That notebook is a bit tricky to me
That notebook is a bit tricky to me
Fagreed
Factually i prefer gradio over these but they dont release and i dont get why
Fi even written them from twitter multiple times
Mi chose the one that was NOT 2.0, my batchzie was small wither 2 or 1 eveytime i ran it, 512 x 512 images
Fcould you have anything else that is consuming your GPU vram?
Fwhat is your GPU model
Mrtx 3070ti 8gb ram, no programs running
M
Fcan you try with clip skip 1? i dont know if that would make difference.
Mwhats a clip skip exactly?
Fit is about training weight vectors
Fyou made it 2
Fcould you show screenshots of the all settings if possible
M
Fmake clip skip 1 and check these 2
F
Falso are you using standard lora? what network size?
Msame problem
M
Tstill having same issue where regularization images come out looking like sketches and training ends up looking artifacted no matter how long/short the training session
Fcould it be trying to use your second gpu? amd?
Fwith all models?
For certain model
Tfollowed your videos to the tee, any model
Trealistic vision v20 and sd 1.5 are my main ive been trying
Fso do a fresh install
Fyour installation is problem
Twhich part?
Ti am getting no errors
Fdont know
Ti thought they installed to venvs
Ti followed your videos exactly, even installation
Ti can do it again
Fhere my sd 1.5 man prompt
F
Fyou dont get this @TheRustingDeadAdmin ?
TI get those types of images yes
Tdid you pick out the sketch like ones
Fok it is working then
Fyou dont need
Mwell when i was setting up kohya it asked which gpu and i said all, also in the beggining when the ocmmand starts to run it says this
Fbase model produces good enough. with custom models they are very biased
Fthat can be reason
TThank you, ill reinstall again
Fcan you try with torch 2?
Mdo i have to uninstall and reinstall
Fno
Factivate venv
