Instructions to use joyfox/Wan2.1-Fight-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use joyfox/Wan2.1-Fight-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.1-I2V-14B-720P,Wan-AI/Wan2.1-I2V-14B-720P-Diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("joyfox/Wan2.1-Fight-LoRA") prompt = "dajia,这是一个两个人对打得视频,镜头拉远,保持人物不变,这两个人开始对打,两个人不断旋转,拳打脚踢,姿势像是传统武术, 十分专业,两个人相互比试,打的有来有回,突然左边的人腾空跳起,保持飞在空中用腿不停踢另一个人上半身, 男人被踢得一边用手阻挡女人的飞踢一边后退,镜头跟随,保持背景和人物的服装不改变." input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png") image = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- result/teaser_00001.gif +3 -0
- result/teaser_00002.gif +3 -0
- result/teaser_00003.gif +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
result/teaser_00001.gif filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
result/teaser_00002.gif filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
result/teaser_00003.gif filter=lfs diff=lfs merge=lfs -text
|
result/teaser_00001.gif
ADDED
|
Git LFS Details
|
result/teaser_00002.gif
ADDED
|
Git LFS Details
|
result/teaser_00003.gif
ADDED
|
Git LFS Details
|