Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion
by emperorcj on Friday September 15, 2023 @03:13AM
(#37519598)
dadabots here: haven't gotten good death metal with it. problem is there's not really much in the dataset.
[ Parent
| on HN ]
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