We’ve updated our Terms of Use to reflect our new entity name and address. You can review the changes here.
We’ve updated our Terms of Use. You can review the changes here.

Artificial Music I

by Cahn Ingold Prelog

/
  • Streaming + Download

    Includes high-quality download in MP3, FLAC and more. Paying supporters also get unlimited streaming via the free Bandcamp app.
    Purchasable with gift card

      name your price

     

1.
2.
3.
4.
5.
6.
7.
Gong bath 01:16
8.
9.
10.
11.
12.
Vaporwave 02:28
13.
14.
15.
16.
17.
18.
19.
20.

about

Text-to-image diffusion models are trained to understand key visual concepts with billions of tagged images. It's a similar (but much more rapid) process to how we learn visual concepts. We know what cats are, because we've seen lots of different cats and understand their common features. And if we want to draw a cat, we use our generic knowledge to create a recognisable picture of a cat, but one that is (very likely to be) slightly different from any other cat picture that we've ever seen.

If the diffusion model is trained specifically on spectrograms, however, rather than pictures of cats, fruit, people etc, then something really interesting happens. Spectrograms are visual representations of sound: plots of frequency vs time, so the machine comes to learn that certain keywords have certain spectrographic similarities. It knows what a generic smooth jazz piece 'looks like' in the same way that it knows what a generic dog looks like. You can then prompt the machine to produce new spectrograms in any style you can think of.

All you have to do then is convert these spectrograms into audio, which is possible thanks to some clever code written by other people, and you end up with some excitingly strange new music, produced by a machine that has absolutely no concept of sound, only about images.

Track titles reflect the prompt used to generate the track, many of which were generated randomly from long lists of genres, countries and adjectives.

credits

released April 6, 2023

Spectrograms by Stable Diffusion with the Riffusion 1.0 model.
Processed into audio with chavinlo's Riffusion Manipulation Tools.
Cover image by Stable Diffusion with the Analog Diffusion 1.0 model.

license

all rights reserved

tags

about

Simon Proffitt Wales, UK

Aware of what the record-buying public want, but neither able nor willing to give it to them.

2018–2024

contact / help

Contact Simon Proffitt

Streaming and
Download help

Shipping and returns

Redeem code

Report this album or account

If you like Artificial Music I, you may also like: