If you support me, please buy me a ko-fi.https://ko-fi.com/turugini
The character Lora was created using only the image of Astolfo wearing a sailor suit. This costume has so many colors that the Cutoff extension is a must.
In version 2, the learning method was changed from kohya_ss to TrainTrain.
version 3, I finally understand stratified learning. I think this will remedy the problem of not being able to use Lora together.
The learning method was changed back from TrainTrain to kohya_ss in version 4. Sorry for the frequent version changes.
A mistake in specifying weights for Down LR weights has been corrected.
version final the model used for training was changed.