DiffRhythm
A local AI music generator that creates full-length songs with diffusion, supports Windows, Linux and Docker, and has Apache 2.0 licensing.
DiffRhythm is an AI music generation model for musicians and developers who want to create full-length songs on their own hardware. It uses diffusion to generate songs from lyric and reference-audio inputs.
- Full-length songs supports generation up to 4 minutes and 45 seconds with the full model, alongside a shorter base model.
- Lyrics and reference audio accepts lyrics in LRC format and an audio reference to guide generation.
- Length and continuation lets you control song length and extend existing songs.
- Vocals only supports vocal generation without accompaniment.
Local deployment supports Linux and Windows, and the project also supports Docker. A separate hosted Hugging Face Space demo lets you try generation online.
The repository uses the Apache License 2.0.
Logotyper
