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/10395573
This style is fucking amazing. I managed to squeeze the maximum out of ridiculously high resolution artworks.
I suggest you to put "cropped, comic, out of frame, blank speech bubble, motion lines" to your negatives since there was a lot of those tags in the captions. Oh, and of course "bar censor, mosaic censoring".
Recommended samplers:
DPM++ 2S a - 20 steps (showed best results)
DPM SDE++ - 18-20 steps
DDPM - ~36 steps
DPM++ 2S Ancestral Comfy - 18-20 steps
Recommended upscale settings - here.
Recommended checkpoint:
NAI-XL vpred1.0 2d accelerated "Final" version
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)
Description
Adjusted tags and dataset images a bit, filtered some really old artworks.
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.