LongCat_Avatar,an upgraded open-source framework for audio-driven human video generation.
Python
6
21 commits
updated Jun 2, 2026
LongCat_Avatar,an upgraded open-source framework for audio-driven human video generation.
In the ./ComfyUI/custom_nodes directory, run the following:
git clone https://github.com/smthemex/ComfyUI_LongCat_Avatar
pip install -r requirements.txt
huggingface links: dit-int8
huggingface links: text_encoders
huggingface links: vocal_separator/whisper-large-v3/lora
huggingface links: vae
├── ComfyUI/models/diffusion_models/
| ├── LongCat-Video-Avatar-1.5-int8.safetensors
├── ComfyUI/models/loras/
| ├── LongCat_Avatar_1.5_lora.safetensors
├── ComfyUI/models/vae/
| ├── LongCat_Avatar_1.5_vae.safetensors
├── ComfyUI/models/clip/
| ├── umt5_xxl_fp8_e4m3fn_scaled.safetensors
├── ComfyUI/models/audio_encoders/
| ├── whisper-large-v3.safetensors # rename or not
├── ComfyUI/models/longcat/
| ├── Kim_Vocal_2.onnx # 配套config文件会自动下,可以下了先放进去
![]()
@misc{meituanlongcatteam2025longcatvideotechnicalreport,
title={LongCat-Video Technical Report},
author={Meituan LongCat Team and Xunliang Cai and Qilong Huang and Zhuoliang Kang and Hongyu Li and Shijun Liang and Liya Ma and Siyu Ren and Xiaoming Wei and Rixu Xie and Tong Zhang},
year={2025},
eprint={2510.22200},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2510.22200},
}
@misc{meituanlongcatteam2025longcatvideoavatar15technicalreport,
title={LongCat-Video-Avatar 1.5 Technical Report},
author={Meituan LongCat Team},
year={2026},
eprint={},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={},
}
@misc{meituanlongcatteam2025longcatvideoavatartechnicalreport,
title={LongCat-Video-Avatar Technical Report},
author={Meituan LongCat Team},
year={2025},
eprint={},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={},
}
21 commits
Python
100.0%
LongCat_Avatar,an upgraded open-source framework for audio-driven human video generation.
Python
6
21 commits
updated Jun 2, 2026
LongCat_Avatar,an upgraded open-source framework for audio-driven human video generation.
In the ./ComfyUI/custom_nodes directory, run the following:
git clone https://github.com/smthemex/ComfyUI_LongCat_Avatar
pip install -r requirements.txt
huggingface links: dit-int8
huggingface links: text_encoders
huggingface links: vocal_separator/whisper-large-v3/lora
huggingface links: vae
├── ComfyUI/models/diffusion_models/
| ├── LongCat-Video-Avatar-1.5-int8.safetensors
├── ComfyUI/models/loras/
| ├── LongCat_Avatar_1.5_lora.safetensors
├── ComfyUI/models/vae/
| ├── LongCat_Avatar_1.5_vae.safetensors
├── ComfyUI/models/clip/
| ├── umt5_xxl_fp8_e4m3fn_scaled.safetensors
├── ComfyUI/models/audio_encoders/
| ├── whisper-large-v3.safetensors # rename or not
├── ComfyUI/models/longcat/
| ├── Kim_Vocal_2.onnx # 配套config文件会自动下,可以下了先放进去
![]()
@misc{meituanlongcatteam2025longcatvideotechnicalreport,
title={LongCat-Video Technical Report},
author={Meituan LongCat Team and Xunliang Cai and Qilong Huang and Zhuoliang Kang and Hongyu Li and Shijun Liang and Liya Ma and Siyu Ren and Xiaoming Wei and Rixu Xie and Tong Zhang},
year={2025},
eprint={2510.22200},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2510.22200},
}
@misc{meituanlongcatteam2025longcatvideoavatar15technicalreport,
title={LongCat-Video-Avatar 1.5 Technical Report},
author={Meituan LongCat Team},
year={2026},
eprint={},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={},
}
@misc{meituanlongcatteam2025longcatvideoavatartechnicalreport,
title={LongCat-Video-Avatar Technical Report},
author={Meituan LongCat Team},
year={2025},
eprint={},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={},
}
21 commits
Python
100.0%