Change Browsing Level to "R" if you want to see the full set of example images.

A character LoRA for the indie VTuber Karo Carabao. Trained on a dataset of 35 images that consists largely of cut up screenshots and images generated by ChatGPT. Despite this, accuracy is pretty good. There can be issues with the hat making her horns appear lopsided but oh well. The below and attached triggers are general suggestions. You can almost certainly get better and more consistent results by more specific prompting. I'm just lazy. Play around with it to see what works for you.

Detailers are highly recommended for the face and eyes.

Manual inpainting or image refinement through ChatGPT are recommended if you're looking to generate small details.

Probably won't be updated.

All example images were generated without a refiner step. You can probably make your generations look much better with improved workflows.

Triggers:

KaroCarabaoWitch, long hair, red hair, green eyes, black horns, curved horns, animal ears, both ears down, medium breasts,

witch hat, black shoulder cape, black top, chest cutout, long sleeves, black sleeves, white cuffs, brown belt, book attached to belt, black cape, green cape interior, white skirt, black overskirt, black tights, black boots,