Please check out my Ko-Fi page if you are interested in supporting me.
LoRA commissions open! -> Fiverr
This is a LoHa LoRA! You need the extension! Why? They do a lot better with multi-concepts.
For her original clothes: <lora:Kikunojov320:1>(yellow kimono, bangs, ponytail, red hair ribbon)
And if you want, tags for feminine or masculine details.
Follow the steps in the Model Version notes to reproduce my images.
Sample images generated with AbyssOrangeMix3A1.
All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.
It was trained on 41 512x512 images scraped from the internet and 20 epochs using Animefull-final-pruned.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger Extension and fine tuned.
You can probably generate it in SFW/NSFW and either very feminine or more masculine body types and genitalia (both types were present in the dataset, people really like to draw her all kinds of ways).
Description
Generate using a weight of 0.3-0.7 like this: <lora:Kikunojo:0.7> .If you don't, the art style of the dataset will overpower your main model style.
How I archived my generations:
txt2img: DPM++ SDE Karras with 20 steps,512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.5, CFG 7. Then send to img2img!
img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.
extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.