| numpy>=1.26.4 | |
| # to quote a-r-r-o-w/finetrainers: | |
| # It is recommended to use Pytorch 2.5.1 or above for training. Previous versions can lead to completely black videos, OOM errors, or other issues and are not tested. | |
| # on some system (Python 3.13+) those do not work: | |
| torch==2.5.1 | |
| torchvision==0.20.1 | |
| torchao==0.6.1 | |
| huggingface_hub | |
| hf_transfer>=0.1.8 | |
| diffusers @ git+https://github.com/huggingface/diffusers.git@main | |
| transformers>=4.45.2 | |
| accelerate | |
| bitsandbytes | |
| peft>=0.12.0 | |
| eva-decord==0.6.1 | |
| wandb | |
| pandas | |
| sentencepiece>=0.2.0 | |
| imageio-ffmpeg>=0.5.1 | |
| torchdata==0.11.0 | |
| flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl | |
| # for youtube video download | |
| pytube | |
| pytubefix | |
| # for scene splitting | |
| scenedetect[opencv] | |
| # for llava video / captionning | |
| pillow | |
| pillow-avif-plugin | |
| polars | |
| einops | |
| open_clip_torch | |
| av==14.1.0 | |
| git+https://github.com/LLaVA-VL/LLaVA-NeXT.git | |
| # for our frontend | |
| gradio==5.20.1 | |
| gradio_toggle | |
| # used for the monitor | |
| matplotlib |