well the thing is we use something rarely exists so that it can overrwite data
well the thing is we use something rarely exists so that it can overrwite data
Fbut t5 thing is new in the workflow opposed to sdxl
Fbecause we save as float
Fsave as fp16
Falso we save rank 128 :d
DI know but now with T5 in the equation that is frozen, how reacts to tokens that are not present on it?
Dthat's the question???
Dreally don't know
Dthere is a way to know if a token is on T5 or not?
Feverything get tokenized
Fso it exists
Fbut it is single token or not unknown
Fi asked this to swarmui dev and he said we dont have t5 tokenizer :d
Flike clip
Ftime to work hard :/
F
Gis it c:/kohya_ai/kohya_ss correct? batch files in main c:/kohya_ai correct?
Gis it c:/kohya_ai/kohya_ss correct? batch files in main c:/kohya_ai correct? and then run the files creating the /kohya_ss folder right? I have this issue too, on 2 machines
Fthis is accurate name should work
GOk will try rn its Windows 10 PRO too not 11
Gok will update shortly
Fsure let us know
HGood evening everyone! @Dr. Furkan Gözükara, will there be a Flux training video for RunPod?
Fediting right now
F
HThank you, Dr.!
FTraining a FLUX LoRA for a client. 24 images. on 4x RTX A6000 GPU. Total 240 epochs. Effective batch size 4 and step count is 1440
Fi also found a new info regarding multi gpu training will update configs
Fi am moving to the city tomorrow hopefully. time to get 1 gbit internet 
Ftime to start 8 more test on flux lora LR
Ftesting more trainings of text encoder - clip L
GHow long did it take? Size1024x1024? I have the A6000. And what is that EFFECTIVE BATCH SIZE 4 Setting at?
Fit is almost linear increase
Fwith slow work flow
F9.41 second it
Gimage res size? and the batch setting?
Gi did torch 2.5 update
Fso lets say 3000 steps takes 9.41 * 3000 / 4 / 60 = 117 minutes
Fit is 1024x1024
Gand i had to add the dll in system32 to fix my fbgemm.dll errors
Fye it is a solution
Fif you go with fast settings it takes 60 minutes for 3000 steps
Fsteps count becoming 750 since 4x gpu
Fand effective batch size being 4
Gwhere do you set steps? that is controlled only by the amount of Images you have right?
GI only have 1 GPU though
Ffor 1 gpu you dont need to change anything
Fthis is for multi gpus
Fexplained in tutorial editing it