Re:Meta releases New SOTA Text to Music generator better tha...
by visarga on Saturday June 10, 2023 @03:37PM
(#36274229)
> remind me of the average, mediocre, soul-lacking content
This model is just the equivalent of GPT-2 for music. It's not the GPT-4 yet. Music is trailing a few years from language. Used to be that language was about 5 years behind vision. Now language is the top.
This model is just the equivalent of GPT-2 for music. It's not the GPT-4 yet. Music is trailing a few years from language. Used to be that language was about 5 years behind vision. Now language is the top.