Trained on AnyLora
To get the best results, please read the description below:
Recommended weight: 0.7-0.9
Activation word: Conis
Upscale to 1.5
Using anime SD models is recommended, I haven't tested any semi-realistic checkpoints.
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 :)
Description
Version 1 - trained on 37 images
FAQ
Comments (2)
beautiful, can you kindly tell me for vertical images, do you use 512x768 (hi-res) or any other aspect ratio?
Yep, i always use 512x768 with 1.5 upscale