Trained on AnyLora
I don't know if i nailed it yet, but this is definitely an improvement over the last version.
To get the best results, please read the description below:
Recommended weight for V1: 0.6-0.9
Recommended weight for V2: 0.7-0.85
Activation word for V1: Power
Activation word for V2: PowerV2
Upscale to 1.5
Using anime SD models is recommended, semi-realistic checkpoints should also work
I would appreciate any reviews, positive or negative!
I would very much appreciate you sharing your results ^_^
If you have any suggestions on what LoRA i should do next, please share them in the comments
Enjoy :)
P.S. I also recommend trying out this checkpoint, it is absolutely underrated which is a shame
It works pretty good with this LoRA as showcased