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.

all 6 comments

sorted by: hot top controversial new old
[–] 4 points 1 year ago (2 children)

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.

  • source
  • hideshow 2 child comments
  • it is currently a open developer hybrid of flux schnell

  • source
  • [–] 1 point 1 year ago (1 child)

    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.

  • source
  • hideshow 1 child comment