I've noticed that all of these music generators suffer from something like "mean" collapse (as opposed to mode, you do get variance, but all results are highly centered around similar sounding songs).

The music is all just very average, it sounds like the most average song with the most average chord progression/drum pattern per genre.

I guess that makes sense if these are most likely next audio token predictors... but it'd be cool if there was a way to inject some type of creativity/novelty into these, or at least tune up the temperature.

Everything so far just sounds like stock library music to me.

Isn’t that what the billboard charts are effectively?