trained on 38 images on NoobAI ε-pred 1.0
same dataset as v1.0 but with better training parameters:
More consistent eyecolor
Less artifacting
Less style impact
Better hands










Character model based on 34 (pony) / 38 (noobAI) images of Indiana from gacha game Azur Lane. Namely the official splash arts, a few official artworks, some screenshots from the music video, and the small handful of fan arts.
Basic
Works well anywhere between a strength of 0.8 to 1.0.
Base trigger is indiana
Specifying dark skin shouldn't be necessary, but may help improve the result.
The face scar is tagged separately in case you don't want to include it, but can be inconsistent.
Higher strengths (0.9-1.0) will more accurately capture the face scar but may lead to the base outfits bleeding into the output.
Outfits
Outfit components are tagged separately so you can choose what to include.
Base skin:long coat, fur coat, necktie between ???????, harness, cleavage, midriff, black chaps, high-waisted ?????, black boots
'High Noon Arrest' skin:cowboy hat, blue cape, tassels, black bra, cleavage, under boob, belt, hotpants, cutoffs, chaps, crotchless legwear, fingerless gloves, brown boots
In the interest of openness and community-helping, I have uploaded the dataset along with the model, this includes: images, captions, and the training json (for kohya_ss).
trained on 38 images on NoobAI ε-pred 1.0
same dataset as v1.0 but with better training parameters:
More consistent eyecolor
Less artifacting
Less style impact
Better hands
1. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。
2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領
