LoRA trained on the anime adaptation of the monogatari series of ligh novels.
Trained on general tags but characters can be generated with associated tags
examples:
Tsubasa Hanekawa: 1girl, solo, long_hair, black_hair, hair_ornamen, brown_eyes, braid, glasses, hairclip, , twin_braids
Shinobu Oshino: 1girl, solo, long_hair, blonde_hair, yellow_eyes, blush_stickers
Mayoi Hachikuji: 1girl, solo, long_hair,, black_hair, red_eyes, ribbon, twintails, hair_ribbon, hairband
Hitagi Senjōgahara : 1girl, solo, long_hair,, blue_eyes, ponytail, purple_hair,
ect
if stuck on how to steer the characters inputting an example image into auto tagger will help.
This model was trained with labels constructed using smiling wolfs wd-v1-4-swinv2-tagger-v2 at .25 threshold. Tags outputted from that are likely to match the training data.
Suggested base model to use for the lora is 7th animeC
Description
FAQ
Comments (2)
was it trained only on characters/people ? did you train it on environment pictures ?
yo, super late comment, but could you link the training images please?



