Telllinex

Facing the same issue while using LORAs, without them everything is fine(nf4)

> I have a 3060 12GB, I trained a lora just the day before yesterday, same config doesn't work today after I updated yesterday. I had `41afd2662ff11e70630066bfbc6101a3272420ab `commit before updating....

> Yes, same error of "returned non-zero exit status [3221225477](tel:3221225477)". Honestly, I didn't want to go back because of a previous miserable experience, and I wasn't in hurry and hoped...

> @Telllinex This might help: https://github.com/bmaltais/kohya_ss/wiki/LoRA-training-parameters > > Also, why did you close this issue as completed? The issue is still there, we just reverted back to a previous commit!...

> @Telllinex This might help: https://github.com/bmaltais/kohya_ss/wiki/LoRA-training-parameters > > Also, why did you close this issue as completed? The issue is still there, we just reverted back to a previous commit!...

> I don't know about this particular error, but 16GB RAM seems too low to train Flux Lora, it takes up a lot of memory. Also, try restarting your PC,...

> See, I get around 10 something s/it with batch size of 1, on my 3060. So, your lack of RAM is definitely worsening your speed. > > Make the...

Still doesn't work - previews appear on second sampler, but not on first. We're talking Wan 2.2

> > Still doesn't work - previews appear on second sampler, but not on first. We're talking Wan 2.2 > > What versions of the app and frontend are you...