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/3052010
Recommended samplers:
DPM++ 2S a - 20 steps
DPM SDE++ - 18-20 steps (showed best results (again. no, I didn't forget to change the description after copypaste))
DDPM - ~36 steps
DPM++ 2S Ancestral Comfy - 18-20 steps
Recommended upscale settings - here.
Recommended checkpoint:
NAI-XL vpred1.0 2d accelerated "Final" version
You can get both colored and monochrome results since pics of both kind were used for training.
Also, "gigantic penis" works really fine. xd
Also also, I just realized I fucked up with placing image to PS canvas, which means you may get small white/random color bars on the edges of the outputs. I think that's not a big deal but I really don't want to launch the training one more time so... sorry for that.
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 (sometimes)