https://arstechnica.com/information-technology/2022/12/riffusions-ai-generates-music-from-text-using-visual-sonograms/

On Thursday, a pair of tech hobbyists released Riffusion, an AI model that generates music from text prompts by creating a visual representation of sound and converting it to audio for playback. It uses a fine-tuned version of the Stable Diffusion 1.5 image synthesis model, applying visual latent diffusion to sound processing in a novel way.