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.
Tired of cute anime faces? Me too. Lets fix that!
Trigger words for V3.20 (old v3.20 gone! It was replaced by this hotfix):
positive: <lora:matureFemalev320:0.8>(mature female)
negative (you might have to do "shiny" and "shiny skin" in negatives): loli, cgi
You can also try "3d", "realistic", "lips apart", "small breasts", "thick thighs" and "wide hips" also helps out with more mature look!
I suggest not prompting for "1girl" at all, just go with "mature female" cus it was trained without "1girl" in dataset.
Follow the steps in the Model Version notes to reproduce my images.
Sample images generated with Hassaku.
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 207 512x512 images borrowed from Unstable Diffusion discord, 20 epochs using Animefull-final-pruned for the Training Model.
Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned manually.
Description
Generate using a weight of 0.3-0.75 like this: <lora:matureFemalev420:0.75>.
Version REUPLOADED (v3.20 gone cus it was TRASH) cus I had to fix some issues with dataset! Also trimmed Dataset a bit. :) No more extra shiny for no reason
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}