Duplicate from vrgamedevgirl84/Wan14BT2VFusioniX

Co-authored-by: DeeJayT <[email protected]>

.gitattributes

@@ -0,0 +1,67 @@
+*.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
+*.lz4 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
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text
+videos/AnimateDiff_00001.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/FusionX_00005.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/FusionX_00012.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Video_00063.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Video_00066.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Video_00067.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Video_00068.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Video_00069.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Video_00072.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/WanVideoWrapper_VACE_startendframe_00002.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/WanVideoWrapper_VACE_startendframe_00022-audio.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/WanVideoWrapper_VACE_startendframe_00030-audio.mp4 filter=lfs diff=lfs merge=lfs -text

FusionX_LoRa/Phantom_Wan_14B_FusionX_LoRA.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef46bf8d034e367bb3157cee2d00c69bb782a6ec5c45e4c0e6d7b03d1aa96b7
+size 316822496

FusionX_LoRa/Wan2.1_I2V_14B_FusionX_LoRA.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb5df85d5bc5fba32966de8b357c7643413219479605cc933412b60305c01f8
+size 371128616

FusionX_LoRa/Wan2.1_T2V_14B_FusionX_LoRA.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c653087fa7c9163abdd1a4c627bfc483966c6d78a4426667d1185f860951c30e
+size 316822496

OtherLoRa's/DetailEnhancerV1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab17e3520fd2b8f97ea25f987017766ec8e76939b3445caa994882966e6d47e
+size 306847400

OtherLoRa's/Wan14B_RealismBoost.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd2217d7df8f2e4de76f8a890174cced33d551cffb58d42f6d6f7f7a6d1c654
+size 306848616

README.md

@@ -0,0 +1,259 @@
+---
+tags:
+- text-to-video
+- diffusion
+- merged-model
+- video-generation
+- wan2.1
+
+widget:
+- text: >-
+    Prompt: A gritty close-up of an elven princess kneeling in a rocky ravine, calming a wounded, desert dragon. Its scales are cracked, dry, She wears a crimson sash over bone-colored armor, her auburn hair half-tied back. The camera dollies in rapidly as she reaches for its eye ridge. Lighting comes from golden sunlight reflecting off surrounding rock, casting a warm, earthy hue with no artificial glow.
+  output:
+    url: videos/Video_00063.mp4
+    
+- text: >-
+    Prompt: Tight close-up of her smiling lips and sparkling eyes, catching golden hour sunlight. She wears a white sundress with floral prints and a wide-brimmed straw hat. Camera pulls back in a dolly motion, revealing her twirling under a cherry blossom tree. Petals flutter in the air, casting playful shadows. Soft lens flares enhance the euphoric, dreamlike vibe. (Before vs After — Left: Wan2.1 | Right: Merged model Wan14BT2V_MasterModel)
+  output:
+    url: videos/AnimateDiff_00001.mp4
+
+- text: >-
+    Prompt: A gritty close-up of a dwarven beastmaster’s face, his grey beard braided tightly, brows furrowed as he looks just off-camera. The camera dollies out over his shoulder, revealing a perched gryphon watching him from a boulder, its feathers rustling slightly in the breeze. The moment holds stillness and mutual trust. Lighting is early daylight, clean and sharp with strong environmental clarity.
+  output:
+    url: videos/FusionX_00012.mp4
+
+- text: >-
+    Prompt: A gritty close-up of a jungle tracker crouching low, face flushed with focus as she watches a perched macaw a few feet ahead. Her cheek twitches as she shifts forward, beads of sweat visible on her brow. The camera slowly dollies in from below her line of sight, capturing the moment her eyes widen in fascination. Lighting is rich and directional from above, creating a warm glow over her face with minimal shadows.
+  output:
+    url: videos/FusionX_00005.mp4
+
+- text: >-
+    Prompt: A gritty close-up of a battle-worn ranger kneeling in a scorched clearing, calming a wounded gryphon whose wing is torn and bloodied. Its feathers are dusky bronze with streaks of ash-gray. She wears soot-covered hunter green armor, her blonde hair pulled into a loose braid. The camera dollies in as her hand brushes the creature's sharp beak. Lighting comes from late afternoon sun filtering through smoke, casting a burnt-orange haze across the frame.
+  output:
+    url: videos/Video_00069.mp4
+
+
+
+base_model:
+- Wan-AI/Wan2.1-T2V-14B
+license: apache-2.0
+---
+
+# 🌀 Wan2.1_14B_FusionX
+
+**High-Performance Merged Text-to-Video Model**  
+Built on WAN 2.1 and fused with research-grade components for cinematic motion, detail, and speed — optimized for ComfyUI and rapid iteration in as few as 6 steps.
+
+Merged models for faster, richer motion & detail — high performance even at just 8 steps.
+
+> 📌 Important: To match the quality shown here, use the linked workflows or make sure to follow the recommended settings outlined below.
+
+---
+
+## 🚀 Overview
+
+A powerful text-to-video model built on top of **WAN 2.1 14B**, merged with several research-grade models to boost:
+
+- Motion quality
+- Scene consistency
+- Visual detail
+
+Comparable with closed-source solutions, but open and optimized for **ComfyUI** workflows.
+
+---
+
+## 💡 Inside the Fusion
+
+This model is made up of the following which is on TOP of Wan 2.1 14B 720p(FusionX would not be what it is without these Models):
+
+- **CausVid** – [Causal motion modeling for better flow and dynamics](https://github.com/tianweiy/CausVid)
+- **AccVideo** – [Better temporal alignment and speed boost](https://github.com/aejion/AccVideo)
+- **MoviiGen1.1** – [Cinematic smoothness and lighting](https://huggingface.co/ZuluVision/MoviiGen1.1)
+- **MPS Reward LoRA** – [Tuned for motion and detail](https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs)
+- **Custom LoRAs** – For texture, clarity, and small detail enhancements (Set at a very low level)
+
+All merged models are provided for research and non-commercial use only.
+Some components are subject to licenses such as CC BY-NC-SA 4.0, and do not fall under permissive licenses like Apache 2.0 or MIT.
+Please refer to each model’s original license for full usage terms.
+
+---
+
+## 🚨✨**Hey guys! Just a quick update!**
+
+We finally cooked up **FusionX LoRAs**!! 🧠💥  
+This is huge – now you can plug FusionX into your favorite workflows as a LoRA on top of the Wan base models and SkyReels models!🔌💫 
+You can still stick with the base FusionX Model if you already use it, but if you would rather have more control over the "FusionX" strength and a speed boost, then this might be for you.
+
+Oh, and there’s a **nice speed boost** too! ⚡  
+**Example:** *(RTX 5090)*  
+- FusionX as a full base model: **8 steps = 160s** ⏱️  
+- FusionX as a **LoRA on Wan 2.1 14B fp8 T2V**: **8 steps = 120s** 🚀
+
+**Bonus:** You can bump up the FusionX LoRA strength and lower your steps for a **huge speed boost** while testing/drafting.  
+Example: strength `2.00` with `3 steps` takes `72 seconds`.  
+Or lower the strength to experiment with a **less “FusionX” look**. ⚡🔍
+
+We’ve got:
+- **T2V (Text to Video)** 🎬 – works perfectly with **VACE** ⚙️  
+- **I2V (Image to Video)** 🖼️➡️📽️  
+- A dedicated **Phantom LoRA** 👻  
+The new LoRA's are [HERE](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/tree/main/FusionX_LoRa)
+Note: The LoRa's are not meant to be put on top of the FusionX main models and instead you would use them with the Wan base models.
+**New workflows**  are [HERE](https://civitai.com/models/1681541)  🛠️🚀
+
+---
+
+After lots of testing 🧪, the video quality with the LoRA is **just as good** (and sometimes **even better**! 💯)  
+That’s thanks to it being trained on the **fp16 version** of FusionX 🧬💎
+
+---
+
+### 🌀 Preview Gallery  
+*These are compressed GIF previews for quick viewing — final video outputs are higher quality.*
+
+![FusionX_00020](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00020.gif)  
+![FusionX_00021](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00021.gif)  
+![FusionX_00022](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00022.gif)  
+![FusionX_00023](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00023.gif)  
+![FusionX_00024](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00024.gif)  
+![FusionX_00025](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00025.gif)  
+![FusionX_00026](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00026.gif)  
+![FusionX_00027](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00027.gif)  
+![FusionX_00028](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00028.gif)  
+![FusionX_00029](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00029.gif)  
+![FusionX_00030](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00030.gif)  
+![FusionX_00031](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/resolve/main/videos/FusionX_00031.gif)
+
+---
+
+
+## 📂 Workflows & Model Downloads
+
+- 💡 **ComfyUI workflows** can be found here:  
+  👉 [Workflow Collection (WIP)](https://civitai.com/models/1663553)
+
+- 📦 **Model files (T2V, I2V, Phantom, VACE)**:  
+  👉 [Main Hugging Face Repo](https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/tree/main)
+
+### 🧠 GGUF Variants:
+- 🖼️ [FusionX Image-to-Video (GGUF)](https://huggingface.co/QuantStack/Wan2.1_I2V_14B_FusionX-GGUF/tree/main)  
+- 🎥 [FusionX Text-to-Video (GGUF)](https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX-GGUF/tree/main)  
+- 🎞️ [FusionX T2V VACE (for native)](https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF/tree/main)  
+- 👻 [FusionX Phantom](https://huggingface.co/QuantStack/Phantom_Wan_14B_FusionX-GGUF/tree/main)
+
+---
+## 🎬 Example Videos
+
+Want to see what FusionX can do? Check out these real outputs generated using the latest workflows and settings:
+
+- **Text-to-Video**  
+  👉 [Watch Examples](https://civitai.com/posts/17874424)
+
+- **Image-to-Video**  
+  👉 [Watch Examples](https://civitai.com/posts/18029174)
+
+- **Phantom Mode**  
+  👉 [Watch Examples](https://civitai.com/posts/17986906)
+
+- **VACE Integration**  
+  👉 [Watch Examples](https://civitai.com/posts/18080876)
+
+---
+
+## 🔧 Usage Details
+
+### Text-to-Video
+
+- **CGF**: Must be set to `1`  
+- **Shift**:  
+  - `1024x576`: Start at `1`  
+  - `1080x720`: Start at `2`  
+  - For realism → lower values  
+  - For stylized → test `3–9`
+- **Scheduler**:  
+  - Recommended: `uni_pc`  
+  - Alternative: `flowmatch_causvid` (better for some details)
+
+### Image-to-Video
+
+- **CGF**: `1`
+- **Shift**: `2` works best in most cases
+- **Scheduler**:  
+  - Recommended: `dmp++_sde/beta`  
+- To boost motion and reduce slow-mo effect:
+  - Frame count: `121`
+  - FPS: `24`
+
+---
+
+## 🛠 Technical Notes
+
+- Works in as few as **6 steps**
+- Best quality at **8–10 steps**
+- Drop-in replacement for `Wan2.1-T2V-14B`
+- Up to **50% faster rendering**, especially with **SageAttn**
+- Works natively and with **Kaji Wan Wrapper**  
+  [Wrapper GitHub](https://github.com/kijai/ComfyUI-WanVideoWrapper)
+- Do **not** re-add merged LoRAs (CausVid, AccVideo, MPS)
+- Feel free to add **other LoRAs** for style/variation
+- Native WAN workflows also supported (slightly slower)
+
+---
+
+## 🧪 Performance Tips
+
+- RTX 5090 → ~138 sec/video at 1024x576 / 81 frames
+- If VRAM is limited:
+  - Enable block swapping
+  - Start with `5` blocks and adjust as needed
+- Use **SageAttn** for ~30% speedup (wrapper only)
+- Do **not** use `teacache`
+- "Enhance a video" (tested): Adds vibrance (try values 2–4)
+- "SLG" not tested — feel free to explore
+
+---
+
+## 🧠 Prompt Help
+
+Want better cinematic prompts? Try the **WAN Cinematic Video Prompt Generator GPT** — it adds visual richness and makes a big difference in quality. [Download Here](https://chatgpt.com/g/g-67c3a6d6d19c81919b3247d2bfd01d0b-wan-cinematic-video-prompt-generator)
+
+---
+
+## 📣 Join The Community
+
+We’re building a friendly space to chat, share outputs, and get help.
+
+- Motion LoRAs coming soon
+- Tips, updates, and support from other users
+
+👉 [Join the Discord](https://discord.com/invite/hxPmmXmRW3)
+
+---
+
+## ⚖️ License
+
+Some merged components use permissive licenses (Apache 2.0 / MIT),  
+**but others** — such as those from research models like *CausVid* — may be released under **non-commercial licenses** (e.g., [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)).
+
+- ✅ You **can** use, modify, and redistribute **under original license terms**  
+- ❗ You **must** retain and respect the license of each component  
+- ⚠️ **Commercial use is not permitted** for models or components under non-commercial licenses  
+- 📌 Outputs are **not automatically licensed** — do your own due diligence
+
+This model is intended for **research, education, and personal use only**.  
+For commercial use or monetization, please consult a legal advisor and verify all component licenses.
+
+---
+
+## 🙏 Credits
+
+- WAN Team (base model)
+- aejion (AccVideo)
+- Tianwei Yin (CausVid)
+- ZuluVision (MoviiGen)
+- Alibaba PAI (MPS LoRA)
+- Kijai (ComfyUI Wrapper)
+
+And thanks to the open-source community!
+
+---

Wan14BT2VFusioniX_Phantom_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16663707f096f8df0ab1f2c5bb96fd755795a8ed7e3b28aa1bdf9f3ed1fc0355
+size 28577796288

Wan14BT2VFusioniX_fp16_.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c098c8547b273149e27545b8aba08cb6473a462a4d7ff30b96f5da21fecd3b
+size 28577792224

Wan14Bi2vFusioniX.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f24cedf1b9bb81353f72d0dc61ddb6c5b472c40b8063d7390507fd38b578041
+size 16397285160

Wan14Bi2vFusioniX_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20969ba3ff6ff1690085d03dd013ff03ace2154273cf7bc0906467647de8e0f6
+size 32791417192

WanT2V_MasterModel.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dcda1af22353047ee5e30273dc7f165ce0cdb99e9c112d34a9974484ddc924
+size 14289641560

videos/AnimateDiff_00001.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6153dcdf80d99f7cc600dd978b075b01a8fec812edca5b19792add0b77cb9e20
+size 5100634

videos/FusionX_00005.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b991cb3201f94de3f30f816b217546de93628bfea87886f1b475dd75da60474e
+size 1088660

videos/FusionX_00012.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1b2dc8d5a64588fb8ed521ddb29e1aec04fab1ee28e70176da8de5ac5d593d
+size 2118658

videos/Video_00063.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47afe9495613be2cf4278934772a59469b6dcaf91364ab5791eef8f73699e17b
+size 2110834

videos/Video_00066.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1df8757d0fb0bed551dd5df31d421771720fb86bb3261225e0e015ae59c78a
+size 1448775

videos/Video_00067.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7f1d7e38e5398073d5d5e0edf903c0bc4c9e81d526406b16656485fe674288
+size 1487338

videos/Video_00068.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40df8803ae32755bc92716029322552b15bc938d20a455ea7c898c2479f055d
+size 2309856

videos/Video_00069.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3ac3a4c17aa52b45d6bc5d8135cc27fcb20950660d11120533e1253c7c7ae5
+size 1484759

videos/Video_00072.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4abc697418a66b788a6c172c4e174702fe7a3273151a4ea07cc0f666e339d01
+size 2822831

videos/WanVideoWrapper_VACE_startendframe_00002.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792c066d8d6d030cb2b53e69aa6b9e688ca8ca87f04cc98147309c8a2b858e2f
+size 2921379

videos/WanVideoWrapper_VACE_startendframe_00022-audio.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c421191e5e2e21f0e34e39c03487ed154a7a03157716cf41ca117a791d185c0e
+size 2084171

videos/WanVideoWrapper_VACE_startendframe_00030-audio.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe0d8e4d14c0caa3734c06aee4a23bc11754d40384af14f70f91f6b42f88fe3
+size 2156290