Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
base_model:
|
6 |
+
- Wan-AI/Wan2.1-I2V-14B-480P
|
7 |
+
- Wan-AI/Wan2.1-I2V-14B-480P-Diffusers
|
8 |
+
pipeline_tag: image-to-video
|
9 |
+
tags:
|
10 |
+
- text-to-image
|
11 |
+
- lora
|
12 |
+
- diffusers
|
13 |
+
- template:diffusion-lora
|
14 |
+
- image-to-video
|
15 |
+
widget:
|
16 |
+
- text: >-
|
17 |
+
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.
|
18 |
+
output:
|
19 |
+
url: example_videos/1.mp4
|
20 |
+
- text: >-
|
21 |
+
A man with a beard is shown smiling. A woman comes into the scene and starts passionately k144ing kissing the man.
|
22 |
+
output:
|
23 |
+
url: example_videos/2.mp4
|
24 |
+
- text: >-
|
25 |
+
A man and a woman are embracing near a lake with mountains in the background. They are k144ing kissing, while still embracing each other.
|
26 |
+
output:
|
27 |
+
url: example_videos/3.mp4
|
28 |
+
---
|
29 |
+
|
30 |
+
<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
|
31 |
+
<h1 style="color: #24292e; margin-top: 0;">Kissing LoRA for Wan2.1 14B I2V 480p</h1>
|
32 |
+
|
33 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
34 |
+
<h2 style="color: #24292e; margin-top: 0;">Overview</h2>
|
35 |
+
<p>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)!</p>
|
36 |
+
</div>
|
37 |
+
|
38 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
39 |
+
<h2 style="color: #24292e; margin-top: 0;">Features</h2>
|
40 |
+
<ul style="margin-bottom: 0;">
|
41 |
+
<li>Trained on the Wan2.1 14B 480p I2V base model</li>
|
42 |
+
<li>Consistent results across different object types</li>
|
43 |
+
<li>Simple prompt structure that's easy to adapt</li>
|
44 |
+
</ul>
|
45 |
+
</div>
|
46 |
+
|
47 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
48 |
+
<h2 style="color: #24292e; margin-top: 0;">Community</h2>
|
49 |
+
<ul style="margin-bottom: 0;">
|
50 |
+
<li><b>Discord:</b> <a href="https://remade.ai/join-discord?utm_source=Huggingface&utm_medium=Social&utm_campaign=model_release&utm_content=kissing" style="color: #0366d6; text-decoration: none;">Join our community</a> to generate videos with this LoRA for free</li>
|
51 |
+
<li><b>Request LoRAs:</b> We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!</li>
|
52 |
+
</ul>
|
53 |
+
</div>
|
54 |
+
</div>
|
55 |
+
|
56 |
+
<Gallery />
|
57 |
+
|
58 |
+
# Model File and Inference Workflow
|
59 |
+
|
60 |
+
## 📥 Download Links:
|
61 |
+
|
62 |
+
- [kissing_30_epochs..safetensors](./kissing_30_epochs..safetensors) - LoRA Model File
|
63 |
+
- [wan_img2vid_lora_workflow.json](./workflow_I2V/wan_img2vid_lora_workflow.json) - Wan I2V with LoRA Workflow for ComfyUI
|
64 |
+
|
65 |
+
---
|
66 |
+
<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
|
67 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
68 |
+
<h2 style="color: #24292e; margin-top: 0;">Recommended Settings</h2>
|
69 |
+
<ul style="margin-bottom: 0;">
|
70 |
+
<li><b>LoRA Strength:</b> 1.0</li>
|
71 |
+
<li><b>Embedded Guidance Scale:</b> 6.0</li>
|
72 |
+
<li><b>Flow Shift:</b> 5.0</li>
|
73 |
+
</ul>
|
74 |
+
</div>
|
75 |
+
|
76 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
77 |
+
<h2 style="color: #24292e; margin-top: 0;">Trigger Words</h2>
|
78 |
+
<p>The key trigger phrase is: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;"> k144ing kissing</code></p>
|
79 |
+
</div>
|
80 |
+
|
81 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
82 |
+
<h2 style="color: #24292e; margin-top: 0;">Prompt Template</h2>
|
83 |
+
<p>For prompting, check out the example prompts; this way of prompting seems to work very well.</p>
|
84 |
+
|
85 |
+
|
86 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
87 |
+
<h2 style="color: #24292e; margin-top: 0;">ComfyUI Workflow</h2>
|
88 |
+
<p>This LoRA works with a modified version of <a href="https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/wanvideo_480p_I2V_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>
|
89 |
+
<img src="./workflow_I2V/workflow_screenshot.png" style="width: 100%; border-radius: 8px; margin: 15px 0; box-shadow: 0 4px 8px rgba(0,0,0,0.1);">
|
90 |
+
<p>See the Downloads section above for the modified workflow.</p>
|
91 |
+
</div>
|
92 |
+
</div>
|
93 |
+
|
94 |
+
<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
|
95 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
96 |
+
<h2 style="color: #24292e; margin-top: 0;">Model Information</h2>
|
97 |
+
<p>The model weights are available in Safetensors format. See the Downloads section above.</p>
|
98 |
+
</div>
|
99 |
+
|
100 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
101 |
+
<h2 style="color: #24292e; margin-top: 0;">Training Details</h2>
|
102 |
+
<ul style="margin-bottom: 0;">
|
103 |
+
<li><b>Base Model:</b> Wan2.1 14B I2V 480p</li>
|
104 |
+
<li><b>Training Data:</b> Trained on 50 seconds of video comprised of 11 short clips (each clip captioned separately) of people kissing.</li>
|
105 |
+
<li><b> Epochs:</b> 30</li>
|
106 |
+
</ul>
|
107 |
+
</div>
|
108 |
+
|
109 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
110 |
+
<h2 style="color: #24292e; margin-top: 0;">Additional Information</h2>
|
111 |
+
<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>
|
112 |
+
</div>
|
113 |
+
|
114 |
+
<div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
|
115 |
+
<h2 style="color: #24292e; margin-top: 0;">Acknowledgments</h2>
|
116 |
+
<p style="margin-bottom: 0;">Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!</p>
|
117 |
+
</div>
|
118 |
+
</div>
|