Fork of LongCat-Video for B200 GPU. Updates for Python, Torch, CUDA, Flash Attention 4, etc. https://spacecruft.org/movies/LongCat-Video-B200
  • Python 98.6%
  • Shell 1.4%
Find a file
2026-05-28 10:08:09 -06:00
assets Add CLI opts, hi quality to I2V 25fps demo script 2026-04-01 18:20:04 -06:00
longcat_video Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
.gitignore git ignores 2026-03-31 18:47:21 -06:00
.python-version Really use Python 3.12 2026-03-31 18:50:07 -06:00
B200.md rm some duplicate scripts 2026-05-26 17:18:08 -06:00
download_models.sh Update to LongCat-Video-Avatar 1.5 2026-05-26 15:41:10 -06:00
LICENSE MIT 2026-03-31 18:47:13 -06:00
README-upstream.md Add upstream README 2026-03-31 18:51:08 -06:00
README.md Note avatar refinement scripts 2026-04-01 13:27:22 -06:00
requirements-dev.txt Add python deps 2026-03-31 18:53:58 -06:00
requirements.txt Add python deps 2026-03-31 18:53:58 -06:00
requirements_avatar.txt Add python deps 2026-03-31 18:53:58 -06:00
run_demo_avatar_multi_audio_to_video_25fps.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_avatar_multi_audio_to_video_25fps.sh Update to LongCat-Video-Avatar 1.5 2026-05-26 15:41:10 -06:00
run_demo_avatar_multi_audio_to_video_25fps_refine.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_avatar_multi_audio_to_video_25fps_refine.sh Update to LongCat-Video-Avatar 1.5 2026-05-26 15:41:10 -06:00
run_demo_avatar_single_audio_to_video_25fps.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_avatar_single_audio_to_video_25fps.sh Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_avatar_single_audio_to_video_25fps_refine.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_avatar_single_audio_to_video_25fps_refine.sh Update to LongCat-Video-Avatar 1.5 2026-05-26 15:41:10 -06:00
run_demo_image_to_video.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_image_to_video.sh Add demo scripts 2026-03-31 18:54:51 -06:00
run_demo_image_to_video_16fps.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_image_to_video_16fps.sh Add 16 fps i2v scripts, kludge workaround 2026-05-13 09:38:50 -06:00
run_demo_image_to_video_25fps.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_image_to_video_25fps.sh Implement 25fps for non-avatar too 2026-04-01 18:06:11 -06:00
run_demo_interactive_video.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_interactive_video.sh Add demo scripts 2026-03-31 18:54:51 -06:00
run_demo_long_video.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_long_video.sh Add demo scripts 2026-03-31 18:54:51 -06:00
run_demo_text_to_video.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_text_to_video.sh Add demo scripts 2026-03-31 18:54:51 -06:00
run_demo_video_continuation.py Fix avatar multi-GPU whisper buglet, format 2026-05-28 10:08:09 -06:00
run_demo_video_continuation.sh Add demo scripts 2026-03-31 18:54:51 -06:00
run_streamlit.py Add python demo scripts 2026-03-31 18:54:23 -06:00
UPGRADE-1.5.md rm some duplicate scripts 2026-05-26 17:18:08 -06:00

LongCat-Video for B200

LongCat-Video generates videos.

Fork

The original upstream code does not run on the Nvidia B200 GPU. This fork updates and optimizes the code to run on the B200. Updates include:

  • Python 3.12.
  • Torch 2.11.
  • CUDA 13.
  • Flash Attention 4.
  • Add Shell script wrappers for demos.
  • Use 720p, not 480p, for demo scripts.
  • Add 25 FPS demo scripts.
  • Add 25 FPS demo scripts for avatars with refinements.
  • Model download script.
  • Bug fixes.
  • Cleanups.
  • Formatting.

Install

Quick and dirty install, flavor to taste:

mkdir -p ~/devel
cd ~/devel/
git clone https://spacecruft.org/movies/LongCat-Video-B200
cd LongCat-Video-B200/
export CUDA_HOME=/usr/local/cuda-13.2
export PATH=$CUDA_HOME/bin:$PATH
export LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH
export TORCH_CUDA_ARCH_LIST="10.0"
python -m venv venv
source venv/bin/activate
pip install -U setuptools pip wheel
pip install torch==2.11.0+cu130 torchvision torchaudio torchcodec --index-url https://download.pytorch.org/whl/cu130
mkdir -p ~/devel/Dao-AILab
cd ~/devel/Dao-AILab
git clone https://github.com/Dao-AILab/flash-attention.git
cd flash-attention/flash_attn/cute/
pip install psutil
pip install -e ".[cu13]"
cd ~/devel/LongCat-Video-B200/
pip install -r requirements.txt
pip install -r requirements_avatar.txt

Upstream

Originally by the fine folks at MeiGen-AI.

See README-upstream.md for the upstream README.

Upstream license MIT.

Copyright © 2025 Meituan.

This fork is unrelated to the upstream project.

License

MIT. See LICENSE.

Copyright © 2026 Jeff Moe.

Loveland, Colorado, USA