[question] Text-to-image gen's engine?

Hello everyone, could you tell me which image generator model was used in text-to-image in Perchance? It's different now, of course, but I'd like to know the model that was before the change, preferably if you have a link.

1 points · 6 comments · view on lemmy.world

6 Comments

GrumblePuss@lemmy.world · 4 pts · 1y (2 replies)

It's using Chroma which is a custom version of Flux.1-Schnell. I believe it's one of the recent snapshots of training data which somewhere around ~40 of 50.

MinoriMirariRProductions@lemmy.world · 1 pts · 364d (1 reply)

cbroma is bazed off of flux Schnell it is not flux schnell.

GrumblePuss@lemmy.world · 2 pts · 359d

That's what I said. What point are you getting at?

MinoriMirariRProductions@lemmy.world · 1 pts · 364d

it is currently a open developer hybrid of flux schnell

yamit@lemmy.world · 0 pts · 1y (1 reply)

Was Stable Diffusion 1.5, the checkpoints are unknown i guess? somewhere in this forum someone was saying that one of the checkpoints was deliberate, but they are just guesses.

qinerous@lemmy.world · 2 pts · 1y

thanks for answer