V2 Update:
Ars Niji 2 - Now with 50% more Waifus coming soon.
Complete rework of the dataset, so it reflects better the adjustments to my "Personal Style" in the last year.



This LoRA is trained on 500 handpicked Niji images that use my 'Personalized Style'

The Trigger is ArsNijiStyle

It works well in the 0.4 – 1.5 range.
Best results found between 0.8 – 1.2, depending on you LoRA stack.

Update: Merged the 2 model cards.