LongCat-Video-Avatar About

Model Introduction

We introduce LongCat-Video-Avatar, a unified model that delivers expressive and highly dynamic audio-driven character animation, supporting native tasks including Audio-Text-to-Video, Audio-Text-Image-to-Video, and Video Continuation with seamless compatibility for both single-stream and multi-stream audio inputs.

Key Features

• Unified architecture for multiple tasks: LongCat-Video-Avatar unifies Audio-Text-to-Video, Audio-Text-Image-to-Video, and Video-Continuation tasks within a single video generation framework. It natively supports all these tasks with a single model and consistently delivers strong performance across each individual task.
• Audio-driven character animation: LongCat-Video-Avatar is specifically designed for expressive and highly dynamic audio-driven character animation, enabling natural lip synchronization and character movements that match audio inputs.
• Single and multi-stream audio support: The model seamlessly supports both single-stream and multi-stream audio inputs, allowing for flexible character animation scenarios including dialogue between multiple characters.
• Long video generation: LongCat-Video-Avatar inherits the long video generation capabilities from LongCat-Video, enabling it to produce minutes-long videos without color drifting or quality degradation.
• Efficient inference: LongCat-Video-Avatar generates high-quality videos within minutes by employing a coarse-to-fine generation strategy along both the temporal and spatial axes.

Quick Start

Installation

Clone the repo:

git clone --single-branch --branch main https://github.com/meituan-longcat/LongCat-Video
cd LongCat-Video

Install dependencies:

# create conda environment
conda create -n longcat-video python=3.10
conda activate longcat-video

# install torch (configure according to your CUDA version)
pip install torch==2.6.0+cu124 torchvision==0.21.0+cu124 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu124

# install flash-attn-2
pip install ninja 
pip install psutil 
pip install packaging 
pip install flash_attn==2.7.4.post1

# install other requirements
pip install -r requirements.txt

# install longcat-video-avatar requirements
conda install -c conda-forge librosa
conda install -c conda-forge ffmpeg
pip install -r requirements_avatar.txt

FlashAttention-2 is enabled in the model config by default; you can also change the model config ("./weights/LongCat-Video-Avatar/dit/config.json") to use FlashAttention-3 or xformers once installed.

Model Download

Download models using huggingface-cli:

pip install "huggingface_hub[cli]"
huggingface-cli download meituan-longcat/LongCat-Video-Avatar --local-dir ./weights/LongCat-Video-Avatar

Run LongCat-Video-Avatar

Single-Audio-to-Video Generation

# Audio-Text-to-Video
torchrun --nproc_per_node=2 run_demo_avatar_single_audio_to_video.py --context_parallel_size=2 --checkpoint_dir=./weights/LongCat-Video-Avatar --stage_1=at2v --input_json=assets/avatar/single_example_1.json

# Audio-Image-to-Video
torchrun --nproc_per_node=2 run_demo_avatar_single_audio_to_video.py --context_parallel_size=2 --checkpoint_dir=./weights/LongCat-Video-Avatar --stage_1=ai2v --input_json=assets/avatar/single_example_1.json

# Audio-Text-to-Video and Video-Continuation
torchrun --nproc_per_node=2 run_demo_avatar_single_audio_to_video.py --context_parallel_size=2 --checkpoint_dir=./weights/LongCat-Video-Avatar --stage_1=at2v --input_json=assets/avatar/single_example_1.json --num_segments=5 --ref_img_index=10 --mask_frame_range=3

# Audio-Image-to-Video and Video-Continuation
torchrun --nproc_per_node=2 run_demo_avatar_single_audio_to_video.py --context_parallel_size=2 --checkpoint_dir=./weights/LongCat-Video-Avatar --stage_1=ai2v --input_json=assets/avatar/single_example_1.json --num_segments=5 --ref_img_index=10 --mask_frame_range=3

Multi-Audio-to-Video Generation

# Audio-Image-to-Video
torchrun --nproc_per_node=2 run_demo_avatar_multi_audio_to_video.py --context_parallel_size=2 --checkpoint_dir=./weights/LongCat-Video-Avatar --input_json=assets/avatar/multi_example_1.json

# Audio-Image-to-Video and Video-Continuation
torchrun --nproc_per_node=2 run_demo_avatar_multi_audio_to_video.py --context_parallel_size=2 --checkpoint_dir=./weights/LongCat-Video-Avatar --input_json=assets/avatar/multi_example_1.json --num_segments=5 --ref_img_index=10 --mask_frame_range=3

Run Streamlit

# Single-GPU inference
streamlit run ./run_streamlit.py --server.fileWatcherType none --server.headless=false

License Agreement

The model weights are released under the MIT License.

Any contributions to this repository are licensed under the MIT License, unless otherwise stated. This license does not grant any rights to use Meituan trademarks or patents.

Usage Considerations

This model has not been specifically designed or comprehensively evaluated for every possible downstream application.

Developers should take into account the known limitations of large language models, including performance variations across different languages, and carefully assess accuracy, safety, and fairness before deploying the model in sensitive or high-risk scenarios.

It is the responsibility of developers and downstream users to understand and comply with all applicable laws and regulations relevant to their use case, including but not limited to data protection, privacy, and content safety requirements.

Nothing in this Model Card should be interpreted as altering or restricting the terms of the MIT License under which the model is released.

Citation

We kindly encourage citation of our work if you find it useful.

@misc{meituanlongcatteam2025longcatvideoavatartechnicalreport,
      title={LongCat-Video-Avatar Technical Report}, 
      author={Meituan LongCat Team},
      year={2025},
      eprint={},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={}, 
}

Acknowledgements

We would like to thank the contributors to the Wan, UMT5-XXL, Diffusers and HuggingFace repositories, for their open research.