Long-form music generation with latent diffusion
This addresses the challenge for musicians and content creators who need AI-generated music with long-term coherence, representing a significant advance over prior methods.
The paper tackled the problem of generating full-length music tracks with coherent structure from text prompts, achieving state-of-the-art results with music up to 4 minutes and 45 seconds long.
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 from text prompts. 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.