M5000x series should be a good upgrade for you
Mbut sadly only 28gb vram
Mshould of at least given 32gb vram
Mone trainer results are quite amazing so far, sadly the loras dont work in forge or comfy yet
M@Dr. Furkan Gözükara also all your configs have a bug in them
Fnah i am gonna buy what people cna buy :d
Fwhich one onetrainer?
Mit finally got fixed today, it was actually passing through conv dim and alpha
Mfor flux
M" from bmalsais" this is what he told me
"Well, the GUI was processing some of the values... but it should not have been. So I just took them out of the flus network list of possible parameters. This ensure only the ones officially supported by sd-scripts are used."
"Well, the GUI was processing some of the values... but it should not have been. So I just took them out of the flus network list of possible parameters. This ensure only the ones officially supported by sd-scripts are used."
Mplease check your jsons, they all had conv dim and alpha in them
"constrain": 0,
"conv_alpha": 1,
"conv_block_alphas": "",
"conv_block_dims": "",
"conv_dim": 1,
"constrain": 0,
"conv_alpha": 1,
"conv_block_alphas": "",
"conv_block_dims": "",
"conv_dim": 1,
Meven though it was training from the toml it creates, there was a bug pushing conv alphas and dims, and other unsupoorted params to flux
Fit uses toml there is no other way to push them
Fit was using default of kohya ss when not pushed
Mi confirmed it with kohya and bmaltis, it still passes through json params
Mwell its fixed now
Fi am gonna train again now with latest version
Flets see if any difference there will be
Mwait
Mdont load in your config
Mcreate a new one manually
Fok
Mlet me know if you get better results, i have been getting better, after running loads of tests
Fi will compare with grid lets see :d
Fanything else to test?
Fi got 8 gpus waiting :d
Fi tested text encoder and i got down to 2 text encoder params
Mi am able to stylize my trainings now
Mhave you tested prior loss weight for reg images? also just training it as person instead of man or woman?
Mhave you also tried kohyas recomendation of shift and 3.1582?
Fyep i tested all prior loss
Fgood one gonna test
Fi tested 1.0
Fit makes impact but didnt like it
Mhave you tried different clip skip values?
Fnope
Mnormally we use clip skip 0
Mon your config you're using 1
Fthen probably ignored
Fi think clip skip 1 in kohya means 0
Fgood point gonna test all now
Mno for kohya clip skip 0 is clip skip 1 for a111
Mi think they fixed it a while back
Fnice making a new config now and starting training all
Fif your ram usage getting like this you will get error. set virtual ram. @Laura Wolf exactly has this error atm
Fi shown that in the video
FYouTubeSECourses
Ultimate Kohya GUI FLUX LoRA training tutorial. This tutorial is product of non-stop 9 days research and training. I have trained over 73 FLUX LoRA models and analyzed all to prepare this tutorial video. The research still going on and hopefully the results will be significantly improved and latest configs and findings will be shared. Please wat...
F00:39:59.240 --> 00:40:06.600
Fin the json file there is no difference