Text-to-Video_Playground / requirements.txt
NeuralInternet's picture
Duplicate from damo-vilab/modelscope-text-to-video-synthesis
ddc31f3
raw
history blame
100 Bytes
decord==0.6.0
fairseq==0.12.2
gradio==3.22.1
modelscope[multi-modal]==1.4.1
open_clip_torch==2.16.0