|
|
|
|
|
|
by sangwulee
316 days ago
|
|
|
Hello HackerNews. My name is Sangwu Lee . I work for Krea and I led the research efforts around the post-training for this model. I'll try to answer any questions you may have, but I recommend you read the technical report I wrote on our site (https://www.krea.ai/blog/flux-krea-open-source-release). I also see that my colleagues already commented here, but I'll try to answer questions you may have. |
|
|
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.