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 Iris Vallod. Trained on a dataset of 40 images that consists largely of cut up screenshots, images generated with my prototype Iris Vallod Illustrious LoRA, and a few fanarts.

I'm still very new to Anima LoRA training so do forgive any issues or weirdness. I do think I prefer Anima over Illustrious since one of the main issues with my Illustrious LoRAs that I never managed to fix was poor hair generation. That issue has been almost completely eliminated upon switching to Anima. Thus, I will probably be making character LoRAs exclusively in Anima going forward as it does really feel like a defacto step up.

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:

IrisVallod, medium hair, long sidelocks, light blue hair, orange eyes, elf ears, medium breasts, vampire fangs,

short cape, red cape, shoulder cape, frilly shoulder cape, dark purple top, frilly top, long sleeves, dark purple rose pin, purple sleeves, white sleeve cuffs, black overalls, dark blue bottom, frilly bottom, lace pantyhose, brown boots,