Obligatory Disclaimer: This LoRA is intended to be used alongside style LoRAs and/or artist style tags to bring out its full potential. All example images use WAI-Anima and the "haku89" artist style tag.

If you don't see all 4 example images, try change Browsing Level to "R" or lower.

A character LoRA for the indie VTuber Haoto. Trained on a dataset of 40 images that consists largely of cut up screenshots, images generated by ChatGPT, and a few fanarts.

I'm still very new to Anima LoRA training so do forgive any issues or weirdness. As such, this LoRA does have its quirks. Sometimes, when prompting for her heterochromia, her lavender eyepatch will appear when face face detailing. Not a big deal but something to consider.

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:

HaotoVT, long hair, ahoge, blue hair, heart-shaped eyepatch, lavender eye patch, pointy ears, black bad wings, medium breasts,

black maid headband, white frilly collar, tight dress, black dress, white dress collar, white maid apron, lavender sleeves, white sleeve cuffs, black thighhighs, garter belts, lavender heels,

heterochromia, red eye, black eye, scar across eye,