Kamiyo Ai form Dark Gathering
Trained with 70 images from the anime on the AAM AnyloraAnimeMix checkpoint.
Recommended settings:
Sampler: Euler a - 35 steps
CFG: 7
Resolution: 512x768, 768x512, (works with most common SD1.5 resolutions)
Lora weight: 0.75
HighRes: 4x_NMKD-Siax_200k, upscale by 2x, 25 steps, 0.35-0.5 denoising
Basic prompt:
<lora:kamiyoai1.2_SD:0.75> kamiyoai, 1girl, blonde hair, red bow, side ponytail, blue eyes, star-shaped pupils, fang, red coat, plaid skirt, pink converse, necktie, choker
(This is just a suggestion, you can change her clothes however you want. You don't need the entire prompt.)
Additional notes:
Make sure to describe the background/setting in detail
I used the FastNegativeV2 embedding by Lykon for the samples
My samples have the prompts embedded if you need inspiration
Star-shaped pupils inpainting lora:
Since SD1.5 struggles with small details, the character's unique pupils often come out misshaped. I trained a separate lora with closeups of her eyes that you can use to fix the issue. Btw, you can use it to inpaint star pupils on any other character as well. :)
Prompt for inpainting:
<lora:ka_star-shaped pupils_SD:0.8> star-shaped pupils
Inpaint area: only masked
Sampler: euler a - 25 steps
Resize to: 768x768
Denoising strength: 0.8 (if you're using an inpainting model you can crank it up to 1.)
Tested models:
AAM AnyloraAnimeMix
EtherBluMix v6
HassakuHentaiModel_v13
Yuzu v1.1