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

A character LoRA for y-chan kig's VTuber model. Trained on a dataset of only 20 images that consists largely of cut up screenshots and images generated by ChatGPT. Despite the small dataset, generation is pretty consistent due to the simplicity of her design. There are some issues with accurate legwear length generation. Most checkpoints seem to very often generate full thighhighs instead of the proper over-knee socks but oh well. Try heavy weighting or different triggers and see what works for you. 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:

ychanVT, long hair, twin tails, curly hair, yellow hair, blue eyes, medium breasts,

white bows, white hoodie, white undershirt, pleated skirt, blue skirt, over-knee socks, black over-knee socks, black Mary Janes,