Quark-Vision/Live-Avatar

🎬 Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Yubo Huang^1,2 · Hailong Guo^1,3 · Fangtai Wu^1,4 · Shifeng Zhang¹ · Shijie Huang¹ · Qijun Gan⁴ · Lin Liu² · Sirui Zhao^2,* · Enhong Chen^2,* · Jiaming Liu^1,‡ · Steven Hoi¹

¹ Alibaba Group    ² University of Science and Technology of China    ³ Beijing University of Posts and Telecommunications    ⁴ Zhejiang University

^* Corresponding authors.    ^‡ Project leader.

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.

👀 More Demos:
:robot: Human-AI Conversation  |  ♾️ Infinite Video  |  🎭 Diverse Characters  |  🎬 Animated Tech Explanation
👉 Click Here to Visit Project Page! 🌐

---

✨ Highlights

• ⚡ ​​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

---

📰 News

• [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.

---

📑 Todo List

🌟 Early December (core code release)

• ✅ 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

⚙️ Later updates

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

🛠️ Installation

Please follow the steps below to set up the environment.

1. Create Environment

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

2. Install CUDA Dependencies (optional)

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

3. Install PyTorch & Flash Attention

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

4. Install Python Requirements

pip install -r requirements.txt

5. Install FFMPEG

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

---

📥 Download Models

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

Model Component	Description	Link
WanS2V-14B	base model	🤗 Huggingface
liveAvatar	our lora model	🤗 Huggingface

# 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
    └── ...

🚀 Inference

Real-time Inference with TPP

💡 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.

📝 Citation

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}, 
}

⭐ Star History

📜 License Agreement

• 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. ([email protected])

🙏 Acknowledgements

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

• CausVid
• Longlive
• WanS2V