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:
WotB Update (I don't recommend you using previous versions):
Recommended samplers:
DPM++ 2S a - 20 steps ★
DPM SDE++ - 18-20 steps
DDPM - ~40 steps (I didn't test it but I am sure it will perform good)
DPM++ 2S Ancestral Comfy - 18-20 steps
Recommended upscale settings - here.
Recommended checkpoint:
NAI-XL vpred1.0 2d accelerated "Final" version
I highly recommend you to put "uncensored" to your prompt and all censor related tags to your negatives since dataset has a lot of images either with bar or mosaic censoring.
Trained on most recent animations frames and manga pages.
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.
Description
Work over the Bugs
A "major" rethink of how I make LoRAs
Consider every "WotB Edition" version as fixed ones with overall better performance.
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.