Works with most anime models. Realistic models might not work, I don't use any.
If you like my LoRA, please consider giving me a rating!
Best weights: 0.6-0.9 - canvas size in portrait formats work well
Use 0.6 if you only care about the general shape of her hair. For results accurate to the characters, use 0.7-0.8. IF you want to be as accurate as possible, use 0.9.
For best results, include the following tags:
tia, long hair, brown hair, yellow eyes,
For her original outfit, include:
jacket, shoes, shorts, hair ornament, holding brush,
Models used for preview images:
MizuMixV5: https://civarchive.com/models/103270?modelVersionId=110783
VampeliumMixV2: https://civarchive.com/models/91829?modelVersionId=113096
XXMix_2.5DV1: https://civarchive.com/models/54416/xxmix25d
4th model is a secret!
Description
Release. Very difficult to create Tia with such a small dataset. I will revisit this LoRA in the future when I have more pictures of her to work with.