Welcome • User Guide
ToS • Privacy • Canary
Donate • Bugs • License

©2025 Poal.co

653

This is just one such site, using the stable diffusion model at the core but using it to draw the spectrogram of prompted music, then using some basic musical constraints to keep a steady tempo, and inverse short-time fourier transforms to convert it to time-domain audio.

This is just one such site, using the stable diffusion model at the core but using it to draw the spectrogram of prompted music, then using some basic musical constraints to keep a steady tempo, and inverse short-time fourier transforms to convert it to time-domain audio.

(post is archived)

You are currently inside a comment thread.
Click here to see all the comments (5).
[–] • 0 pt

I tried "space blues" and was disappointed. It's a fusion, but sucks.

[–] • 0 pt

AI will never be able to write music that is interesting