TL;DR: Live Avatar is an algorithm–system co-designed framework that enables real-time, streaming, infinite-length interactive avatar video generation. Powered by a 14B-parameter diffusion model, it achieves 20 FPS on 5×H800 GPUs with 4-step sampling and supports Block-wise Autoregressive processing for 10,000+ second streaming videos.

• ⚡ ​​Real-time Streaming Interaction​​ - Achieve 20 FPS real-time streaming with low latency
• ♾️ ​​​​Infinite-length Autoregressive Generation​​​​ - Support 10,000+ second continuous video generation
• 🎨 ​​​​Generalization Performances​​​​ - Strong generalization across cartoon characters, singing, and diverse scenarios

• [2025.12.12] 🚀 We released single-gpu inference Code — no need for 5×H100 (house-priced server), a single 80GB VRAM GPU is enough to enjoy.
• [2025.12.08] 🚀 We released real-time inference Code and the model Weight.
• [2025.12.08] 🎉 LiveAvatar won the Hugging Face #1 Paper of the day!
• [2025.12.04] 🏃‍♂️ We committed to open-sourcing the code in early December.
• [2025.12.04] 🔥 We released Paper and demo page Website.

• ✅ Release the paper
• ✅ Release the demo website
• ✅ Release checkpoints on Hugging Face
• ✅ Release Gradio Web UI
• ✅ Experimental real-time streaming inference on at least H800 GPUs
  • ✅ Distribution-matching distillation to 4 steps
  • ✅ Timestep-forcing pipeline parallelism

• ✅ Inference code supporting single GPU (offline generation)
• ⬜ Multi-character support
• ⬜ UI integration for easily streaming interaction
• ⬜ TTS integration
• ⬜ Training code
• ⬜ LiveAvatar v1.1

Please follow the steps below to set up the environment.

conda create -n liveavatar python=3.10 -y
conda activate liveavatar

conda install nvidia/label/cuda-12.4.1::cuda -y
conda install -c nvidia/label/cuda-12.4.1 cudatoolkit -y

pip install torch==2.8.0 torchvision==0.23.0 --index-url https://download.pytorch.org/whl/cu128
pip install flash-attn==2.8.3 --no-build-isolation

pip install -r requirements.txt

apt-get update && apt-get install -y ffmpeg                 

Please download the pretrained checkpoints from links below and place them in the ./ckpt/ directory.

# If you are in china mainland, run this first: export HF_ENDPOINT=https://hf-mirror.com
pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.2-S2V-14B --local-dir ./ckpt/Wan2.2-S2V-14B
huggingface-cli download Quark-Vision/Live-Avatar --local-dir ./ckpt/LiveAvatar

After downloading, your directory structure should look like this:

ckpt/
├── Wan2.2-S2V-14B/          # Base model
│   ├── config.json
│   ├── diffusion_pytorch_model-*.safetensors
│   └── ...
└── LiveAvatar/              # Our LoRA model
    ├── liveavatar.safetensors
    └── ...

💡 Currently, This command can run on GPUs with at least 80GB VRAM.

# CLI Inference
bash infinite_inference_multi_gpu.sh
# Gradio Web UI
bash gradio_multi_gpu.sh

💡 The model can generate videos from audio input combined with reference image and optional text prompt.

💡 The size parameter represents the area of the generated video, with the aspect ratio following that of the original input image.

💡 The --num_clip parameter controls the number of video clips generated, useful for quick preview with shorter generation time.

💡 Currently, our TPP pipeline requires five GPUs for inference. We are planning to develop a 3-step version that can be deployed on a 4-GPU cluster. Furthermore, we are planning to integrate the LightX2V VAE component. This integration will eliminate the dependency on additional single-GPU VAE parallelism and support 4-step inference within a 4-GPU setup.

Please visit our project page to see more examples and learn about the scenarios suitable for this model.

💡 This command can run on a single GPU with at least 80GB VRAM.

# CLI Inference
bash infinite_inference_single_gpu.sh
# Gradio Web UI
bash gradio_single_gpu.sh

💡 If you encounter OOM errors after multiple runs in the Gradio Web UI, please try lowering the resolution (the size parameter) as a temporary fix. We are actively developing enhanced single GPU memory optimization; track our progress in the "Later updates" section.

💡 To avoid performance degradation caused by frequent CPU offloading, we set the enable_online_decode parameter to false by default in the single-GPU scripts. This may slightly reduce quality when generating extremely long videos; in such cases, consider adding --enable_online_decode to your inference command.

If you find this project useful for your research, please consider citing our paper:

@misc{huang2025liveavatarstreamingrealtime,
      title={Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length}, 
      author={Yubo Huang and Hailong Guo and Fangtai Wu and Shifeng Zhang and Shijie Huang and Qijun Gan and Lin Liu and Sirui Zhao and Enhong Chen and Jiaming Liu and Steven Hoi},
      year={2025},
      eprint={2512.04677},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.04677}, 
}

• The majority of this project is released under the Apache 2.0 license as found in the LICENSE.
• The Wan model (Our base model) is also released under the Apache 2.0 license as found in the LICENSE.
• The project is a research preview. Please contact us if you find any potential violations. (jmliu1217@gmail.com)

We would like to express our gratitude to the following projects:

• CausVid
• Longlive
• WanS2V