SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads

Tan Yu*, Qian Qiao*^✉, Le Shen*, Ke Zhou, Jincheng Hu, Dian Sheng, Bo Hu, Haoming Qin, Jun Gao, Changhai Zhou, Shunshun Yin, Siyuan Liu ^✉

^*Equal Contribution ^✉Corresponding Author

 

⚡ Highlights

• Model_Lite Released get 96 FPS, or 3-concurrent real-time(25+ FPS) streaming on single RTX4090.
• Model_Pro Released can generate high-quality videos with 10.8 FPS on single RTX4090, or real-time(25+ FPS) on two RTX5090.
• Model_Pretrained is coming soon, providing high-performance weights and experimental foundations for community research.

🔥 News

• 2026.02.12 - The online demo is now available via the Soul App. Download it today to try it out. Download it today to try it out.
• 2026.02.12 - We have released the inference code, and the model weights.
• 2026.02.12 - We released Project page on SoulX-FlashHead.
• 2026.02.07 - We released Dataset.
• 2026.02.07 - We released SoulX-FlashHead Technical Report on Arxiv and GitHub repository.

📑 Todo List

• Technical report
• Project Page
• Inference code
• Distilled Checkpoint of Pro-Model & Lite-Model release
• Pretrained Checkpoint release

🌰 Examples

📖 Quickstart

🔧 Installation

1. Create a Conda environment

2. Install PyTorch on CUDA

3. Install other dependencies

4. FlashAttention installation:

1. download wheel file from here
2. pip install xxx.whl

5. SageAttention installation (Optional)

5. FFmpeg installation

🤗 Model download

🚀 Inference

👋 Online Experience

Real-time Online Experience (SoulApp 实时在线体验)

📧 Contact Us

Join WeChat Group (加入微信技术群)

Download SoulApp & Join Group (下载SoulApp加入群组)

📚 Citation

@misc{yu2026soulxflashheadoracleguidedgenerationinfinite,
      title={SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads}, 
      author={Tan Yu and Qian Qiao and Le Shen and Ke Zhou and Jincheng Hu and Dian Sheng and Bo Hu and Haoming Qin and Jun Gao and Changhai Zhou and Shunshun Yin and Siyuan Liu},
      year={2026},
      eprint={2602.07449},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2602.07449}, 
}

🙇 Acknowledgement

• Wan: the base model we built upon.
• LTX-Video: the VAE of our Lite-Model.
• Self forcing: the codebase we built upon.
• DMD and Self forcing++: the key distillation technique used by our method.
• SoulX-FlashTalk is another model developed by our team, featuring 14B parameters and real-time capabilities.

[!TIP] If you find our work useful, please also consider starring the original repositories of these foundational methods.

💡 Star History