This is my first SDXL LoRA, so please be nice.

This LoRA makes images with a gothic chibi doll look and should work with most SDXL models.

Usage Guide

• While this doesn't require a trigger word, adding 'gothic doll' somewhere in the prompt can help.

• A LoRA strength between 0.5 to 1.5 is recommended.

• Higher strengths than 1 will increase the style strength but can introduce visual artifacts.

• When up-scaling it can help to reduce the LoRA strength to allow the base model to fix some of the artifacts introduced.

This was trained off a dataset of my own images, so if people like it I'll make a flux version.