Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Shuai Tan · Biao Gong^† · Xiang Wang · Shiwei Zhang
Dandan Zheng · Ruobing Zheng · Kecheng Zheng · Jingdong Chen · Ming Yang


Ant Group   |   Tongyi Lab

[🔥 We release our inference codes at https://github.com/antgroup/animate-x ]
This repository is the official implementation of paper "Animate-X: Universal Character Image Animation with Enhanced Motion Representation". Animate-X is a universal animation framework based on latent diffusion models for various character types (collectively named X), including anthropomorphic characters.

📌 Updates

• 2025 01.23 🎉 Our paper is accepted by ICLR 2025.
• 2024 12.18 🔥 This repository will no longer be maintained. For the latest version, please refer to https://github.com/antgroup/animate-x
• 2024 12.16 🔥 We release our inference codes at https://github.com/antgroup/animate-x
• 2024 11.25: Thank you for your patience. Although the code is ready, due to the company's latest open-source policy, this project can only be open-sourced on https://github.com/antgroup, with an expected release in the spring of 2025. We sincerely apologize for the delay. Open-sourcing is never easy, and we kindly ask for your understanding.
• 2024 10.21: Thank you all for your interest in Animate-X. The main reasons we haven't made the code public yet are: 1. The company needs to go through certain public approval processes, which take time. 2. We are currently cleaning up the code and preparing for open source in various aspects. We promise to release the code and the models by mid to late November. We appreciate your patience.
• 2024 10.1: The project page and Arxiv paper of Animate-X are released.

TODO List

• Release model, checkpoint and demo code.

Citation

If you find this codebase useful for your research, please use the following entry.

@article{AnimateX2025,
  title={Animate-X: Universal Character Image Animation with Enhanced Motion Representation},
  author={Tan, Shuai and Gong, Biao and Wang, Xiang and Zhang, Shiwei and Zheng, Dandan and Zheng, Ruobing and Zheng, Kecheng and Chen, Jingdong and Yang, Ming},
  journal={arXiv preprint arXiv:2410.10306},
  year={2025}
}

@article{Mimir2025,
  title={Mimir: Improving Video Diffusion Models for Precise Text Understanding},
  author={Tan, Shuai and Gong, Biao and Feng, Yutong and Zheng, Kecheng and Zheng, Dandan and Shi, Shuwei and Shen, Yujun and Chen, Jingdong and Yang, Ming},
  journal={arXiv preprint arXiv:2412.03085},
  year={2025}
}