Riffusion is an app for real-time music generation with stable diffusion. It is based on audio diffusion↗︎. With diffusion models, it is possible to condition their creations not only on a text prompt but also on other images. It uses the v1.5 stable diffusion model with no modifications, just fine-tuned on images of spectrograms paired with text. It can generate infinite variations of a prompt by varying the seed. All the same web UIs and techniques like img2img, inpainting, negative prompts, and interpolation work out of the box.
riffusion
Free Service
Song
Music
Diffusion
Sound
Create music from with a text prompt
Model details
AuthorSeth Forsgren and Hayk Martiros
Published in2022
Architecturediffusion
Licensemit
Related models:
Didn't find what you are looking for? Send us your suggestions!