Re:Stability AI releases DeepFloyd IF, a powerful text-to-im...
by lucidrains on Friday April 28, 2023 @01:17PM
(#35744266)
tldr: bigger text encoder is better. SD will catch up quickly, as conditioning on a new set of precomputed text embeddings is a trivial change
[ Parent
| on HN ]
Re:Stability AI releases DeepFloyd IF, a powerful text-to-im...
by mkaic on Friday April 28, 2023 @01:23PM
(#35744341)
I didn't think about that but you're totally right, assuming they have those embeddings cached it would be super easy to retrain SD using them. 11B parameter count is rather unfortunate though tbh, I've never been the biggest fan of "scale is all you need" even though it seems to ring irritatingly true most of the time.