[jasbur]

It's interesting that the Death Metal was the hardest to reproduce. I conclude that it's the most fundamentally human of all genres.

[dontreact]

Well... they hardly tried all genres :)

It sounds like it can't handle lyrics or semantics that well so I suspect any genre where the lyricism is important would also be quite mushy and recognizably AI

[Jeff_Brown]

The Beatles seemed to be the hardest music for JukeBox to emulate.

[Ninovdmark]

The sound sample seemed to fit the 'vibe', but lacked any discernible definition. Could it be that it's too sonically dense to easily reproduce? Perhaps this could be improved with a more tailored training set.

[awestroke]

I think it was just the genre that was the least represented in the training data

[emperorcj]

dadabots here: haven't gotten good death metal with it. problem is there's not really much in the dataset.

[emperorcj]

(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

[chankstein38]

It sounds more like break core haha