This isn't the first time OpenAI has worked on generative music models. The company has experimented in this direction even ...
(1) We released the 50 diffusion steps model (instead of 1000 steps) which runs 20X faster with comparable results. (2) Calling CLIP just once and caching the result runs 2X faster for all models.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback