-
Notifications
You must be signed in to change notification settings - Fork 135
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Lycoris extreme slow training after update to latest version #167
Comments
please provide full configuration. |
These are the setting used in both Versions { |
What's your hardware |
Win 11, Nvidia 4090, 64gb ddr5 ram, i9 13900k, running from nvme 4th gen |
I do some test and cannot reproduce this error... I'm using almost same hardware (64GB -> 128GB ram) as yours so it should be ok |
@KohakuBlueleaf |
@whythisusername Can you try drouput=0 (all kind of dropout)? |
@KohakuBlueleaf
|
@whythisusername does 2.3.0.dev10 still so slow? |
@KohakuBlueleaf
|
@whythisusername @killerciao Can you try 3.0.0.dev4? |
Tested with latest kohya_ss gui:
🤷♂️ |
umm ok I think it is due to some dtype things |
can you try other algorithm? |
LoKr: |
Thx, looks like locon have some bugs |
@KohakuBlueleaf
|
Can you try to enable "bypass_mode"? |
@KohakuBlueleaf
|
Ok I think the problem is solved |
After updating to the latest release Lycoris/LoCon (the only one i tested) training in kohya_ss is super slow. With my 4090 with the same setting loaded, in the previous version was running at about 1it/s for SDXL training, now 4-10s/it.
Nothing has changed in the training data.
Uninstalling 2.2post3 and installing 2.1.0post2 fixes the problem
The text was updated successfully, but these errors were encountered: