You can achieve either colored or monochrome results (exclude any color tags and use monochrome, greyscale, hatching \(texture\) ).
Artist's resources:
https://www.pixiv.net/en/users/4122
If you found the LoRA interesting or somehow useful, consider supporting me by joining my Telegram channel. I post thoughts there and do streams of LoRA making.
Best shot update:
WotB
Recommended samplers:
DPM SDE++ ★ - 18 steps
DPM++ 2S a - 16-20 steps
DDPM - ~40 steps
Recommended upscale settings - here.
Recommended checkpoint:
NAI-XL vpred1.0 2d accelerated "Final" version
Won't get any better or worse.
ILLUSTRIOUS UPDATE
Well who would've thought that making a good style lora of an artist who has little colored images and has no consistent coloring techniques is nearly impossible. I've spend 5 days trying to achieve good result but ended up unsatisfied again. Well, at least it is something.
Illustrious version is really different from the pony one, and I don't know exactly why is that.
Again, it would be great if you share your generated results and maybe leave a feedback.
Description
I completed the dataset and retagged all images. It looks completely different but it reflects style of the artist better (I THINK). It has troubles with foreskin and phimosis tags, so try to avoid or even put it in negative prompt. Also you may want to add tags such "pink background" and "dark skin" to negatives.