Dance Diffusion is a family of audio-generating machine learning models created by Harmonai, an open source community building generative audio tools for producers and musicians. Harmonai is funded by Stability AI, the startup behind the popular Stable Diffusion text-to-image model.
Like Stable Diffusion, Dance Diffusion appeals to a broad, more layperson audience. Many machine learning models are only known and used by machine learning engineers, but Dance Diffusion speaks to music creators, many of whom likely have little to no experience with machine learning.
I wrote this content for exactly this audience: people who do not have a machine learning background, but have heard of this new “Dance Diffusion” thing and would like to know a little bit more.
- Ranks #2 (with some fluctuation) on Google for the search term “dance diffusion”
- Top five top-of-funnel content pieces at Weights & Biases during the second half of 2022