text-to-video / requirements.txt
Felix9390's picture
Duplicate from damo-vilab/modelscope-text-to-video-synthesis
d74ee44
raw
history blame
189 Bytes
accelerate==0.17.1
git+https://github.com/huggingface/diffusers@9dc8444
gradio==3.23.0
huggingface-hub==0.13.3
imageio[ffmpeg]==2.26.1
torch==2.0.0
torchvision==0.15.1
transformers==4.27.2