VACE-Annotators / requirements.txt
fffiloni's picture
Update requirements.txt
d6dfd68 verified
torch>=2.5.1
torchvision>=0.20.1
opencv-python>=4.9.0.80
diffusers>=0.31.0
transformers>=4.49.0
tokenizers>=0.20.3
accelerate>=1.1.1
gradio>=5.0.0
numpy>=1.23.5,<2
tqdm
imageio
easydict
ftfy
dashscope
imageio-ffmpeg
#flash_attn
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp310-cp310-linux_x86_64.whl
decord
einops
scikit-image
scikit-learn
pycocotools
timm
onnxruntime-gpu
BeautifulSoup4
wan@git+https://github.com/Wan-Video/Wan2.1
# Annotators deps
insightface
git+https://github.com/facebookresearch/sam2.git
git+https://github.com/facebookresearch/segment-anything.git
git+https://github.com/xinyu1205/recognize-anything.git
git+https://github.com/martin-chobanyan-sdc/RAFT.git
https://huggingface.co/ali-vilab/VACE-Annotators/resolve/main/gdino/groundingdino-0.1.0-cp310-cp310-linux_x86_64.whl
#groundingdino==0.1.0
#https://huggingface.co/ali-vilab/VACE-Annotators/raw/main/gdino/groundingdino-0.1.0-cp310-cp310-linux_x86_64.whl