MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

Mingyuan Zhang¹*  Zhongang Cai^1,2*  Liang Pan¹  Fangzhou Hong¹  Xinying Guo¹  Lei Yang²  Ziwei Liu¹⁺

¹S-Lab, Nanyang Technological University  ²SenseTime Research 

*equal contribution  ⁺corresponding author

play the guitar	walk sadly	walk happily	check time

This repository contains the official implementation of MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model.

---

[Project Page] • [arXiv] • [Video] • [Colab Demo] • [Hugging Face Demo]

Updates

[10/2022] Add a 🤗Hugging Face Demo for text-driven motion generation!

[10/2022] Add a Colab Demo for text-driven motion generation!

[10/2022] Code release for text-driven motion generation!

[8/2022] Paper uploaded to arXiv.

Text-driven Motion Generation

You may refer to this file for detailed introduction.

Citation

If you find our work useful for your research, please consider citing the paper:

@article{zhang2022motiondiffuse,
  title={MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model},
  author={Zhang, Mingyuan and Cai, Zhongang and Pan, Liang and Hong, Fangzhou and Guo, Xinying and Yang, Lei and Liu, Ziwei},
  journal={arXiv preprint arXiv:2208.15001},
  year={2022}
}

Acknowledgements

This study is supported by NTU NAP, MOE AcRF Tier 2 (T2EP20221-0033), and under the RIE2020 Industry Alignment Fund – Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contribution from the industry partner(s).