Riffusion

Uses Stable Diffusion models to generate music

About

Stable Diffusion is an open-source AI model that can generate images from text. Riffusion tweaked the model to make it able to create images called spectrograms, and then turn those into audio clips. Spectrograms are like pictures that show what different frequencies sound like at different times. They also made an interactive web app so anyone can type in a prompt to generate an audio clip, and then the app will make a smooth transition between different prompts or different seeds of the same prompt.

Categories

Penno Partner Deal

Get 1 month free with our partner Penno.

Code: AI-POWERED

Join Our Newsletter

Find it useful?

Subscribe to get weekly recommendations for your profession

Related Tools

Remove vocals and instruments from songs

A tool to enhance speech from audio.

Wzrd is an AI music visualizer tool built for creators and artists. It uses audio analysis and a vis..

A tool for creating and remixing musical stems

Generate high-fidelity music from text descriptions (Google Research)

Uses AI to take your text and turn it into a song

text-to-speech for fun music

AI Songwriting assistant

AI-based music composition platform

We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw ..

The AI tool is a web player for music and podcasts called Spotify. Users can sign up or log in to ac..