News for hackers. Stuff that matters.
Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by emperorcj on Friday September 15, 2023 @05:58PM (#37529596)
(context: i make ai death metal & also i worked on stable audio). 100% it was a dataset problem. Diffusion models still work well when you train them on death metal: https://www.youtube.com/watch?v=rlsRMQzD_6Q

There are no comments on this comment yet.