VideoModelStudio / requirements_without_flash_attention.txt
jbilcke-hf's picture
jbilcke-hf HF staff
initial commit log 🪵🦫
91fb4ef
raw
history blame
738 Bytes
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.
torch==2.5.1
torchvision==0.20.1
torchao==0.6.1
huggingface_hub
hf_transfer>=0.1.8
diffusers>=0.30.3
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
# 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==5.15.0
gradio_toggle