Long-form music generation with latent diffusion

Zach Evans, Julian Parker, CJ Carr, Zack Zukowski, Josiah Taylor, Jordi Pons

Long-form music generation with latent diffusion: 27 upvotes on Hugging Face Daily Papers, #2 of 2 papers on 2024-04-17. Day-by-day upvote history.

Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure. We show that by training a generative model on long temporal contexts it is possible to produce long-form music of up to 4m45s. Our model consists of a diffusion-transformer operating on a highly downsampled continuous latent representation (latent rate of 21.5Hz). It obtains state-of-the-art generations according to metrics on audio quality and prompt alignment, and subjective tests reveal that it produces full-length music with coherent structure.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.