The first thing you should do after you start using the LoRA is to go to one of the artist's pages and leave a few nice words under one of their artworks. That's a rule now - support the artist!

Artist's resources:

https://www.pixiv.net/en/users/16??9234

https://x.com/kopikakopika

Other previews are here.

I trained this two weeks ago and completely forgot about it lmao

Recommended samplers:

• DPM++ 2S a - 20 steps

• DPM SDE++ - 18-20 steps

• DDPM - ~40 steps

• DPM++ 2S Ancestral Comfy - 18-20 steps

Recommended upscale settings - here.

Recommended checkpoint:

NAI-XL vpred1.0 2d accelerated "Final" version

You may try to generate with graphite \(medium\) instead of canvas but I found outputs with "canvas" in positives are way better in terms of colors and such.

Also LoRA gives interesting results without traditional media and graphite tags.

If you found the LoRA interesting or somehow useful, consider supporting me by joining my Telegram channel. I post thoughts (in Russian) there and do streams of LoRA making.