DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion

Ziqian Ning, Huakang Chen, Yuepeng Jiang, Chunbo Hao, Guobin Ma, Shuai Wang, Jixun Yao, Lei Xie†

Huggingface Space  
📑 Paper    |    📑 Demo   

DiffRhythm (Chinese: 谛韵, Dì Yùn) is the first diffusion-based song generation model that is capable of creating full-length songs. The name combines "Diff" (referencing its diffusion architecture) with "Rhythm" (highlighting its focus on music and song creation). The Chinese name 谛韵 (Dì Yùn) phonetically mirrors "DiffRhythm", where "谛" (attentive listening) symbolizes auditory perception, and "韵" (melodic charm) represents musicality.

News and Updates

2025.3.4 🔥 We released the DiffRhythm paper and Huggingface Space demo.

TODOs

• Support local deployment:
• Support Colab:
• Support Docker:
• Release paper to Arxiv.
• Online serving on huggingface space.

Model Versions

License & Disclaimer

DiffRhythm (code and DiT weights) is released under the Apache License 2.0. This open-source license allows you to freely use, modify, and distribute the model, as long as you include the appropriate copyright notice and disclaimer.

We do not make any profit from this model. Our goal is to provide a high-quality base model for music generation, fostering innovation in AI music and contributing to the advancement of human creativity. We hope that DiffRhythm will serve as a foundation for further research and development in the field of AI-generated music.

DiffRhythm enables the creation of original music across diverse genres, supporting applications in artistic creation, education, and entertainment. While designed for positive use cases, potential risks include unintentional copyright infringement through stylistic similarities, inappropriate blending of cultural musical elements, and misuse for generating harmful content. To ensure responsible deployment, users must implement verification mechanisms to confirm musical originality, disclose AI involvement in generated works, and obtain permissions when adapting protected styles.

Citation

@article{ning2025diffrhythm,
  title={{DiffRhythm}: Blazingly Fast and Embarrassingly Simple</br>End-to-End Full-Length Song Generation with Latent Diffusion<},
  author={Ziqian, Ning and Huakang, Chen and Yuepeng, Jiang and Chunbo, Hao and Guobin, Ma and Shuai, Wang and Jixun, Yao and Lei, Xie},
  journal={arXiv preprint arXiv:2503.01183},
  year={2025}
}

Contact Us

If you are interested in leaving a message to our research team, feel free to email nzqiann@gmail.com.