diffusers==0.30.2 accelerate==0.28.0 numpy>=1.24.4,<2.3.0 opencv-python>=4.9.0.80 soundfile==0.12.1 transformers==4.39.2 huggingface_hub==0.30.2 librosa==0.11.0 einops==0.8.1 gradio==5.24.0 gdown requests imageio[ffmpeg] omegaconf ffmpeg-python moviepy albumentations>=2.0.8 scikit-image>=0.25.2