Riffusion
id:
riffusion-302-18256039
title:
Riffusion
text:
Riffusion is a neural network, designed by Seth Forsgren and Hayk Martiros, that generates music using images of sound rather than audio. It was created as a fine-tuning of Stable Diffusion, an existing open-source model for generating images from text prompts, on spectrograms. This results in a model which uses text prompts to generate image files, which can be put through an inverse Fourier transform and converted into audio files. While these files are only several seconds long, the model can
brand slug:
wiki
category slug:
encyclopedia
description:
Music-generating machine learning model
original url:
https://en.wikipedia.org/wiki/Riffusion
date created:
date modified:
2023-11-29T11:16:38Z
main entity:
{"identifier":"Q115939172","url":"https://www.wikidata.org/entity/Q115939172"}
image:
{"content_url":"https://upload.wikimedia.org/wikipedia/commons/a/a1/AI-generated_audio_featuring_bossa_nova_music_with_electric_guitar.png","width":1536,"height":512}
fields total:
13
integrity:
15