Tools to train a generative model on arbitrary audio samples

Run time and cost

Predictions run on Nvidia T4 GPU hardware. Predictions typically complete within 7 minutes. The predict time for this model varies significantly based on the inputs.

Dance Diffusion v0.10

Welcome to the Dance Diffusion beta!

Dance Diffusion is the first in a suite of generative audio tools for producers and musicians to be released by Harmonai. For more info or to get involved in the development of these tools, please visit https://harmonai.org and fill out the form on the front page.

Click here to ensure you are using the latest version

Audio diffusion tools in this notebook:

  • Unconditional random audio sample generation
  • Audio sample regeneration/style transfer using a single audio file
  • Audio interpolation between two audio files

Model ported to cog by Pollinations