Hacker News Reader

Yeah, it’s basically stable diffusion but for music

I used "rollicking" in one description and it was exactly what it sounds like to your unconscious when you are far too drunk at a country bar

Not Stable Diffusion. MusicLM is a neural codec language model. Basically if GPT was predicting the next audio token while conditioned on text.

So like DALLE-1?

FWIW, the various diffusion models (tend to) use cross attention to an attention-based approach.