Update 2.0!
v2 trained completely from scratch on the SDXL base model for maximum compatibility with other models (works great on Juggernaut XL and Anime Art Diffusion). The training set was increased from 80 images to 350 and trained over a much longer period.
The trigger words have also been changed from "flat color" to "fca style" to avoid conflicts with existing training bias in some models which would really mess up the images.
An anime Lora trained on a modern flat color anime style. SD 1.5 has some really great flat color checkpoints (Flat Color 2D and Coloring Master Anime in particular), but SDXL has been lacking in this particularly style. This Lora aims to fill that hole. It was trained on a lot of images across a range of characters, clothing types, skin tones, hair and eye colours, and a load of other additions so it should have good flexibility.
Recommended weight: 1
Trigger word: fca style