yes but training not the entire model, just the human class
yes but training not the entire model, just the human class
Dthat will be cheaper
Cthat requires making a lora. that's what loras are for. and that can not be done
Che would have to train the base model and update the weights in it
Dyou can do a dreambooth
Cand IF he has a client, like a hollywood studio, that's willing to foot the bill and pay him a profit, he'll do it for them
Dand a new checkpoint
Cbut that'll be pro only, and probably an exclusive model
Cit won't be availble to anyone else.
Cno, you can't. dream booth doesn't allow you to train the entire base model. you are training a checkpoint but that isn't something you can do with flux. you have to train the entire base model.
Cthe neural network he decided to use is a bloody LLM! for crying out loud
Dok, I get your point
Dthanks
Chere's a silly prompt: a tired, weary man sitting in a lawn chair on the beach. A large crab looms behind him, its claws spread open in a threatening manner, and in the distance we see a whale spouting water into the air
DThanks man, I'm going to sleep I have to work tomorrow
Cnight
CFantastic thank you very much!
Dsaw an interesting comment. are different blocks responsible for face likeness and overall image look? or its just broscience?
CEach block does something specific
Fyes more memory better. i plan to upgrade 128gb
Ftrue but i am planning models to get more ready
Fstill too early i think
Cyou need vram, not system ram
Fok i see his method seems very weak
Fno i doubt that it will ever work 
Fi need both :d
Cnot really. you shouldn't be using that CPU for anything graphics related. and if you have an AMD, you should go through CS1o's AMD guides and make sure it's set up right.
Ceverything should be on your GPU and in vram
Fit is pretty much nonsense
Factually i was expecting training single block would reduce bleeding but it didnt
Fi guess due to transformer arcihecture even single layer changes alls output
Fit depends on how many apps you open at the same time
Cthere's a 12 step program for that
X@Dr. Furkan Gözükara have you tried flux 1.1?
Fit is only api
Fi did a quick test it was better for some mystical stuff like
Fa dinasaur
Fbacking up test data
Ftrainings started
F
DI'm not comfortable with you spending 8 GPUs on my 5 lines of code from thing morning 
Dbut it's up to you
Fye it is fine
Fif works it will be big
Mare you using your 5200 reg images?
Mi dont think dx is using any reg images
Fyep
Fi am testing both cases
Dhttps://huggingface.co/nyanko7/flux-dev-de-distill I'm testing this model on forge and I'm having interesting results, distilled cfg does nothing, is completely disabled
Dregular Flux-dev random prompt
