mirror of
https://github.com/zenlm/mu.git
synced 2026-07-26 22:08:54 +00:00
Mu
Full-length song generation with latent diffusion. Part of the Zen LM ecosystem.
Overview
Mu generates full-length songs (up to 4m45s) using latent diffusion with a Diffusion Transformer backbone. It supports text-conditioned music generation with optional lyrics alignment.
Features
- Full-length song generation (up to 4:45)
- Lyrics-conditioned generation
- Diffusion Transformer architecture
- Audio codec for high-quality reconstruction
Related
- zen-musician — Music generation models
- zen-foley — Sound effect generation
- Zen LM — Full model family
License
Apache 2.0