Are you running your OS with the same 12GB card?
Are you running your OS with the same 12GB card?
EWhich 1 step installer?
AIn the kohya 1 click installer on his patreon
LYes and RAM 32GB
LI used all Config file train_data_dir. 8 GB GPUs : Rank_9_7514MB.json, 10 GB GPUs : Rank_7_9502MB.json, 12 GB GPUs : Rank_5_11498MB_Slow.json, all give memory errors
PI do this all the time on accident, but make sure you are using the LORA tab and not the Dreambooth tab in Koyha. It will fail with out of memory errors.
EHmm, I can see the 12gb it looks like it is failing pretty early. Do you have a game running in the BG or another stable diffusion UI running in the BG.
It looks like it is failing because there is only 5gb free on the card and it needs 6gb
It looks like it is failing because there is only 5gb free on the card and it needs 6gb
LNo, I don't have any other background tasks, I only work with Kohya.
L
LI don't know, I've been testing everything and something's going wrong.
Fsorry for delay. i was planning actually today too but i got some real life bussines. moving from moutain house to city again
Fsure showna ll
Fdepends on how many epochs
Ftell me i can tell you
Fye i am aware but i still like kohya
Fi train in my rtx 3060
Fhow much vram your system using before starting the script?
Falso dont upgrade torch 2.5 it may use more vram and it didnt bring speed when using single layer strategy
Fplease do this and see what error you get
F
Fopen google remote
Fi will pin point your error
Fif you have 1 time loaded config into dreambooth it will get corrupted
LI haven't updated anything. I have RAM running at max level, before moving text encoders to gpu and after that it gives an error
Fprivate message me your config json file please
Falso show your task manager gpu before starting training
Fscreenshot of it
M1024 Speeds on windows finally working faster 
Fawesome speed
Fused torch 2.5?
Mjust pulled the latest dev one
F4090 is a beast and shines with flux
Fsdxl had no such speed diff
Fwhen training
Mhave you tried h100?
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