Store b/Laughing/example_videos/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6 Binary files /dev/null and b/Laughing/example_videos/.DS_Store differ diff --git a/Laughing/example_videos/1.mp4 b/Laughing/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b2b7327c5d30ded04ac155d95e30616a12e36a95 --- /dev/null +++ b/Laughing/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3181f2cabdeeb8e34520e8a14bffa9926ee84c76553316a351f62432185ae3 +size 316009 diff --git a/Laughing/example_videos/2.mp4 b/Laughing/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b26c0a4fee1a3344e1e4cee1947b991821ead9ff --- /dev/null +++ b/Laughing/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9c4eaa7e57c33e6d56443c860bc64d3bf77b841bdd04c75e701d24ad2e9053 +size 201678 diff --git a/Laughing/example_videos/3.mp4 b/Laughing/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f36768dc70e07009e1236a35119c9625bbef82a7 --- /dev/null +++ b/Laughing/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6621f7e85716de74b0307896d6da3db1109f7260bf7e5524f11b6bc61ae5471 +size 331441 diff --git a/Laughing/laughing_15_epochs.safetensors b/Laughing/laughing_15_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20f6615e799b8edf688502dead6cc88d691e058a --- /dev/null +++ b/Laughing/laughing_15_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c22fa4ea852a10ccd167955e60436486626e2d2effd55f4a1f8e7547348e62f +size 359257680 diff --git a/Laughing/workflow_I2V/wan_img2vid_lora_workflow.json b/Laughing/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Laughing/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Laughing/workflow_I2V/workflow_screenshot.png b/Laughing/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Laughing/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Mona-Lisa/.gitattributes b/Mona-Lisa/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..68b87279e5e3d279ea919e8f7b40f3c75a9223a9 --- /dev/null +++ b/Mona-Lisa/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man_mona_lisa.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/woman_mona_lisa.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Mona-Lisa/README.md b/Mona-Lisa/README.md new file mode 100644 index 0000000000000000000000000000000000000000..468215d880d653335456e900ea6309c51f887ff3 --- /dev/null +++ b/Mona-Lisa/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with an image of a woman. The m0n4 Mona Lisa transformation begins as a dark sheet seems to wrap around the woman, and when the image resolves, the woman is depicted as a Mona Lisa version of itself. The Mona Lisa version of the woman sits in a chair with a backdrop featuring a landscape painting. + output: + url: example_videos/woman_mona_lisa.mp4 +- text: >- + The video starts with an image of a man wearing a suit. The m0n4 Mona Lisa transformation begins as a dark sheet seems to wrap around him, and when the image resolves, he is depicted as a Mona Lisa version of himself. The Mona Lisa version sits in a chair with a backdrop featuring a landscape painting. + output: + url: example_videos/man_mona_lisa.mp4 +--- + +
+

Mona Lisa Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a Mona Lisa version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a Mona Lisa version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [mona_lisa_45_epochs.safetensors](./mona_lisa_45_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: m0n4 Mona Lisa transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into Mona Lisa!
  • +
  • Epochs: 45
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Mona-Lisa/example_videos/man_mona_lisa.mp4 b/Mona-Lisa/example_videos/man_mona_lisa.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..979d496c077e6c856a27305a7295814eb3071dd3 --- /dev/null +++ b/Mona-Lisa/example_videos/man_mona_lisa.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68ec9f76f065eac0e9100fae2b0c2218b8d6939dbac403fad2801e11771e2d08 +size 576169 diff --git a/Mona-Lisa/example_videos/woman_mona_lisa.mp4 b/Mona-Lisa/example_videos/woman_mona_lisa.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8e900660c1d6c5784404ad9cee18bd2d567505a5 --- /dev/null +++ b/Mona-Lisa/example_videos/woman_mona_lisa.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6571f0ceb8ad2080c71fb18e0355d4f9c224406c31346a1b6ecd7d5e38c4620b +size 405997 diff --git a/Mona-Lisa/mona_lisa_45_epochs.safetensors b/Mona-Lisa/mona_lisa_45_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1767d892811a49444ab77e799fcaaa6b3d9fd500 --- /dev/null +++ b/Mona-Lisa/mona_lisa_45_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f37f4e2a6b313017e0857f649c6d0346116ee455740bad1c3464bb14564693 +size 359257680 diff --git a/Mona-Lisa/wan_I2V_LoRA_workflow.json b/Mona-Lisa/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Mona-Lisa/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Muscle/.gitattributes b/Muscle/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..76ad5654474b4523138382278a63672f5b648074 --- /dev/null +++ b/Muscle/.gitattributes @@ -0,0 +1,41 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/elon_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man1_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/trump_muscle.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_muscle.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Muscle/README.md b/Muscle/README.md new file mode 100644 index 0000000000000000000000000000000000000000..7ec6c156c36fcfa2d513533d8368303cc415c2d4 --- /dev/null +++ b/Muscle/README.md @@ -0,0 +1,131 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + Donald Trump speaking into a microphone, then t2k1s takes off clothes + revealing a lean muscular body and shows off muscles, pointing his index + finger. + output: + url: example_videos/trump_muscle.mp4 +- text: >- + Elon Musk smiling slightly in a suit jacket, then t2k1s takes off clothes + revealing a lean muscular body and shows off muscles, giving a friendly + smile. + output: + url: example_videos/elon_muscle.mp4 +- text: >- + A man with a well-groomed beard and blue shirt smiles at the camera, then + t2k1s takes off clothes revealing a lean muscular body and shows off muscles + while smiling widely. + output: + url: example_videos/man1_muscle.mp4 +- text: >- + A smiling man with dark, curly hair and a white t-shirt, then t2k1s takes + off clothes revealing a lean muscular body and shows off muscles, flexing + and smiling. + output: + url: example_videos/man2_muscle.mp4 +--- + +
+

Muscle Show-Off Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to give muscles to anyone in an image!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject showing off developed muscles
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [muscle_18_epochs.safetensors](./muscle_18_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: t2k1s takes off clothes revealing a lean muscular body and shows off muscles

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 30 seconds of video comprised of 12 short clips (each clip captioned separately) of people showing off their muscles
  • +
  • Epochs: 18
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Muscle/example_videos/elon_muscle.mp4 b/Muscle/example_videos/elon_muscle.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c9521ea77c587d7a2a3f6621e121028f9df0c78e --- /dev/null +++ b/Muscle/example_videos/elon_muscle.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:568e7f8cffb11415b51c47c3dcd51c39ba364e66c0466b1c66634774e4bd38d0 +size 403262 diff --git a/Muscle/example_videos/man1_muscle.mp4 b/Muscle/example_videos/man1_muscle.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cbe3478721717eee7368913c0f1fb83ab9f34e79 --- /dev/null +++ b/Muscle/example_videos/man1_muscle.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1af731ab58c5050bedca99b2c8a428260ae5a37aefd0a2f271863e04d08f72 +size 411034 diff --git a/Muscle/example_videos/man2_muscle.gif b/Muscle/example_videos/man2_muscle.gif new file mode 100644 index 0000000000000000000000000000000000000000..1ec0f872ab988a4e30183aa2278e6fcfa6882802 --- /dev/null +++ b/Muscle/example_videos/man2_muscle.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d609bfe8624dd41d5a205374472b2f9e0fe81ea110a0597197471f01cf81d1 +size 5580525 diff --git a/Muscle/example_videos/man2_muscle.mp4 b/Muscle/example_videos/man2_muscle.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..98f270efe62ba035a17351085234ab1b53f064ad --- /dev/null +++ b/Muscle/example_videos/man2_muscle.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610e7fa1c3edd3cd4e5ef2ce7493169fb61c0d3b16c2d81dab73f5d816fe7d13 +size 410794 diff --git a/Muscle/example_videos/trump_muscle.mp4 b/Muscle/example_videos/trump_muscle.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..65389fa2f327faf57b533116f455793d2248e690 --- /dev/null +++ b/Muscle/example_videos/trump_muscle.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19d860ebf43716755ac12210ef22c67e7ad7a80f2f600c7a8f5c5cb31287ecb +size 488185 diff --git a/Muscle/muscle_18_epochs.safetensors b/Muscle/muscle_18_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9f773a5a238d11203838cea21491784580c1c13 --- /dev/null +++ b/Muscle/muscle_18_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a10ba09bfaee0128f64660c32c5e86dd86c1b00fbfd2db0200748d79bb8e4d25 +size 359257680 diff --git a/Muscle/workflow/wan_img2vid_lora_workflow.json b/Muscle/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Muscle/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Muscle/workflow/workflow_screenshot.png b/Muscle/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..fb759c955425257a80b3cb7531fd44fe9cd78ccd --- /dev/null +++ b/Muscle/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7bfa06c7cd86f62875b16eb1917b7469e15e183c6deee8d8b9c9f794b2f7e7f +size 532519 diff --git a/Painting/.gitattributes b/Painting/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..3fd2d744bc4a926db6544212c5166d19898ebde1 --- /dev/null +++ b/Painting/.gitattributes @@ -0,0 +1,38 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/dog_painting.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man_painting.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/woman_painting.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Painting/README.md b/Painting/README.md new file mode 100644 index 0000000000000000000000000000000000000000..c56d8b5fb6e2fe9df7aab9e359c0284a33b683a9 --- /dev/null +++ b/Painting/README.md @@ -0,0 +1,119 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a dog. The next scene shows the dog inside a gold framed mirror in a room. The dog is wearing the same clothes and the background outside the frame shows a landscape scene. Next, the dog transforms into a p41nt1ng painting frame it, where the dog is dressed in red and blue clothing. The background is an older style painting scene. Finally, the dog is in another p41nt1ng painting frame it, where it is dressed in a red robe with the same landscape background in the painting. + output: + url: example_videos/dog_painting.mp4 +- text: >- + The video starts with a woman. The next scene shows the woman inside a gold framed mirror in a room. She is wearing the same clothes and the background outside the frame shows a landscape scene. Next, the woman transforms into a p41nt1ng painting frame it, where she is dressed in red and blue clothing. The background is an older style painting scene. Finally, the woman is in another p41nt1ng painting frame it, where she is dressed in a red robe with the same landscape background in the painting. + output: + url: example_videos/woman_painting.mp4 +- text: >- + The video starts with a man. The next scene shows the man inside a gold framed mirror in a room. He is wearing the same clothes and the background outside the frame shows a landscape scene. Next, the man transforms into a p41nt1ng painting frame it, where he is dressed in red and blue clothing. The background is an older style painting scene. Finally, the man is in another p41nt1ng painting frame it, where he is dressed in a red robe with the same landscape background in the painting. + output: + url: example_videos/man_painting.mp4 +--- + +
+

Historic Painting Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a historic painting version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a historic painting version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [painting_50_epochs.safetensors](./painting_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: p41nt1ng painting frame it

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a painting version of themselves!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Painting/example_videos/dog_painting.mp4 b/Painting/example_videos/dog_painting.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9a500c51687ca94de38d7f3e6d54f4e0ccfd749e --- /dev/null +++ b/Painting/example_videos/dog_painting.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13079837d64bce4a1e435ea2285c4469dca9104c51944ec7636a4da629991a27 +size 652203 diff --git a/Painting/example_videos/man_painting.mp4 b/Painting/example_videos/man_painting.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ca367584fbb697600d9842bdc0d5971c599d39c6 --- /dev/null +++ b/Painting/example_videos/man_painting.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc311ddf055e2caa07846978e23cbcfe0bbeddd8ce9c81265873791c1ee05f27 +size 756990 diff --git a/Painting/example_videos/woman_painting.mp4 b/Painting/example_videos/woman_painting.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..116de4fa27ecc20720ef787dfa178da62ac8481d --- /dev/null +++ b/Painting/example_videos/woman_painting.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f10332bd499aefc365e60c1eed37770deccc7b7f4ae1e3a9a42c5570c9d946d +size 563544 diff --git a/Painting/painting_50_epochs.safetensors b/Painting/painting_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a05c8ca0d77d8adb231b016e015c895762230685 --- /dev/null +++ b/Painting/painting_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cfdd2cc11c347e808e4e132e9c1ccee95b7a1f7b6ec2d99bd931d8627eb8438 +size 359257680 diff --git a/Painting/wan_I2V_LoRA_workflow.json b/Painting/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Painting/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Pirate-Captain/.gitattributes b/Pirate-Captain/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..890b278533fc9f73076a6e5a31c4bb30f2a64127 --- /dev/null +++ b/Pirate-Captain/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/cat_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/goku_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rabbit_pirate_captain.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/cat_example.gif.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Pirate-Captain/README.md b/Pirate-Captain/README.md new file mode 100644 index 0000000000000000000000000000000000000000..9f9d8d65091c59494ca4b6c76c85f6227560d00d --- /dev/null +++ b/Pirate-Captain/README.md @@ -0,0 +1,123 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with a cat. The image then transitions to the p1r4t3 pirate captain transformation. The cat is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing the cat on a wooden ship. The cat has long dreadlock style hair and a sword. The scene changes again to show the cat with his sword, in the same location on the boat. + output: + url: example_videos/cat_pirate_captain.mp4 +- text: >- + The video begins with Goku. The image then transitions to the p1r4t3 pirate captain transformation. Goku is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing Goku on a wooden ship. Goku has long dreadlock style hair and a sword. The scene changes again to show Goku with his sword, in the same location on the boat. + output: + url: example_videos/goku_pirate_captain.mp4 +- text: >- + The video begins with a man posing. The image then transitions to the p1r4t3 pirate captain transformation. The man is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing the man on a wooden ship. He has long dreadlock style hair and a sword. The scene changes again to show the man with his sword, in the same location on the boat. + output: + url: example_videos/man_pirate_captain.mp4 +- text: >- + The video begins with a rabbit. The image then transitions to the p1r4t3 pirate captain transformation. The rabbit is wearing a black pirate hat with a red band around it, a coat and pants, and a pirate style sash. The scene changes, showing the rabbit on a wooden ship. The rabbit has long dreadlock style hair and a sword. The scene changes again to show the rabbit with his sword, in the same location on the boat. + output: + url: example_videos/rabbit_pirate_captain.mp4 +--- + +
+

Pirate Captain Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a Pirate Captain version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a Pirate Captain version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [pirate_captain_50_epochs.safetensors](./pirate_captain_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: p1r4t3 pirate captain transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a pirate captain!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Pirate-Captain/example_videos/cat_example.gif.gif b/Pirate-Captain/example_videos/cat_example.gif.gif new file mode 100644 index 0000000000000000000000000000000000000000..e6b30b29598215aed2c2f212fed83b40bad1737f --- /dev/null +++ b/Pirate-Captain/example_videos/cat_example.gif.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed31e4f2ffc300628ef7cf0c1e89b2fb5aafc5e99ed24e05cf67c818561fc453 +size 11185095 diff --git a/Pirate-Captain/example_videos/cat_pirate_captain.mp4 b/Pirate-Captain/example_videos/cat_pirate_captain.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..ab01913dd685f47017b7a004f587e1826719b458 --- /dev/null +++ b/Pirate-Captain/example_videos/cat_pirate_captain.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d75a4e6e1b626cf182214c9ecefd5d2feb2bb4bc6bd922e7be51749494013b3f +size 1043337 diff --git a/Pirate-Captain/example_videos/goku_pirate_captain.mp4 b/Pirate-Captain/example_videos/goku_pirate_captain.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..20bc7bdd5773725886c724c89fe2b1e7febda118 --- /dev/null +++ b/Pirate-Captain/example_videos/goku_pirate_captain.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f7d33b4a811977d21f4d25fa11e27343633128b86bb665dfa8fc19322545c09 +size 986891 diff --git a/Pirate-Captain/example_videos/man_pirate_captain.mp4 b/Pirate-Captain/example_videos/man_pirate_captain.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2d0c34db260874111f57662cd33cf9d4c5104a93 --- /dev/null +++ b/Pirate-Captain/example_videos/man_pirate_captain.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b2fb741b274b0d4e350f333bf909a76eb1199c850c193a5f9bf9cdbee2a388 +size 974598 diff --git a/Pirate-Captain/example_videos/rabbit_pirate_captain.mp4 b/Pirate-Captain/example_videos/rabbit_pirate_captain.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..7d1661ee8a1c203be76ff8e2bbf8f68d672f7d13 --- /dev/null +++ b/Pirate-Captain/example_videos/rabbit_pirate_captain.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d68512c92b0e3e8af6beb4045b2bd8098f0f9ad1bf204dd59ff54adfc13e5361 +size 995403 diff --git a/Pirate-Captain/pirate_captain_50_epochs.safetensors b/Pirate-Captain/pirate_captain_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9d88d3d1ef6fab3f4c0db1f73a1def233ea899a --- /dev/null +++ b/Pirate-Captain/pirate_captain_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a63b6a73960d3c9ed9deb9c0100248b5b88cfcbc28866fae9afd7c7c9c8e59 +size 359257680 diff --git a/Pirate-Captain/wan_I2V_LoRA_workflow.json b/Pirate-Captain/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Pirate-Captain/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Princess/.gitattributes b/Princess/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..69ec653d16fb923af7b5405589ee9b5563e80548 --- /dev/null +++ b/Princess/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man_princess.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/woman_princess.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Princess/README.md b/Princess/README.md new file mode 100644 index 0000000000000000000000000000000000000000..7b06b91d219743da47045fa38bcd9cd40c5e905e --- /dev/null +++ b/Princess/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with an image of a woman. A pr1nc355 princess transformation then happens as white sparkling light appears around the woman's shoulders and chest. The woman is now wearing a tiara on her head, a long, silver beaded gown, and silver gloves that reach up to her biceps. The woman is seated on a chair in front of a table with gifts and candles. The background is a room with white curtains. The woman is looking directly at the camera and holding her hand up. The camera pans to the right to display more gifts and candles. Thew man then moves their hand closer to the camera. + output: + url: example_videos/woman_princess.mp4 +- text: >- + The video begins with an image of a man. A pr1nc355 princess transformation then happens as white sparkling light appears around the man's shoulders and chest. The man is now wearing a tiara on his head, a long, silver beaded gown, and silver gloves that reach up to their biceps. The man is seated on a chair in front of a table with gifts and candles. The background is a room with white curtains. The man is looking directly at the camera and holding their hand up. The camera pans to the right to display more gifts and candles. The man then moves their hand closer to the camera. + output: + url: example_videos/man_princess.mp4 +--- + +
+

Princess Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a princess version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a princess version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [princess_45_epochs.safetensors](./princess_45_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: pr1nc355 princess transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a princess!
  • +
  • Epochs: 45
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Princess/example_videos/man_princess.mp4 b/Princess/example_videos/man_princess.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..efa9076c00f1f5a4d4e6a9c828c8a74ef98c25db --- /dev/null +++ b/Princess/example_videos/man_princess.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cfd514a3d7a574126785fde600a0a83eeb42d35056ab2eaeab9aebaa4dd339a +size 1626885 diff --git a/Princess/example_videos/woman_princess.mp4 b/Princess/example_videos/woman_princess.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..60c1fabef7f4a8c6fda5bf57c1ba5c09a366506f --- /dev/null +++ b/Princess/example_videos/woman_princess.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af39ec71dc588312e2adccd4589b3e7193ec9f99d8e567e8ff3739e07a54fab6 +size 1467346 diff --git a/Princess/princess_45_epochs.safetensors b/Princess/princess_45_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aec07d4c19fbeed176b8e4ce9b8e876eedb3fac6 --- /dev/null +++ b/Princess/princess_45_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463f720340b8b3915bf658334a2159ad7ed53ccd417cffd73c9a4116427fa53a +size 359257680 diff --git a/Princess/wan_I2V_LoRA_workflow.json b/Princess/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Princess/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Puppy/.gitattributes b/Puppy/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..18c7262e01c360d195c97ad74ec92b7c4cc1c08d --- /dev/null +++ b/Puppy/.gitattributes @@ -0,0 +1,38 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man1_puppy.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_puppy.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man3_puppy.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Puppy/README.md b/Puppy/README.md new file mode 100644 index 0000000000000000000000000000000000000000..212a6dd2b64d3d616bb751f4a1682225d698e940 --- /dev/null +++ b/Puppy/README.md @@ -0,0 +1,119 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with a close-up portrait of a man wearing a suit. The background changes and then the pu11y puppy effect begins. The man is now surrounded by many puppies. He pets the puppies. + output: + url: example_videos/man1_puppy.mp4 +- text: >- + The video begins with a relaxed shot of a man smiling, sitting on a modern gray armchair. The pu11y puppy effect happens, and the man is surrounded by golden retriever puppies. He interacts with the puppies on his phone. + output: + url: example_videos/man2_puppy.mp4 +- text: >- + The video opens with a studio portrait of a man smiling in a white t-shirt. The pu11y puppy effect then begins, as puppies begin to gather and surround him. He is now holding a puppy in his arms. + output: + url: example_videos/man3_puppy.mp4 +--- + +
+

Puppy Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image get surrounded by puppies!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject surrounded by puppies!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [puppy_50_epochs.safetensors](./puppy_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: pu11y puppy effect

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people getting surrounded by puppies!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Puppy/example_videos/man1_puppy.mp4 b/Puppy/example_videos/man1_puppy.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d00e0019fe5e83ad4fb378910775db7582fd1a25 --- /dev/null +++ b/Puppy/example_videos/man1_puppy.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a564308f285d285463333905e2102722ac06c4224e134caee7812dd594655ccb +size 589411 diff --git a/Puppy/example_videos/man2_puppy.mp4 b/Puppy/example_videos/man2_puppy.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c560f83b79f86ce37213a7a6f8cae301c18962a9 --- /dev/null +++ b/Puppy/example_videos/man2_puppy.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed974f54c457f8fc7821512a38ae937c9b6c883335c837ae66814767e22a0dab +size 446705 diff --git a/Puppy/example_videos/man3_puppy.mp4 b/Puppy/example_videos/man3_puppy.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c738e498c2cd78ad35af3af9c0372072d24637ac --- /dev/null +++ b/Puppy/example_videos/man3_puppy.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890044d87d0d76b568095d7d4b96ae4156432b584f830ac74198c44e7a8ba71d +size 449770 diff --git a/Puppy/puppy_50_epochs.safetensors b/Puppy/puppy_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d5aeaa9214499e391f51660d0061880973d84b1 --- /dev/null +++ b/Puppy/puppy_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b8b7d153610036a027725a8564d18f59cd975e9a51cd3cdb2a43e21e5dfa61 +size 359257680 diff --git a/Puppy/wan_I2V_LoRA_workflow.json b/Puppy/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Puppy/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Robot-Face-Reveal/.gitattributes b/Robot-Face-Reveal/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..376d3dd61284f42ae443d0d31f6d9eb11da5e3cb --- /dev/null +++ b/Robot-Face-Reveal/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/robot1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/robot2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/robot3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/robot4.mp4 filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Robot-Face-Reveal/README.md b/Robot-Face-Reveal/README.md new file mode 100644 index 0000000000000000000000000000000000000000..76a1e3d17cce73b6aa3fe50d015838745aaaccbc --- /dev/null +++ b/Robot-Face-Reveal/README.md @@ -0,0 +1,123 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + Grumpy Cat's face, with the r8b8t1c robotic face reveal starting with subtle movements, then lines appear on his face, his expression remaining grumpy as the robot face is revealed. + output: + url: example_videos/robot1.mp4 +- text: >- + A young man with a thoughtful expression. The r8b8t1c robotic face reveal progresses, lines appearing and his face transforming into a metallic, robotic visage. + output: + url: example_videos/robot2.mp4 +- text: >- + Shrek with a friendly smile. The r8b8t1c robotic face reveal shows metallic lines forming, his jovial expression shifting, then his face opening to reveal his robotic interior. + output: + url: example_videos/robot3.mp4 +- text: >- + A young man with dark curly hair and a neutral expression. The r8b8t1c robotic face reveal commences, lines forming as a metallic mask replaces his features. + output: + url: example_videos/robot4.mp4 +--- + +
+

Westworld-Inspired Robot Face Reveal LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to reveal a robotic face from any image subject. The effect works on a wide variety of objects, from animals to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject revealing a robotic face
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [robot_face_reveal_35_epochs.safetensors](./robot_face_reveal_35_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: r8b8t1c robotic face reveal

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 25 seconds of video comprised of 5 short clips (each clip captioned separately) of robotic face reveals
  • +
  • Epochs: 35
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Robot-Face-Reveal/example_videos/robot1.mp4 b/Robot-Face-Reveal/example_videos/robot1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3067c8aaaaa2b1d90af045bc8fd38d7924e1acb4 --- /dev/null +++ b/Robot-Face-Reveal/example_videos/robot1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd0819709f6a6c2d7384db4903d8d45a46bc7dd8b5a3ef79b157f649760d50f +size 771209 diff --git a/Robot-Face-Reveal/example_videos/robot2.mp4 b/Robot-Face-Reveal/example_videos/robot2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4524efa3c1eaa470b0b660cd6cab629a7ff9f927 --- /dev/null +++ b/Robot-Face-Reveal/example_videos/robot2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146cc2a92ff2e1567bf238a6676c2b4dc248b5162bc36dfeab5cbd8a97732b25 +size 616570 diff --git a/Robot-Face-Reveal/example_videos/robot3.mp4 b/Robot-Face-Reveal/example_videos/robot3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..acd991826eb1540ff169f06877797bd7def305df --- /dev/null +++ b/Robot-Face-Reveal/example_videos/robot3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e06c3eb5abdcceb62c58d90f23bf0df6feeaed5d2dc6ed07a2733d10a8733cf +size 356303 diff --git a/Robot-Face-Reveal/example_videos/robot4.mp4 b/Robot-Face-Reveal/example_videos/robot4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9743a318a665f2e4ce1d2788fff0e79ca525d3ff --- /dev/null +++ b/Robot-Face-Reveal/example_videos/robot4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b75cd0a92b6e7cf8c7ebd3294d006157e8525176ae9fe2a50869564266f06d5 +size 535959 diff --git a/Robot-Face-Reveal/robot_face_reveal_35_epochs.safetensors b/Robot-Face-Reveal/robot_face_reveal_35_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c03a60beb0e41f5e719a64718951baef51637b0 --- /dev/null +++ b/Robot-Face-Reveal/robot_face_reveal_35_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db5e9306f30ac87bb059270b616482fec844b8adfdb5ed99ee93e97b204c4c9f +size 359257680 diff --git a/Robot-Face-Reveal/workflow/wan_img2vid_lora_workflow.json b/Robot-Face-Reveal/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Robot-Face-Reveal/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Robot-Face-Reveal/workflow/workflow_screenshot.png b/Robot-Face-Reveal/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..695c14033d6db840decff1f4c8e01859e005187d --- /dev/null +++ b/Robot-Face-Reveal/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a895d0ada14f5d9dca9065f65a32f53c5a98d1c92a39977ae7de191471f166a +size 499152 diff --git a/Rotate/.gitattributes b/Rotate/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..5ef5d9f043fc9238f20f98df877ec84f75c0b0bf --- /dev/null +++ b/Rotate/.gitattributes @@ -0,0 +1,41 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/bike_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/chair_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/figure_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man_rotate.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/chair-rotate.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Rotate/README.md b/Rotate/README.md new file mode 100644 index 0000000000000000000000000000000000000000..dc1145946f164f72f22eeab72dea119bab106854 --- /dev/null +++ b/Rotate/README.md @@ -0,0 +1,128 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video shows a man seated on a chair. The man and the chair performs a + r0t4tion 360 degrees rotation. + output: + url: example_videos/man_rotate.mp4 +- text: >- + The overweight boy rides the bicycle down the dirt road, showing a full + r0t4tion 360 degrees rotation as he descends the hill, with a shocked + expression. + output: + url: example_videos/bike_rotate.mp4 +- text: >- + The cartoonish boy stands ready with his backpack, then performs a r0t4tion + 360 degrees rotation, starting in a neutral pose. + output: + url: example_videos/figure_rotate.mp4 +- text: >- + The video features a wooden chair with a blue cushion doing a r0t4tion 360 + degrees rotation. + output: + url: example_videos/chair_rotate.mp4 +--- + +
+

360 Degree Rotation Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to rotate any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of it being rotated
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [rotate_20_epochs.safetensors](./rotate_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: r0t4tion 360 degrees rotation

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 30 seconds of video comprised of 12 short clips (each clip captioned separately) of things being rotated
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Rotate/example_videos/bike_rotate.mp4 b/Rotate/example_videos/bike_rotate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..395eb7c30063930be97d19db2abccffda1851261 --- /dev/null +++ b/Rotate/example_videos/bike_rotate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105769c40b7782baf3a6d1792824d9242e26a783d8c8122079ca7cd19a263f70 +size 848649 diff --git a/Rotate/example_videos/chair-rotate.gif b/Rotate/example_videos/chair-rotate.gif new file mode 100644 index 0000000000000000000000000000000000000000..fedc355ddc121f271a4f8fdb31f7c4e5ae47035a --- /dev/null +++ b/Rotate/example_videos/chair-rotate.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85ae5824db38305d1150c62685a60925a484cd4a7a1d01da8caad57f3f94331 +size 3141719 diff --git a/Rotate/example_videos/chair_rotate.mp4 b/Rotate/example_videos/chair_rotate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..760ea0deadc3f772cee1ad82ddc1d6c0069a6677 --- /dev/null +++ b/Rotate/example_videos/chair_rotate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b29ea6047ecb3c27b1c6e8a6d4b08dbfafe66400c606eceee7c62a699a8a70 +size 172717 diff --git a/Rotate/example_videos/figure_rotate.mp4 b/Rotate/example_videos/figure_rotate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..561ef80ae18c4431ce310f95e1bd152fcd6803b8 --- /dev/null +++ b/Rotate/example_videos/figure_rotate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b40847f903a0308df4c76cd0d80ce2f1feb80db2a4a6e5442111f626bf8878 +size 452461 diff --git a/Rotate/example_videos/man_rotate.mp4 b/Rotate/example_videos/man_rotate.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f168f484c27434ff16987edf80eb18e7959b79ce --- /dev/null +++ b/Rotate/example_videos/man_rotate.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc02867fbfa7c7b38dd12751078739f0ff496080995f82027de0845e308e4bf4 +size 592004 diff --git a/Rotate/rotate_20_epochs.safetensors b/Rotate/rotate_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0bf2fd50005254ad92fb973ce255cd716a28bdeb --- /dev/null +++ b/Rotate/rotate_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ce56166b6941eb0037fd7a7675885a221e8cfd53486c4d923b3464f1db1560 +size 359257680 diff --git a/Rotate/workflow/wan_img2vid_lora_workflow.json b/Rotate/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Rotate/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Rotate/workflow/workflow_screenshot.png b/Rotate/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..58097f9698843ffa985f71db0a4f9be0e84bebca --- /dev/null +++ b/Rotate/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bfd8989ff15613fe437ed7f017387e921d52434141f57b4fee4cfba140639a6 +size 768843 diff --git a/Samurai/.gitattributes b/Samurai/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..3ac74ac47d9177d0a3ef6656373650db686269cb --- /dev/null +++ b/Samurai/.gitattributes @@ -0,0 +1,38 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man_samurai.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rabbit_samurai.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rabbit_samurai.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Samurai/README.md b/Samurai/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d9d4110805c90686bbf6bdd4278ba601eb606e92 --- /dev/null +++ b/Samurai/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with a man. He begins the 54mur41 samurai transformation, and becomes a samurai. He is wearing a traditional samurai outfit, and is holding a katana. The background behind him is a misty mountainous landscape. + output: + url: example_videos/man_samurai.mp4 +- text: >- + The video begins with a rabbit. The rabbit begins the 54mur41 samurai transformation, and becomes a samurai. The rabbit is wearing a traditional samurai outfit, and is holding a katana. The background behind the rabbit is a misty mountainous landscape. + output: + url: example_videos/rabbit_samurai.mp4 +--- + +
+

Samurai Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a Samurai version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a Samurai version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [samurai_50_epochs.safetensors](./samurai_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 54mur41 samurai transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a Samurai!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Samurai/example_videos/man_samurai.mp4 b/Samurai/example_videos/man_samurai.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2150153970b4bedb0331a597b409d42044657b37 --- /dev/null +++ b/Samurai/example_videos/man_samurai.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67311788ca4160bd819c2ff9d6916a07b6bba78f1de3f0992d6d343e7acddff +size 632599 diff --git a/Samurai/example_videos/rabbit_samurai.gif b/Samurai/example_videos/rabbit_samurai.gif new file mode 100644 index 0000000000000000000000000000000000000000..8304e058858cfad38c288197bb583069cb0ff1b5 --- /dev/null +++ b/Samurai/example_videos/rabbit_samurai.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ca5e0b8aff77be7acf8888b28ebf33ca3a423c681e3f2b30259c4febb9ebf8 +size 8651228 diff --git a/Samurai/example_videos/rabbit_samurai.mp4 b/Samurai/example_videos/rabbit_samurai.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..cd6f20f51b94acccaebec4857604c7f408ae2289 --- /dev/null +++ b/Samurai/example_videos/rabbit_samurai.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3a41134fd86338a4ebd172f966837f62a4e4f30d6333f54523261390e07435 +size 500866 diff --git a/Samurai/samurai_50_epochs.safetensors b/Samurai/samurai_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..184b920e89451d921acc1131743f525c1500ba7a --- /dev/null +++ b/Samurai/samurai_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6cae8ea4c058bcaeacafa2ee6181d08c6a437c08bc9104f65da600f67345f8b +size 359257680 diff --git a/Samurai/wan_I2V_LoRA_workflow.json b/Samurai/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Samurai/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Selfie-With-Younger-Self/.gitattributes b/Selfie-With-Younger-Self/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..07ebe4fbd69e49895d6a386a8a78459249e744ab --- /dev/null +++ b/Selfie-With-Younger-Self/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Selfie-With-Younger-Self/README.md b/Selfie-With-Younger-Self/README.md new file mode 100644 index 0000000000000000000000000000000000000000..65f7f0a9e7c03d3a84a9278407fe069410c13855 --- /dev/null +++ b/Selfie-With-Younger-Self/README.md @@ -0,0 +1,118 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a man with a beard smiling at the camera, then s31lf13 taking a selfie with their younger self, and the younger self appears next to him with similar facial features and eye color. The younger self wears a white t-shirt and has a cream white jacket. The younger self is smiling slightly. + output: + url: example_videos/1.mp4 +- text: >- + The video shows a man with gray hair, wearing a gray shirt and smiling at the camera. Then, s31lf13 taking a selfie with their younger self, the younger self shares similar facial features. The younger self is smiling. The two are in the s31lf13 taking a selfie with their younger self. + output: + url: example_videos/2.mp4 +- text: >- + The video shows a woman with black skin, dark hair, and dark eyes who is smiling as she looks towards the camera. Then, s31lf13 taking a selfie with their younger self, her younger self then appears next to her. The younger self shares similar facial features, eye colour and skin tone appearing to be the woman when she was young. + output: + url: example_videos/3.mp4 +--- + +
+

Taking a Selfie with Your Younger Self LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to take a selfie with your younger self!

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [selfie_younger_self_15_epochs.safetensors](./selfie_younger_self_15_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: s31lf13 taking a selfie with their younger self

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 40 seconds of video comprised of 9 short clips (each clip captioned separately) of people taking a selfie with their younger self
  • +
  • Epochs: 35
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Selfie-With-Younger-Self/example_videos/1.mp4 b/Selfie-With-Younger-Self/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..98ad4405f8cca82d9158e5c6a624eff0d8823fa3 --- /dev/null +++ b/Selfie-With-Younger-Self/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87eae9405c6adab49222bb1195de579cf09a7c97cb5f54d8ffbdc63600cbaaf2 +size 388786 diff --git a/Selfie-With-Younger-Self/example_videos/2.mp4 b/Selfie-With-Younger-Self/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..8fa11b5a459687f2322556d00c3ab39e446cc09f --- /dev/null +++ b/Selfie-With-Younger-Self/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:388186df604538acaa7907a6e3e23ed0c3f8359442e2270259a8b719d3f677e5 +size 332030 diff --git a/Selfie-With-Younger-Self/example_videos/3.mp4 b/Selfie-With-Younger-Self/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d976b9ca047159aac51f012c9bafe75c42f9f162 --- /dev/null +++ b/Selfie-With-Younger-Self/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5831f15f81eac220868d78708fc3172cb9fcf41cbec4dc4a544da57ef0f5d7b +size 644341 diff --git a/Selfie-With-Younger-Self/selfie_younger_self_15_epochs.safetensors b/Selfie-With-Younger-Self/selfie_younger_self_15_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4fbd0a5c02de5eaef660a487956f697dcc4612a6 --- /dev/null +++ b/Selfie-With-Younger-Self/selfie_younger_self_15_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a70df3f0ef938d00884ce7fe77b7bfb0e65a3a82d20b0a65606e1ac639e74c7 +size 359257680 diff --git a/Selfie-With-Younger-Self/workflow_I2V/wan_img2vid_lora_workflow.json b/Selfie-With-Younger-Self/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/Selfie-With-Younger-Self/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Selfie-With-Younger-Self/workflow_I2V/workflow_screenshot.png b/Selfie-With-Younger-Self/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/Selfie-With-Younger-Self/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/Snow-White/.gitattributes b/Snow-White/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..d450b59f10ce2efe3d7196d48b2fd541aca9b4d2 --- /dev/null +++ b/Snow-White/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man1_snow_white.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_snow_white.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/Snow-White/README.md b/Snow-White/README.md new file mode 100644 index 0000000000000000000000000000000000000000..aee27ca16578109df758d633994b34017d2c5b0b --- /dev/null +++ b/Snow-White/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with a portrait of a man. The scene cuts to the man in the sn0w_wh1t3 Snow White transformation. He is now wearing the classic Snow White dress, and his hair is pulled back in a braid. He is holding a red apple in his right hand. The background has changed to a forest. The background and lighting add to the Snow White scene. + output: + url: example_videos/man1_snow_white.mp4 +- text: >- + The video begins with a man in a sunny outdoor setting. The scene cuts to the man in the sn0w_wh1t3 Snow White transformation. He is now wearing the classic Snow White dress, and his hair is pulled back in a braid. He is holding a red apple in his right hand. The background has changed to a forest. The background and lighting add to the Snow White scene. + output: + url: example_videos/man2_snow_white.mp4 +--- + +
+

Snow White Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a Snow White version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a Snow White version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [snow_white_50_epochs.safetensors](./snow_white_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: sn0w_wh1t3 Snow White transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into Snow White!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Snow-White/example_videos/man1_snow_white.mp4 b/Snow-White/example_videos/man1_snow_white.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..3bcfd905aaa5facb64fe69045dc144fabc35c9be --- /dev/null +++ b/Snow-White/example_videos/man1_snow_white.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497bf66e0e5e26f38265942ef24e1dbfac6ed91a20abb934306afe3021dd9760 +size 902075 diff --git a/Snow-White/example_videos/man2_snow_white.mp4 b/Snow-White/example_videos/man2_snow_white.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a1d61ba406d177e23c630457e96cef268d222a38 --- /dev/null +++ b/Snow-White/example_videos/man2_snow_white.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f625151dac8175ef04ebc16268fa00580dbc000a1be40d33bea1b5197357bef6 +size 964694 diff --git a/Snow-White/snow_white_50_epochs.safetensors b/Snow-White/snow_white_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24a3f2154011f8c9e510664b1a098b0b704f1351 --- /dev/null +++ b/Snow-White/snow_white_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bb488e12d25e5a014a2d889e6c657299606dca41812565ce02f2b2700289228 +size 359257680 diff --git a/Snow-White/wan_I2V_LoRA_workflow.json b/Snow-White/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Snow-White/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Squish/.gitattributes b/Squish/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..dbc328520ab66be84b4e81ffecdebc518919be14 --- /dev/null +++ b/Squish/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/balloon_squish.gif filter=lfs diff=lfs merge=lfs -text +example_videos/dog_squish.gif filter=lfs diff=lfs merge=lfs -text +example_videos/person_squish.gif filter=lfs diff=lfs merge=lfs -text +example_videos/rodent_squish.gif filter=lfs diff=lfs merge=lfs -text +example_videos/tank_squish.gif filter=lfs diff=lfs merge=lfs -text +example_videos/balloon_squish.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/dog_squish.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/person_squish.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rodent_squish.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/tank_squish.mp4 filter=lfs diff=lfs merge=lfs -text +example_gifs/balloon_squish.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/dog_squish.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/person_squish.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/rodent_squish.gif filter=lfs diff=lfs merge=lfs -text +example_gifs/tank_squish.gif filter=lfs diff=lfs merge=lfs -text +squish_compilation_mmaudio.mp4 filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Squish/README.md b/Squish/README.md new file mode 100644 index 0000000000000000000000000000000000000000..3d9b42c2b6ef4d81f78f81d504c8bdb9e1e5b40e --- /dev/null +++ b/Squish/README.md @@ -0,0 +1,189 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +widget: +- text: >- + In the video, a miniature dog is presented. The dog is held in a person's + hands. The person then presses on the dog, causing a sq41sh squish effect. + The person keeps pressing down on the dog, further showing the sq41sh squish + effect. + output: + url: example_videos/dog_squish.mp4 +- text: >- + In the video, a miniature tank is presented. The tank is held in a person's + hands. The person then presses on the tank, causing a sq41sh squish effect. + The person keeps pressing down on the tank, further showing the sq41sh + squish effect. + output: + url: example_videos/tank_squish.mp4 +- text: >- + In the video, a miniature balloon is presented. The balloon is held in a + person's hands. The person then presses on the balloon, causing a sq41sh + squish effect. The person keeps pressing down on the balloon, further + showing the sq41sh squish effect. + output: + url: example_videos/balloon_squish.mp4 +- text: >- + In the video, a miniature rodent is presented. The rodent is held in a + person's hands. The person then presses on the rodent, causing a sq41sh + squish effect. The person keeps pressing down on the rodent, further showing + the sq41sh squish effect. + output: + url: example_videos/rodent_squish.mp4 +- text: >- + In the video, a miniature person is presented. The person is held in a + person's hands. The person then presses on the person, causing a sq41sh + squish effect. The person keeps pressing down on the person, further showing + the sq41sh squish effect. + output: + url: example_videos/person_squish.mp4 +--- +
+

Squish Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to squish any object in an image. The effect works on a wide variety of objects, from animals to vehicles to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of it being squished
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [squish_18.safetensors](./squish_18.safetensors) - LoRA Model File +- [wan_img2video_lora_workflow.json](./workflow/wan_img2video_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +## Using with Diffusers +```py +pip install git+https://github.com/huggingface/diffusers.git +``` + +```py +import torch +from diffusers.utils import export_to_video, load_image +from diffusers import AutoencoderKLWan, WanImageToVideoPipeline +from transformers import CLIPVisionModel +import numpy as np + +model_id = "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers" +image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32) +vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32) +pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16) +pipe.to("cuda") + +pipe.load_lora_weights("Remade/Squish") + +pipe.enable_model_cpu_offload() #for low-vram environments + +prompt = "In the video, a miniature cat toy is presented. The cat toy is held in a person's hands. The person then presses on the cat toy, causing a sq41sh squish effect. The person keeps pressing down on the cat toy, further showing the sq41sh squish effect." + +image = load_image("https://huggingface.co/datasets/diffusers/cat_toy_example/resolve/main/1.jpeg") + +max_area = 480 * 832 +aspect_ratio = image.height / image.width +mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1] +height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value +width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value +image = image.resize((width, height)) + +output = pipe( + image=image, + prompt=prompt, + height=height, + width=width, + num_frames=81, + guidance_scale=5.0, + num_inference_steps=28 +).frames[0] +export_to_video(output, "output.mp4", fps=16) +``` + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: sq41sh squish effect

+
+ +
+

Prompt Template

+

For best results, use this prompt structure:

+
+ In the video, a miniature [object] is presented. The [object] is held in a person's hands. The person then presses on the [object], causing a sq41sh squish effect. The person keeps pressing down on the [object], further showing the sq41sh squish effect. +
+

Simply replace [object] with whatever you want to see squished!

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: 1.5 minutes of video (20 short clips of things being squished)
  • +
  • Epochs: 18
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Squish/example_gifs/balloon_squish.gif b/Squish/example_gifs/balloon_squish.gif new file mode 100644 index 0000000000000000000000000000000000000000..8d1f8d147a51ad43c51a31737d1b8e898193a140 --- /dev/null +++ b/Squish/example_gifs/balloon_squish.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86696606fba115019cecadfa82533d68dc8768195073b3188a4e8ea7a87ebd3d +size 5140219 diff --git a/Squish/example_gifs/dog_squish.gif b/Squish/example_gifs/dog_squish.gif new file mode 100644 index 0000000000000000000000000000000000000000..1fe3b4b315306f53784afb778c5f4fd27e568bf0 --- /dev/null +++ b/Squish/example_gifs/dog_squish.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9c7645eff69e0338b9491ec97f39373d05bf53559fa041d33fb45db3176f66 +size 8015893 diff --git a/Squish/example_gifs/person_squish.gif b/Squish/example_gifs/person_squish.gif new file mode 100644 index 0000000000000000000000000000000000000000..9f28ade27f85ecddd51fba9cf96312b58a71190e --- /dev/null +++ b/Squish/example_gifs/person_squish.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5338e9618b3dd25d7d20f283525e711d1fe8ffe12ef333c7c4cdb88d168891 +size 5120305 diff --git a/Squish/example_gifs/rodent_squish.gif b/Squish/example_gifs/rodent_squish.gif new file mode 100644 index 0000000000000000000000000000000000000000..68a8969065c48a582f699a39940085e3e2f6599a --- /dev/null +++ b/Squish/example_gifs/rodent_squish.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1eb3f6b6db2745a0c7dc5522c9806afe403b98d079aaed6aa71576e695d96d +size 5319893 diff --git a/Squish/example_gifs/tank_squish.gif b/Squish/example_gifs/tank_squish.gif new file mode 100644 index 0000000000000000000000000000000000000000..a66ddfa6587edc9924fadca51e9f558d76ad22e5 --- /dev/null +++ b/Squish/example_gifs/tank_squish.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7af4cd975986fc06db044fc00452eb8be099c21f46947b94968d5cd76ee7589 +size 6767546 diff --git a/Squish/example_videos/balloon_squish.mp4 b/Squish/example_videos/balloon_squish.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..2e8b7bed5caa74e329831a5f4ecadabec6139246 --- /dev/null +++ b/Squish/example_videos/balloon_squish.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967c28741952c20f90a3046353972e6cc84f0c5b97c731fe89b5c60fde11907f +size 586858 diff --git a/Squish/example_videos/dog_squish.mp4 b/Squish/example_videos/dog_squish.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a4f8f264abc4a0386f4c688a65ecb90e9dab9edf --- /dev/null +++ b/Squish/example_videos/dog_squish.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9a3021b5991931bdce68bc886a27d6ece7b1fdfb49670a797aee2ecec6d149 +size 718980 diff --git a/Squish/example_videos/person_squish.mp4 b/Squish/example_videos/person_squish.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f24266a5aa2bd01c5c8abb92a91a4b4ea84698be --- /dev/null +++ b/Squish/example_videos/person_squish.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8c01f56a360c2c868c7ccc7080b31c634af70d447f1d10d4c967c97e503893 +size 412580 diff --git a/Squish/example_videos/rodent_squish.mp4 b/Squish/example_videos/rodent_squish.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..68bfe8a1925559f9c4e27774df1d89a2af6c6902 --- /dev/null +++ b/Squish/example_videos/rodent_squish.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dd0c254288ac90cecc1b20a1e2f871b075ffdee9472ab28e82ac586a0fec57f +size 485042 diff --git a/Squish/example_videos/tank_squish.mp4 b/Squish/example_videos/tank_squish.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..aa1022c5d989e11eecbbe38d78778e7e9731ebc8 --- /dev/null +++ b/Squish/example_videos/tank_squish.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278d8c1409d1d71d847f634425da84a97a2e61da11f25d72caf5c9e954e7da14 +size 616381 diff --git a/Squish/squish_18.safetensors b/Squish/squish_18.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bdfe98b4c6afa4b1a76a75e3772d5be43b45bc00 --- /dev/null +++ b/Squish/squish_18.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2195da8077b02674775929e94b43caa30dc069ed74b1818a2e2adf8fe559cf7 +size 359257680 diff --git a/Squish/squish_compilation_mmaudio.mp4 b/Squish/squish_compilation_mmaudio.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..25c74dd8d8909205cdf4c17c75ac2d26244035b6 --- /dev/null +++ b/Squish/squish_compilation_mmaudio.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67cb381142895e776b29a4c3421935ae304a5e2447413bfee9b6937b80c1d35c +size 14548632 diff --git a/Squish/workflow/wan_img2video_lora_workflow.json b/Squish/workflow/wan_img2video_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..eb12a90c1a41b5fd3fd33d7c2816c5be83f096e6 --- /dev/null +++ b/Squish/workflow/wan_img2video_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00033.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00033.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00033.mp4" + } + } + } + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "SN56-06-110121-P07-PikaChew-MD-1.jpg", + "image" + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 189992167790583, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 402.9853515625, + -296.4585266113281 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Squish\\squish_18.safetensors", + 1 + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "In the video, a miniature tank is presented. The tank is held in a person’s hands. The person then presses on the tank, causing a sq41sh squish effect. The person keeps pressing down on the tank, further showing the sq41sh squish effect.", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7972024500000019, + "offset": { + "0": -135.86273193359375, + "1": 357.7580871582031 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Squish/workflow/workflow_screenshot.png b/Squish/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..6d89f330670426922938dd897c8336dca3f37d17 --- /dev/null +++ b/Squish/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ccfa5c79fc16dd50cfdc881c70e59eca6ff47c4ebdabad6f4baeb95cfd18e5e +size 610120 diff --git a/Super-Saiyan/.gitattributes b/Super-Saiyan/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..be3dc9cc9f99dc6389593123cc5e330096e4dbfc --- /dev/null +++ b/Super-Saiyan/.gitattributes @@ -0,0 +1,40 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/super1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/super2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/super3.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/super4.mp4 filter=lfs diff=lfs merge=lfs -text +workflow/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/Super-Saiyan/README.md b/Super-Saiyan/README.md new file mode 100644 index 0000000000000000000000000000000000000000..20ccdd096d8f4b98dd2f157d45dfe6147f14b0f3 --- /dev/null +++ b/Super-Saiyan/README.md @@ -0,0 +1,123 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + A man with short hair and a beard clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. + output: + url: example_videos/super1.mp4 +- text: >- + A South Asian man with dark hair and a beard clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. + output: + url: example_videos/super2.mp4 +- text: >- + An old Asian man with short hair clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. + output: + url: example_videos/super3.mp4 +- text: >- + A man with curly dark hair and a beard clenches his fists, staring forward. His hair brightens to glowing yellow, spiking up as gold energy surges around his body. The background pulses with yellow light, and sparks crackle in the air during his 5up3r super saiyan transformation, real life style. + output: + url: example_videos/super4.mp4 +--- + +
+

Dragon Ball Super Saiyan LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to turn anyone into a Super Saiyan. The effect works on a wide variety of objects, from animals to people!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject turning into a Super Saiyan
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [super_saiyan_35_epochs.safetensors](./super_saiyan_35_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 5up3r super saiyan transformation

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 1 minute of video comprised of 13 short clips (each clip captioned separately) of various Super Saiyan transformations
  • +
  • Epochs: 35
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Super-Saiyan/example_videos/super1.mp4 b/Super-Saiyan/example_videos/super1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a0e7cada20dbba631d4cbe1731a1c01f0ad442ca --- /dev/null +++ b/Super-Saiyan/example_videos/super1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a0cb710d4e6aa83f84c06e1b2c91731ca67c67b0408561be3e6b0506fa45417 +size 649712 diff --git a/Super-Saiyan/example_videos/super2.mp4 b/Super-Saiyan/example_videos/super2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..fe3fecab0515a37d486a6b6c7bbc73acf8a2bbef --- /dev/null +++ b/Super-Saiyan/example_videos/super2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7295c657f5c8bc9439bd716d677393f41e4f3431c5c378709a946bc25664257a +size 698097 diff --git a/Super-Saiyan/example_videos/super3.mp4 b/Super-Saiyan/example_videos/super3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..a9b958eb651a20559bf256b3bce3314aba92dec7 --- /dev/null +++ b/Super-Saiyan/example_videos/super3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae17266e53a83d095bc87525a415322efffffe5820a7916af0f6ba45ab6277be +size 768371 diff --git a/Super-Saiyan/example_videos/super4.mp4 b/Super-Saiyan/example_videos/super4.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..90ce5e206caed768847267cf5cd9b1bdb79db020 --- /dev/null +++ b/Super-Saiyan/example_videos/super4.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e80e4b6b845e9c31693e73a351c672aaef6b96f77a7006ec361dfa429c5b4d2 +size 822992 diff --git a/Super-Saiyan/super_saiyan_35_epochs.safetensors b/Super-Saiyan/super_saiyan_35_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86d93d1dfd525cd669edeb825e6a36ecfb7d2171 --- /dev/null +++ b/Super-Saiyan/super_saiyan_35_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14051e6645f5009fce2041eece0e3819bc2b59ccac013df54651edf54484611 +size 359257680 diff --git a/Super-Saiyan/workflow/wan_img2vid_lora_workflow.json b/Super-Saiyan/workflow/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ee357cd582925a55230978fee2e6682ea2e4d9 --- /dev/null +++ b/Super-Saiyan/workflow/wan_img2vid_lora_workflow.json @@ -0,0 +1,801 @@ +{ + "last_node_id": 43, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 648.850341796875, + 976.850341796875 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00034.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00034.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00034.mp4" + } + } + } + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 853268816080959, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_0cf53e8c-f636-45bc-a49b-281a1f320911.jpg", + "image" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 382.2516174316406, + -311.5375671386719 + ], + "size": [ + 315, + 102 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Cakeify\\cakeify_16_epochs.safetensors", + 1 + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "The video opens on a cat. A knife, held by a hand, is coming into frame and hovering over the cat. The knife then begins cutting into the cat to c4k3 cakeify it. As the knife slices the cat open, the inside of the cat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the cat are revealed. \n", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 440, + 440, + 29, + true, + 0, + 1, + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000011, + "offset": { + "0": 16.369264602661133, + "1": 438.202392578125 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Super-Saiyan/workflow/workflow_screenshot.png b/Super-Saiyan/workflow/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..421c68aec15193305ad088196c5ea89bf5ab938f --- /dev/null +++ b/Super-Saiyan/workflow/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7218323786dbf5e729b2bb8f1c837e99713fd313ad7d1e50a88109679877a7 +size 513526 diff --git a/VIP/.gitattributes b/VIP/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..3aea6643fe9b1d37f74d1c7cc4c1575a1a50aad8 --- /dev/null +++ b/VIP/.gitattributes @@ -0,0 +1,38 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man_vip.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/thanos_vip.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/thanos_vip.gif filter=lfs diff=lfs merge=lfs -text diff --git a/VIP/README.md b/VIP/README.md new file mode 100644 index 0000000000000000000000000000000000000000..c7cf8b951bd4da9f225ff000a7c5699bd4a12339 --- /dev/null +++ b/VIP/README.md @@ -0,0 +1,115 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video begins with an image of purple Thanos from Marvel. Then the v1p red carpet transformation appears. Purple Thanos is shown wearing a black dress, with gold jewelry around his neck and ears. The image is again of purple Thanos looking straight at the camera against a more lighted gray background. The v1p red carpet transformation continues, purple Thanos is now on the red carpet with photographers taking pictures and other people behind a barricade to the sides. Purple Thanos is wearing the same black dress and jewelry, in focus at the center of the frame. + output: + url: example_videos/thanos_vip.mp4 +- text: >- + The video begins with an image of a man. Then the v1p red carpet transformation appears. He is shown wearing a black dress, with gold jewelry around his neck and ears. The image is again of him looking straight at the camera against a more lighted gray background. The v1p red carpet transformation continues, he is now on the red carpet with photographers taking pictures and other people behind a barricade to the sides. He is wearing the same black dress and jewelry, in focus at the center of the frame. + output: + url: example_videos/man_vip.mp4 +--- + +
+

VIP Red Carpet Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a female VIP version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a female VIP version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [vip_50_epochs.safetensors](./vip_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: v1p red carpet transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a female VIP version of themselves!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/VIP/example_videos/man_vip.mp4 b/VIP/example_videos/man_vip.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4ea76b53290c310f581c0466f276d95c0895f4e0 --- /dev/null +++ b/VIP/example_videos/man_vip.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c373964ef6ce926501b151c83c04e7bbef875297e1111f75ef2d52bcc44d3bd +size 643806 diff --git a/VIP/example_videos/thanos_vip.gif b/VIP/example_videos/thanos_vip.gif new file mode 100644 index 0000000000000000000000000000000000000000..3e954f358e6ee3fa59e2a762579e18c212fa8dc2 --- /dev/null +++ b/VIP/example_videos/thanos_vip.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f673c1008653ca60e0e4186f1170518cd36e588c2a3fc7be1d43a0715f008a2 +size 10509523 diff --git a/VIP/example_videos/thanos_vip.mp4 b/VIP/example_videos/thanos_vip.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e9d978aa302f694c31a0ef8d7ef957983e869e65 --- /dev/null +++ b/VIP/example_videos/thanos_vip.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8da70324574674b74a02ff0dad1d0f1d01666ef63b889bb8a28b3ef81c4a83b +size 1183639 diff --git a/VIP/vip_50_epochs.safetensors b/VIP/vip_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7fc897030f7453dde66e8f4c709ce1733c08b27d --- /dev/null +++ b/VIP/vip_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a802fc04d8325bbddc31fbb329b15115de1980dcf6e0ab281e9bdef712c9280 +size 359257680 diff --git a/VIP/wan_I2V_LoRA_workflow.json b/VIP/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/VIP/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Warrior/.gitattributes b/Warrior/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..33e0e8ef66633128c034ff2e4d0cafacc0ffb878 --- /dev/null +++ b/Warrior/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/dog_warrior.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man1_warrior.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/man2_warrior.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/dog_warrior.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Warrior/README.md b/Warrior/README.md new file mode 100644 index 0000000000000000000000000000000000000000..9cf4d72f5faded1c3b26dd74b293110d4b7a1399 --- /dev/null +++ b/Warrior/README.md @@ -0,0 +1,119 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a man. The next scene shows him with a mountain range in the background. His shirt is pulled up to his midriff, and he is wearing a skirt-like bottom. The man has a belt around his waist and is gesturing with his right hand. He is wearing brown, medieval looking leggings. The effect seen is warr10r warrior it. The man now appears as a warrior with an axe. He is shirtless, muscular, has tattoos, and is smiling with a determined look on his face. The background is the same mountain range as before. The next scene shows the man still as a warrior, and he is holding an axe with a golden axe head. + output: + url: example_videos/man1_warrior.mp4 +- text: >- + The video starts with a man. The next scene shows him with a mountain range in the background. His shirt is pulled up to his midriff, and he is wearing a skirt-like bottom. The man has a belt around his waist and is gesturing with his right hand. He is wearing brown, medieval looking leggings. The effect seen is warr10r warrior it. The man now appears as a warrior with an axe. He is shirtless, muscular, has tattoos, and is smiling with a determined look on his face. The background is the same mountain range as before. The next scene shows the man still as a warrior, and he is holding an axe with a golden axe head. + output: + url: example_videos/man2_warrior.mp4 +- text: >- + The video starts with a dog. The next scene shows the dog with a mountain range in the background. The dog's shirt is pulled up to his midriff, and it is wearing a skirt-like bottom. The dog has a belt around its waist and is gesturing with its right hand. The dog is wearing brown, medieval looking leggings. The effect seen is warr10r warrior it. The dog now appears as a warrior with an axe. The dog is shirtless, muscular, has tattoos, and is smiling with a determined look on her face. The background is the same mountain range as before. The next scene shows the dog still as a warrior, and he is holding an axe with a golden axe head. + output: + url: example_videos/dog_warrior.mp4 +--- + +
+

Warrior Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a warrior version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a warrior version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [warrior_45_epochs.safetensors](./warrior_45_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: warr10r warrior it

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into a warrior!
  • +
  • Epochs: 45
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Warrior/example_videos/dog_warrior.gif b/Warrior/example_videos/dog_warrior.gif new file mode 100644 index 0000000000000000000000000000000000000000..7749b12d3f76bcdd5d3239d4ba9cc94a1311e708 --- /dev/null +++ b/Warrior/example_videos/dog_warrior.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6d3e86c2db365bcfa0b98ee8544fbea225f510d39b19f49252c6dd78a63ccc +size 11713999 diff --git a/Warrior/example_videos/dog_warrior.mp4 b/Warrior/example_videos/dog_warrior.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5e269ed28bf25a3d277a0f6fecd145af20d34944 --- /dev/null +++ b/Warrior/example_videos/dog_warrior.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a1dc6d1ec131e06bc0b49439df3b020dc00ee9b4331bd0ca1608c338e448be +size 936996 diff --git a/Warrior/example_videos/man1_warrior.mp4 b/Warrior/example_videos/man1_warrior.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d5b0ab997f43cd01e813f24d10bb61006a7c1b64 --- /dev/null +++ b/Warrior/example_videos/man1_warrior.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e9d617c9587c1439864fbcf09973385d167c3b25e1aa644a1cf9f700dbf0b7 +size 723564 diff --git a/Warrior/example_videos/man2_warrior.mp4 b/Warrior/example_videos/man2_warrior.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..96a83f0c439799036dedbd46d97390bc935a06e0 --- /dev/null +++ b/Warrior/example_videos/man2_warrior.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ee8d9ab2a0ea4c9e3edd35a5e23e1e59163c6c75ccff3f8419b14e4890f973 +size 850785 diff --git a/Warrior/wan_I2V_LoRA_workflow.json b/Warrior/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Warrior/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Warrior/warrior_45_epochs.safetensors b/Warrior/warrior_45_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0eb31e8f30655bb446d3e5e954d849a44674a02 --- /dev/null +++ b/Warrior/warrior_45_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60f3c07b2338769149465f509261e38065bd1d050d9f385e9ebc84d16cf26175 +size 359257680 diff --git a/Zen/.gitattributes b/Zen/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..568c3bd963a48c9706c7266cbd84bf7a3b59a984 --- /dev/null +++ b/Zen/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/man_zen.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/rodent_zen.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/thanos_zen.mp4 filter=lfs diff=lfs merge=lfs -text +man_zen.gif filter=lfs diff=lfs merge=lfs -text diff --git a/Zen/README.md b/Zen/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0c84c83d2f2f7f197c0b3d99ee58baafe55b07ee --- /dev/null +++ b/Zen/README.md @@ -0,0 +1,119 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a portrait of a rodent. The scene then transitions to the rodent's z3n1fy zen transformation as the rodent is wearing a pink robe with a white shirt underneath, with a zen garden background. The rodent is facing the camera with a neutral expression. The background appears to be blurred and out of focus. The scene then transitions again to show the transformed rodent, in what appears to be a garden setting. The rodent is now wearing a black kimono with white floral designs and a white belt. The rodent carries a basket in one hand and a colorful fan in the other. The rodent is walking down a pathway lined with hedges and greenery. The z3n1fy zen transformation is complete. The rodent has a neutral expression, looking directly at the camera. + output: + url: example_videos/rodent_zen.mp4 +- text: >- + The video starts with a portrait of a purple Thanos from Marvel. The scene then transitions to the Thanos' z3n1fy zen transformation as he's wearing a pink robe with a white shirt underneath, with a zen garden background. Thanos is facing the camera with a neutral expression. The background appears to be blurred and out of focus. The scene then transitions again to show the transformed Thanos, in what appears to be a garden setting. He is now wearing a black kimono with white floral designs and a white belt. Thanos carries a basket in one hand and a colorful fan in the other. He is walking down a pathway lined with hedges and greenery. The z3n1fy zen transformation is complete. Thanos has a neutral expression, looking directly at the camera. + output: + url: example_videos/thanos_zen.mp4 +- text: >- + The video starts with a portrait of an old man. The scene then transitions to the man's z3n1fy zen transformation as he's wearing a pink robe with a white shirt underneath, with a zen garden background. He is facing the camera with a neutral expression. The background appears to be blurred and out of focus. The scene then transitions again to show the transformed man, in what appears to be a garden setting. He is now wearing a black kimono with white floral designs and a white belt. He carries a basket in one hand and a colorful fan in the other. He is walking down a pathway lined with hedges and greenery. The z3n1fy zen transformation is complete. The man has a neutral expression, looking directly at the camera. + output: + url: example_videos/man_zen.mp4 +--- + +
+

Zen Effect LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make any person/object in an image become a Zen version of themselves!

+
+ +
+

Features

+
    +
  • Transform any image into a video of the subject as a Zen version of themselves!
  • +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [zen_50_epochs.safetensors](./zen_50_epochs.safetensors) - LoRA Model File +- [wan_I2V_LoRA_workflow.json](./wan_I2V_LoRA_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: z3n1fy zen transformation

+
+ +
+

Prompt Template

+

For best results, try following the structure of the prompt examples above. These worked well for me.

+
+ +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people transforming into their zen version!
  • +
  • Epochs: 50
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/Zen/example_videos/man_zen.gif b/Zen/example_videos/man_zen.gif new file mode 100644 index 0000000000000000000000000000000000000000..e767ff082e8f88c1b96d9d66d7f987f3f6810b42 --- /dev/null +++ b/Zen/example_videos/man_zen.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee07122844b7730ad423d407ddbc935a0f4cbbc39baabe3ca2c04103a3678fc +size 11148659 diff --git a/Zen/example_videos/man_zen.mp4 b/Zen/example_videos/man_zen.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e7437cb9793b38dcef5403bcedc611263e5eff22 --- /dev/null +++ b/Zen/example_videos/man_zen.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b28160b966b7e37fbe49415c06a85203c75dbadb15619b7ed4b33f789da6747 +size 1202365 diff --git a/Zen/example_videos/rodent_zen.mp4 b/Zen/example_videos/rodent_zen.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c2c4329d478c5a685559da53512f634bc4fdffee --- /dev/null +++ b/Zen/example_videos/rodent_zen.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c13fbba76e2de537cc5dc9cdade9867db902270b4e6ce046aeeaf8e48e7562 +size 1208060 diff --git a/Zen/example_videos/thanos_zen.mp4 b/Zen/example_videos/thanos_zen.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..00096329799e58f93bdf81cf6716e577df315c4d --- /dev/null +++ b/Zen/example_videos/thanos_zen.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e22d3b358f4bae63cf86ba26823c1c77682ad1363c8e043674ffaa0dcc47ee7 +size 1341989 diff --git a/Zen/wan_I2V_LoRA_workflow.json b/Zen/wan_I2V_LoRA_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..93b09066b86c3dd78171d878ca5f12df384c7b75 --- /dev/null +++ b/Zen/wan_I2V_LoRA_workflow.json @@ -0,0 +1,835 @@ +{ + "last_node_id": 44, + "last_link_id": 42, + "nodes": [ + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 389.7322998046875, + -13.508200645446777 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 270.7287902832031, + 165.3174591064453 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 310.204833984375, + 320.3585510253906 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 36 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 34, + "type": "Note", + "pos": [ + 904.7526245117188, + 562.6104736328125 + ], + "size": [ + 262.5184020996094, + 58 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Under 81 frames doesn't seem to work?" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 20, + 6, + 5, + 405223873797667, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 36, + "type": "Note", + "pos": [ + 106.82392120361328, + -5.778542518615723 + ], + "size": [ + 265.13958740234375, + 90.68971252441406 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "sdpa should work too, haven't tested flaash\n\nfp8_fast seems to cause huge quality degradation" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 410.6151428222656, + -130.26060485839844 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 33, + "type": "Note", + "pos": [ + 86.63419342041016, + -128.0150146484375 + ], + "size": [ + 318.5887756347656, + 58 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 408, + 408, + 29, + true, + 0, + 1, + 1 + ] + }, + { + "id": 30, + "type": "VHS_VideoCombine", + "pos": [ + 1633.1920166015625, + -278.24945068359375 + ], + "size": [ + 593.6573486328125, + 718.1015014648438 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 36 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "WanVideo2_1_00040.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 16, + "workflow": "WanVideo2_1_00040.png", + "fullpath": "C:\\Users\\drini\\OneDrive\\Documents\\ComfyUI_windows_portable\\ComfyUI\\output\\WanVideo2_1_00040.mp4" + } + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 473.90985107421875, + 451.8916931152344 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "uploads_cfcc5ea7-f518-4dcf-8edd-f35c54fefb1c.jpg", + "image" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "", + "bad quality video", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.55419921875, + -297.7393493652344 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "Muscle\\muscle_18_epochs.safetensors", + 1 + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 36, + 28, + 0, + 30, + 0, + "IMAGE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 1.1671841070450009, + "offset": { + "0": -896.97705078125, + "1": 311.2933349609375 + } + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/Zen/zen_50_epochs.safetensors b/Zen/zen_50_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3918f623e1ec27483df431eb70976d5aacd936d2 --- /dev/null +++ b/Zen/zen_50_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4adb94454a6ea91c92f688cfd2f8c41a26ddd543fb2dc79f28965f8bec23fd44 +size 359257680 diff --git a/angry-face/.gitattributes b/angry-face/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..07ebe4fbd69e49895d6a386a8a78459249e744ab --- /dev/null +++ b/angry-face/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text diff --git a/angry-face/README.md b/angry-face/README.md new file mode 100644 index 0000000000000000000000000000000000000000..de8de996b8404b6c71f122675dba22011adc29f4 --- /dev/null +++ b/angry-face/README.md @@ -0,0 +1,118 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The man begins with a neutral expression. His expression changes to 4ngr23 angry face, and he starts yelling. He then throws his arms up while making the 4ngr23 angry face. + output: + url: example_videos/1.mp4 +- text: >- + The video starts with a man looking at the camera with a neutral face. Then his facial expression changes to 4ngr23 angry face, and he begins to yell with clenched fists. + output: + url: example_videos/2.mp4 +- text: >- + The video starts with a man looking forward with a neutral expression. Then his facial expression turns to 4ngr23 angry face, clenching his fists. The man then begins yelling and making the 4ngr23 angry face. + output: + url: example_videos/3.mp4 +--- + +
+

Angry Face LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make yourself or your friends angry!

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [angry_face_5_epochs.safetensors](./angry_face_5_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: 4ngr23 angry face

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 50 seconds of video comprised of 11 short clips (each clip captioned separately) of people being angry.
  • +
  • Epochs: 5
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/angry-face/angry_face_5_epochs.safetensors b/angry-face/angry_face_5_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7577c9bcf907fe8b41407c846662c80cd9dc86e --- /dev/null +++ b/angry-face/angry_face_5_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c1345180ed79eadd88b2b95a9b5da9b782568c1f21d9bd310f63a3321084ac1 +size 359257680 diff --git a/angry-face/example_videos/1.mp4 b/angry-face/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f61a0f1bbe4a70dd8378ef516163ddf7c52601e1 --- /dev/null +++ b/angry-face/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5a568a3c5530a20e3b4afecfb9be6def75f16bf18d48817e128eb825644b6d +size 637768 diff --git a/angry-face/example_videos/2.mp4 b/angry-face/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..59470c62fafa83ab8e4120929205437cf611e257 --- /dev/null +++ b/angry-face/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59815549dd19497445be5dd2ef738eb74b409f3bd2e943250b62cc2a977b827d +size 918827 diff --git a/angry-face/example_videos/3.mp4 b/angry-face/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b0291f0d2942052d43df59f024b9b033685808fc --- /dev/null +++ b/angry-face/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a24a61e137c4c37d4917fb5b2a41d80ad6b146bec9b74ad2e612ce1e126829 +size 813965 diff --git a/angry-face/workflow_I2V/wan_img2vid_lora_workflow.json b/angry-face/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/angry-face/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/angry-face/workflow_I2V/workflow_screenshot.png b/angry-face/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/angry-face/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/clone.sh b/clone.sh new file mode 100644 index 0000000000000000000000000000000000000000..583bdd5159562bd0c18641f8a1e1a7aded845667 --- /dev/null +++ b/clone.sh @@ -0,0 +1,39 @@ +git clone https://huggingface.co/Remade-AI/Squish && +git clone https://huggingface.co/Remade-AI/Rotate && +git clone https://huggingface.co/Remade-AI/Inflate && +git clone https://huggingface.co/Remade-AI/Cakeify && +git clone https://huggingface.co/Remade-AI/Deflate && +git clone https://huggingface.co/Remade-AI/Crush && +git clone https://huggingface.co/Remade-AI/Gun-Shooting && +git clone https://huggingface.co/Remade-AI/Muscle && +git clone https://huggingface.co/Remade-AI/Bride && +git clone https://huggingface.co/Remade-AI/Puppy && +git clone https://huggingface.co/Remade-AI/Baby && +git clone https://huggingface.co/Remade-AI/VIP && +git clone https://huggingface.co/Remade-AI/Mona-Lisa && +git clone https://huggingface.co/Remade-AI/Princess && +git clone https://huggingface.co/Remade-AI/Jungle && +git clone https://huggingface.co/Remade-AI/Pirate-Captain && +git clone https://huggingface.co/Remade-AI/Samurai && +git clone https://huggingface.co/Remade-AI/Zen && +git clone https://huggingface.co/Remade-AI/Assassin && +git clone https://huggingface.co/Remade-AI/Warrior && +git clone https://huggingface.co/Remade-AI/Painting && +git clone https://huggingface.co/Remade-AI/Disney-Princess && +git clone https://huggingface.co/Remade-AI/Snow-White && +git clone https://huggingface.co/Remade-AI/Classy && +git clone https://huggingface.co/Remade-AI/Fus-Ro-Dah && +git clone https://huggingface.co/Remade-AI/Hug-Jesus && +git clone https://huggingface.co/Remade-AI/Super-Saiyan && +git clone https://huggingface.co/Remade-AI/Robot-Face-Reveal && +git clone https://huggingface.co/Remade-AI/Explode && +git clone https://huggingface.co/Remade-AI/Electrify && +git clone https://huggingface.co/Remade-AI/Dolly-Effect && +git clone https://huggingface.co/Remade-AI/Hulk-Transformation && +git clone https://huggingface.co/Remade-AI/Selfie-With-Younger-Self && +git clone https://huggingface.co/Remade-AI/angry-face && +git clone https://huggingface.co/Remade-AI/kissing && +git clone https://huggingface.co/Remade-AI/crying && +git clone https://huggingface.co/Remade-AI/Cartoon_Jaw_Drop && +git clone https://huggingface.co/Remade-AI/Laughing && +git clone https://huggingface.co/Remade-AI/Jumpscare \ No newline at end of file diff --git a/crying/.gitattributes b/crying/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..b2ef8347a4eaa53aab5388ff3daf6161f58e7937 --- /dev/null +++ b/crying/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/crying/README.md b/crying/README.md new file mode 100644 index 0000000000000000000000000000000000000000..23600eb570f05e12e4ec9977eee86f9499b827d9 --- /dev/null +++ b/crying/README.md @@ -0,0 +1,118 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + The video starts with a man, appearing with a sad expression. Then a tear rolls down his cheek, as he is cr471ng crying. + output: + url: example_videos/1.mp4 +- text: >- + The video starts with a man with a solemn expression. Then a tear rolls down his cheek, as he is cr471ng crying. + output: + url: example_videos/2.mp4 +- text: >- + The video starts with a woman smiling at the camera, but her face quickly turns to an expression of deep cr471ng crying as tears well in her eyes. She covers her face with both hands, her watery eyes and sad expression are clearly visible as she continues the cr471ng crying. + output: + url: example_videos/3.mp4 +--- + +
+

Crying LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make yourself or your friends cry!

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [crying_20_epochs.safetensors](./crying_20_epochs.safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: cr471ng crying

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 50 seconds of video comprised of 10 short clips (each clip captioned separately) of people crying.
  • +
  • Epochs: 20
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/crying/crying_20_epochs.safetensors b/crying/crying_20_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2338779f7a7a80a10ca69583ef89f7dbfdcc847e --- /dev/null +++ b/crying/crying_20_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644eb73f513d66d37789f6910c8f04de1f3a2cbea40defc8c63d1f4ffed842c7 +size 359257680 diff --git a/crying/example_videos/.DS_Store b/crying/example_videos/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6 Binary files /dev/null and b/crying/example_videos/.DS_Store differ diff --git a/crying/example_videos/1.mp4 b/crying/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b006244097b03160ee49ba0985ec0a6fefe4b085 --- /dev/null +++ b/crying/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:761377ff344e2524ed2a2dc7a3674afb7d642cdabcabf347a3e317d44748c840 +size 596830 diff --git a/crying/example_videos/2.mp4 b/crying/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..c17fcdedc3365f20f39bfc24f28148d307b0acac --- /dev/null +++ b/crying/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2703c8c7a77bb2459881f4abdca2f65da3e787472100f6fc26d07cd104757c2 +size 434898 diff --git a/crying/example_videos/3.mp4 b/crying/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..157ce8020aded790760432c5ffb5cafd2173f435 --- /dev/null +++ b/crying/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d359858ab7156c918fa059677818c95c4d9cd80004250684c3e1f26f2d04697 +size 780545 diff --git a/crying/workflow_I2V/wan_img2vid_lora_workflow.json b/crying/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/crying/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/crying/workflow_I2V/workflow_screenshot.png b/crying/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/crying/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905 diff --git a/kissing/.gitattributes b/kissing/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..b2ef8347a4eaa53aab5388ff3daf6161f58e7937 --- /dev/null +++ b/kissing/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +workflow_I2V/workflow_screenshot.png filter=lfs diff=lfs merge=lfs -text +example_videos/1.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/2.mp4 filter=lfs diff=lfs merge=lfs -text +example_videos/3.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/kissing/README.md b/kissing/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ce9346260bab1366259865e49a30c058917b019b --- /dev/null +++ b/kissing/README.md @@ -0,0 +1,118 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Wan-AI/Wan2.1-I2V-14B-480P +- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers +pipeline_tag: image-to-video +tags: +- text-to-image +- lora +- diffusers +- template:diffusion-lora +- image-to-video +widget: +- text: >- + A man and a woman wearing jackets and hats are standing close together in the snowy mountains. The man is standing facing the woman, then they engage in k144ing kissing. + output: + url: example_videos/1.mp4 +- text: >- + A man with a beard is shown smiling. A woman comes into the scene and starts passionately k144ing kissing the man. + output: + url: example_videos/2.mp4 +- text: >- + A man and a woman are embracing near a lake with mountains in the background. They are k144ing kissing, while still embracing each other. + output: + url: example_videos/3.mp4 +--- + +
+

Kissing LoRA for Wan2.1 14B I2V 480p

+ +
+

Overview

+

This LoRA is trained on the Wan2.1 14B I2V 480p model and allows you to make yourself kiss your partner (or an AI generated one)!

+
+ +
+

Features

+
    +
  • Trained on the Wan2.1 14B 480p I2V base model
  • +
  • Consistent results across different object types
  • +
  • Simple prompt structure that's easy to adapt
  • +
+
+ +
+

Community

+
    +
  • Discord: Join our community to generate videos with this LoRA for free
  • +
  • Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!
  • +
+
+
+ + + +# Model File and Inference Workflow + +## 📥 Download Links: + +- [kissing_30_epochs..safetensors](./kissing_30_epochs..safetensors) - LoRA Model File +- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI + +--- +
+
+

Recommended Settings

+
    +
  • LoRA Strength: 1.0
  • +
  • Embedded Guidance Scale: 6.0
  • +
  • Flow Shift: 5.0
  • +
+
+ +
+

Trigger Words

+

The key trigger phrase is: k144ing kissing

+
+ +
+

Prompt Template

+

For prompting, check out the example prompts; this way of prompting seems to work very well.

+ + +
+

ComfyUI Workflow

+

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

+ +

See the Downloads section above for the modified workflow.

+
+
+ +
+
+

Model Information

+

The model weights are available in Safetensors format. See the Downloads section above.

+
+ +
+

Training Details

+
    +
  • Base Model: Wan2.1 14B I2V 480p
  • +
  • Training Data: Trained on 50 seconds of video comprised of 11 short clips (each clip captioned separately) of people kissing.
  • +
  • Epochs: 30
  • +
+
+ +
+

Additional Information

+

Training was done using Diffusion Pipe for Training

+
+ +
+

Acknowledgments

+

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!

+
+
\ No newline at end of file diff --git a/kissing/example_videos/.DS_Store b/kissing/example_videos/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6 Binary files /dev/null and b/kissing/example_videos/.DS_Store differ diff --git a/kissing/example_videos/1.mp4 b/kissing/example_videos/1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..aea3c04c5701c5ae49baf42ce13633680bd4ae7c --- /dev/null +++ b/kissing/example_videos/1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85df905ab4fe716f167f147dd4a52eae10d437abbd3c333dfe9326377570d701 +size 1489573 diff --git a/kissing/example_videos/2.mp4 b/kissing/example_videos/2.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..4c7706d90331d578a4ddef008b7703a17c8731bf --- /dev/null +++ b/kissing/example_videos/2.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560c8f6f372eb65bf3ed43dabaed692874de3689c05696ac22cc34d6f19fb5f0 +size 1739277 diff --git a/kissing/example_videos/3.mp4 b/kissing/example_videos/3.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..04f255ca21a34034860b8c3a07c9feee609a3fab --- /dev/null +++ b/kissing/example_videos/3.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d242cf6cfcd1f33d5ae265344755da769d54cd2e0de944112dd77231389b53aa +size 645158 diff --git a/kissing/kissing_30_epochs.safetensors b/kissing/kissing_30_epochs.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f576c211f3af41ceb0c33eef6e467e874af871be --- /dev/null +++ b/kissing/kissing_30_epochs.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7a40159b8dbd5fd33da3b90885157331f5296da0e3d2e66ecf031035dece89 +size 359257680 diff --git a/kissing/workflow_I2V/wan_img2vid_lora_workflow.json b/kissing/workflow_I2V/wan_img2vid_lora_workflow.json new file mode 100644 index 0000000000000000000000000000000000000000..330df36dacaff6499fc38582699cee215c58f50f --- /dev/null +++ b/kissing/workflow_I2V/wan_img2vid_lora_workflow.json @@ -0,0 +1,759 @@ +{ + "last_node_id": 48, + "last_link_id": 43, + "nodes": [ + { + "id": 35, + "type": "WanVideoTorchCompileSettings", + "pos": [ + 1229.75146484375, + -314.2430725097656 + ], + "size": [ + 390.5999755859375, + 178 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "localized_name": "torch_compile_args", + "type": "WANCOMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true + ] + }, + { + "id": 32, + "type": "WanVideoBlockSwap", + "pos": [ + 383.29461669921875, + -221.3290252685547 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [ + 39 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoBlockSwap" + }, + "widgets_values": [ + 10 + ] + }, + { + "id": 11, + "type": "LoadWanVideoT5TextEncoder", + "pos": [ + 327.5020751953125, + -107.61225891113281 + ], + "size": [ + 377.1661376953125, + 130 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_t5_model", + "localized_name": "wan_t5_model", + "type": "WANTEXTENCODER", + "links": [ + 15 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoT5TextEncoder" + }, + "widgets_values": [ + "umt5-xxl-enc-bf16.safetensors", + "bf16", + "offload_device", + "disabled" + ] + }, + { + "id": 13, + "type": "LoadWanVideoClipTextEncoder", + "pos": [ + 252.51512145996094, + 84.87367248535156 + ], + "size": [ + 510.6601257324219, + 106 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "wan_clip_model", + "localized_name": "wan_clip_model", + "type": "WANCLIP", + "links": [ + 17 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "LoadWanVideoClipTextEncoder" + }, + "widgets_values": [ + "open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors", + "fp16", + "offload_device" + ] + }, + { + "id": 21, + "type": "WanVideoVAELoader", + "pos": [ + 311.7225646972656, + 244.46807861328125 + ], + "size": [ + 441.94390869140625, + 90.83087158203125 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "links": [ + 21, + 34 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoVAELoader" + }, + "widgets_values": [ + "Wan2_1_VAE_bf16.safetensors", + "fp16" + ] + }, + { + "id": 41, + "type": "WanVideoLoraSelect", + "pos": [ + 361.02728271484375, + -383.58984375 + ], + "size": [ + 349.4956359863281, + 106.13947296142578 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "prev_lora", + "localized_name": "prev_lora", + "type": "WANVIDLORA", + "shape": 7, + "link": null + }, + { + "name": "blocks", + "localized_name": "blocks", + "type": "SELECTEDBLOCKS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "links": [ + 41 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoLoraSelect" + }, + "widgets_values": [ + "super_saiyan_35_epochs.safetensors", + 1 + ] + }, + { + "id": 22, + "type": "WanVideoModelLoader", + "pos": [ + 736.3001098632812, + -306.7892761230469 + ], + "size": [ + 477.4410095214844, + 226.43276977539062 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "localized_name": "compile_args", + "type": "WANCOMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "localized_name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": 39 + }, + { + "name": "lora", + "localized_name": "lora", + "type": "WANVIDLORA", + "shape": 7, + "link": 41 + } + ], + "outputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "links": [ + 29 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoModelLoader" + }, + "widgets_values": [ + "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn" + ] + }, + { + "id": 16, + "type": "WanVideoTextEncode", + "pos": [ + 795.1016235351562, + -16.162620544433594 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "t5", + "localized_name": "t5", + "type": "WANTEXTENCODER", + "link": 15 + } + ], + "outputs": [ + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "links": [ + 30 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoTextEncode" + }, + "widgets_values": [ + "A pair of men clench their fists, staring forward. Their hair brightens to glowing yellow, spiking up as gold energy surges around their bodies. The background pulses with yellow light, and sparks crackle in the air during their 5up3r super saiyan transformation, real life style.\n", + "cartoon", + true, + [ + false, + true + ], + [ + false, + true + ] + ] + }, + { + "id": 27, + "type": "WanVideoSampler", + "pos": [ + 1216.8856201171875, + -52.87528991699219 + ], + "size": [ + 315, + 330 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "localized_name": "model", + "type": "WANVIDEOMODEL", + "link": 29 + }, + { + "name": "text_embeds", + "localized_name": "text_embeds", + "type": "WANVIDEOTEXTEMBEDS", + "link": 30 + }, + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "link": 32 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "localized_name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "links": [ + 33 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoSampler" + }, + "widgets_values": [ + 30, + 6, + 5, + 290077345463967, + "randomize", + true, + "dpm++", + 0, + 1 + ] + }, + { + "id": 17, + "type": "WanVideoImageClipEncode", + "pos": [ + 875.01025390625, + 278.4588623046875 + ], + "size": [ + 315, + 242 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "clip", + "localized_name": "clip", + "type": "WANCLIP", + "link": 17 + }, + { + "name": "image", + "localized_name": "image", + "type": "IMAGE", + "link": 18 + }, + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 21 + } + ], + "outputs": [ + { + "name": "image_embeds", + "localized_name": "image_embeds", + "type": "WANVIDIMAGE_EMBEDS", + "links": [ + 32 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoImageClipEncode" + }, + "widgets_values": [ + 720, + 720, + 81, + true, + 0, + 1, + 1 + ] + }, + { + "id": 28, + "type": "WanVideoDecode", + "pos": [ + 1220.4002685546875, + 371.8823547363281 + ], + "size": [ + 315, + 174 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "vae", + "localized_name": "vae", + "type": "WANVAE", + "link": 34 + }, + { + "name": "samples", + "localized_name": "samples", + "type": "LATENT", + "link": 33 + } + ], + "outputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "links": [ + 43 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "WanVideoDecode" + }, + "widgets_values": [ + true, + 272, + 272, + 144, + 128 + ] + }, + { + "id": 48, + "type": "VHS_VideoCombine", + "pos": [ + 1657.403564453125, + -73.2489013671875 + ], + "size": [ + 365.15972900390625, + 376 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "images", + "localized_name": "images", + "type": "IMAGE", + "link": 43 + }, + { + "name": "audio", + "localized_name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "localized_name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "localized_name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "localized_name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 16, + "loop_count": 0, + "filename_prefix": "WanVideo2_1", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": {}, + "muted": false + } + } + }, + { + "id": 18, + "type": "LoadImage", + "pos": [ + 498.1949462890625, + 388.14373779296875 + ], + "size": [ + 255.50192260742188, + 314 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "localized_name": "IMAGE", + "type": "IMAGE", + "links": [ + 18 + ] + }, + { + "name": "MASK", + "localized_name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "Logo color@4x-100.jpg", + "image" + ] + } + ], + "links": [ + [ + 15, + 11, + 0, + 16, + 0, + "WANTEXTENCODER" + ], + [ + 17, + 13, + 0, + 17, + 0, + "WANCLIP" + ], + [ + 18, + 18, + 0, + 17, + 1, + "IMAGE" + ], + [ + 21, + 21, + 0, + 17, + 2, + "VAE" + ], + [ + 29, + 22, + 0, + 27, + 0, + "WANVIDEOMODEL" + ], + [ + 30, + 16, + 0, + 27, + 1, + "WANVIDEOTEXTEMBEDS" + ], + [ + 32, + 17, + 0, + 27, + 2, + "WANVIDIMAGE_EMBEDS" + ], + [ + 33, + 27, + 0, + 28, + 1, + "LATENT" + ], + [ + 34, + 21, + 0, + 28, + 0, + "VAE" + ], + [ + 39, + 32, + 0, + 22, + 1, + "BLOCKSWAPARGS" + ], + [ + 41, + 41, + 0, + 22, + 2, + "WANVIDLORA" + ], + [ + 43, + 28, + 0, + 48, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.7247295000000005, + "offset": [ + 81.1754729752961, + 489.9560918264742 + ] + }, + "node_versions": { + "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a", + "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506", + "comfy-core": "0.3.18" + }, + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true, + "ue_links": [], + "workspace_info": { + "id": "mZ-DLut47Mni3MFPHoL4Y", + "saveLock": false, + "cloudID": null, + "coverMediaPath": null + } + }, + "version": 0.4 +} \ No newline at end of file diff --git a/kissing/workflow_I2V/workflow_screenshot.png b/kissing/workflow_I2V/workflow_screenshot.png new file mode 100644 index 0000000000000000000000000000000000000000..5ac602e61d37fdefcafcdc38b1d0da6775446d26 --- /dev/null +++ b/kissing/workflow_I2V/workflow_screenshot.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1ad76dc0e46eb4acaa1f76b1a113e8e0e7997ea77e0042c424f585861b81ca +size 278905