Re:Imagen, a text-to-image diffusion model
by jowday on Monday May 23, 2022 @06:11PM
(#31485465)
Much like OpenAIs marketing speak about withholding their models for safety, this is just a progressive-sounding cover story for them not wanting to essentially give away a model they spent thousands of man hours and tens of millions of dollars worth of compute training.
[ Parent
| on HN ]
There are no comments on this comment yet.