Remade commited on
Commit
3f79380
·
verified ·
1 Parent(s): 95c1b33

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +121 -0
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - Wan-AI/Wan2.1-T2V-14B
7
+ pipeline_tag: text-to-video
8
+ tags:
9
+ - text-to-video
10
+ - text-to-image
11
+ - lora
12
+ - diffusers
13
+ - template:diffusion-lora
14
+ widget:
15
+ - text: >-
16
+ l3g0_5ty13 Lego animation style, a close-up shot of a Lego pirate minifigure with a black tricorn hat, an eye patch, and a red coat. He is holding a silver cutlass in his right hand, and a small Lego parrot is perched on his shoulder. The background is a blurry mix of blue and brown Lego bricks resembling an ocean scene.
17
+ output:
18
+ url: example_videos/1.mp4
19
+ - text: >-
20
+ l3g0_5ty13 Lego animation style, a Lego figure of a cat with a blue bow tie is walking down a street, with cars driving on the road beside him.
21
+ output:
22
+ url: example_videos/2.mp4
23
+ - text: >-
24
+ l3g0_5ty13 Lego animation style, a Lego spaceship flies through space, with planets in the background.
25
+ output:
26
+ url: example_videos/3.mp4
27
+ - text: >-
28
+ l3g0_5ty13 Lego animation style, a close-up shot of a Lego minifigure with sunglasses and a black leather jacket, sitting inside a Lego sports car. His hands grip the tiny steering wheel, and the dashboard has tiny glowing screens. The background is a blurry city filled with neon Lego signs.
29
+ output:
30
+ url: example_videos/4.mp4
31
+ ---
32
+
33
+ <div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
34
+ <h1 style="color: #24292e; margin-top: 0;">Lego Style LoRA for Wan2.1 14B T2V</h1>
35
+
36
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
37
+ <h2 style="color: #24292e; margin-top: 0;">Overview</h2>
38
+ <p>This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate videos in Lego style!</p>
39
+ </div>
40
+
41
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
42
+ <h2 style="color: #24292e; margin-top: 0;">Features</h2>
43
+ <ul style="margin-bottom: 0;">
44
+ <li>Trained on the Wan2.1 14B T2V base model</li>
45
+ <li>Consistent results across different object and scenes types</li>
46
+ <li>Simple prompt examples that are easy to adapt</li>
47
+ </ul>
48
+ </div>
49
+
50
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
51
+ <h2 style="color: #24292e; margin-top: 0;">Community</h2>
52
+ <ul style="margin-bottom: 0;">
53
+ <li><b>Discord:</b> <a href="https://remade.ai/join-discord?utm_source=Huggingface&utm_medium=Social&utm_campaign=model_release&utm_content=lego" style="color: #0366d6; text-decoration: none;">Join our community</a> to generate videos with this LoRA for free</li>
54
+ <li><b>Request LoRAs:</b> We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!</li>
55
+ </ul>
56
+ </div>
57
+ </div>
58
+
59
+ <Gallery />
60
+
61
+ # Model File and Inference Workflow
62
+
63
+ ## 📥 Download Links:
64
+
65
+ - [lego_35_epochs.safetensors](./lego_35_epochs.safetensors) - LoRA Model File
66
+ - [wan_txt2vid_lora_workflow.json](./workflow_T2V/wan_txt2vid_lora_workflow.json) - Wan T2V with LoRA Workflow for ComfyUI
67
+
68
+ ---
69
+ <div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
70
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
71
+ <h2 style="color: #24292e; margin-top: 0;">Recommended Settings</h2>
72
+ <ul style="margin-bottom: 0;">
73
+ <li><b>LoRA Strength:</b> 1.0</li>
74
+ <li><b>Embedded Guidance Scale:</b> 6.0</li>
75
+ <li><b>Flow Shift:</b> 5.0</li>
76
+ </ul>
77
+ </div>
78
+
79
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
80
+ <h2 style="color: #24292e; margin-top: 0;">Trigger Words</h2>
81
+ <p>The key trigger phrase is: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">l3g0_5ty13 Lego animation style</code></p>
82
+ </div>
83
+
84
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
85
+ <h2 style="color: #24292e; margin-top: 0;">Prompt Template</h2>
86
+ <p>For prompting, check out the example prompts; this way of prompting seems to work very well.</p>
87
+
88
+
89
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
90
+ <h2 style="color: #24292e; margin-top: 0;">ComfyUI Workflow</h2>
91
+ <p>This LoRA works with a modified version of <a href="https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/wanvideo_T2V_example_02.json" style="color: #0366d6; text-decoration: none;">Kijai's Wan Video Wrapper workflow</a>. The main modification is adding a Wan LoRA node connected to the base model.</p>
92
+ <img src="./workflow_T2V/workflow_screenshot.png" style="width: 100%; border-radius: 8px; margin: 15px 0; box-shadow: 0 4px 8px rgba(0,0,0,0.1);">
93
+ <p>See the Downloads section above for the modified workflow.</p>
94
+ </div>
95
+ </div>
96
+
97
+ <div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
98
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
99
+ <h2 style="color: #24292e; margin-top: 0;">Model Information</h2>
100
+ <p>The model weights are available in Safetensors format. See the Downloads section above.</p>
101
+ </div>
102
+
103
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
104
+ <h2 style="color: #24292e; margin-top: 0;">Training Details</h2>
105
+ <ul style="margin-bottom: 0;">
106
+ <li><b>Base Model:</b> Wan2.1 14B T2V</li>
107
+ <li><b>Training Data:</b> Trained on 1 minute of video comprised of 25 short clips (each clip captioned separately) of various Lego style scenes.</li>
108
+ <li><b> Epochs:</b> 35</li>
109
+ </ul>
110
+ </div>
111
+
112
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
113
+ <h2 style="color: #24292e; margin-top: 0;">Additional Information</h2>
114
+ <p>Training was done using <a href="https://github.com/tdrussell/diffusion-pipe" style="color: #0366d6; text-decoration: none;">Diffusion Pipe for Training</a></p>
115
+ </div>
116
+
117
+ <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
118
+ <h2 style="color: #24292e; margin-top: 0;">Acknowledgments</h2>
119
+ <p style="margin-bottom: 0;">Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!</p>
120
+ </div>
121
+ </div>