Part_LoRAs
This is a LoHa LoRA! You need the extension!
Why? LoHa have virtually no effect in output art style and they do a lot better with multi-concepts.
Trigger words for V3.13:
<lora:KnottedShirtv313:0.7>(knotted shirt)
You can try "cleavage" or "shirt pull"(they don't work together), "bra", "no bra", "short sleeves", "long sleeves", "sleeveless", "plaid", "nipple slip", "see-through"(could be paired with "wet"), "navel", "midriff"(for short shirt).
Notes: DON'T USE "FRONT-TIE TOP"!!! Also, use "shirt pull" for breasts poking out, should work with and without the bra) and "nipples" helps with nudity! "shirt pull, bra:0.5" helps with breasts poking out WITH the bra.
Follow the steps in the Model Version notes to reproduce my images.
Sample images generated from Grapefruit.
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.
You might want to add some negatives, for example:
(nipple slip, see-through, no bra, shirt pull)
It was trained on 210 512x512 images scraped from the internet and 13 epochs using animefull_final.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.
Popularity
Info
Version v3.13: 1 File
About this version: v3.13
Generate using a weight of 0.3-1 like this: <lora:KnottedShirtv313:0.7>.
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 0.4, 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.
If anyone is curious about my version names: v{version}.{trainingEpochs}
3 Versions
Go ahead and upload yours!
