The style of CoolerINKER.
Trigger word is @inker shike (changed from previous versions to avoid unwanted inclusion on coolers). This is a Unet-only DoRA for Anima Base 1.0. The dataset is the same as my Illustrious version, other than the changed trigger word.
I'm working on updating my Katawa Shoujo character pack to Anima, alongside significantly improving its capabilities, but that's taking more efforts than anticipated. I'm also developing a dataset preparation toolkit for it, and I decided to take it for a spin on a simpler task for a change.
19.09.2026 - Added regular LoRA version in addition to the DoRA.
If you like the style, please support the original author.
Description
I realized DoRAs had downsides I hadn't previously considered, so now I'm remaking LoRA versions of my DoRA models. In short:
DoRA works better alone and on the same model it was trained for
LoRA works better in combination with other adapters or on checkpoint finetunes
LoRA also appears to work better on Anima 3.8B