Re:FLUX.1 Krea: post-trained text-to-image model from Black ...
by oompty on Thursday July 31, 2025 @04:23PM
(#44749722)
The model looks incredible!
Regarding this part:
> Since flux-dev-raw is a guidance distilled model, we devise a custom loss to finetune the model directly on a classifier-free guided distribution.
Could you go more into detail on the loss used for this and other possible tips for finetuning those? I remember the general open source ai art community had a hard time with finetuning the original distilled flux-dev so I'm very curious about that.
Regarding this part: > Since flux-dev-raw is a guidance distilled model, we devise a custom loss to finetune the model directly on a classifier-free guided distribution.
Could you go more into detail on the loss used for this and other possible tips for finetuning those? I remember the general open source ai art community had a hard time with finetuning the original distilled flux-dev so I'm very curious about that.