Today i finished my first manga character LoRA for Minami Mitsuko - very hot milf from hentai manga Ultramadam.
Now it is available on NoobAI-XL / PonyXL and SD 1.5 anime!
NoobAI-XL / PonyXL tags:
Minami Mitsuko, 1girl, mature female, brown hair, short hair, brown eyes, earrings, huge breasts, thighs,
Blue uniform: blue uniform, black undershirt, black skirt, miniskirt, collarbone, cleavage
Housewife: orange sweater, grey skirt, miniskirt
Office lady: black blazer, black skirt, miniskirt, collarbone, cleavage
For office lady recommended negative: blue uniform, military uniform, trim
SD 1.5 tags:
Main tags:
MinamiMitsuko, 1girl, mature female, brown hair, short hair, brown eyes, earrings, curvy, large breasts, thighs,
Blue uniform: blue uniform, black bandeau, black miniskirt, collarbone,
Open blue uniform: blue uniform, jacket, long sleeves, (open clothes:1.1), black tank top, black miniskirt,
Housewife: orange sweater, grey skirt
Office lady: black blazer, black miniskirt, collarbone, cleavage
NoobAI-XL quality prompt:
Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.
Use euler, cfg 4-5. Don't use higher CFG!
If you have over-constrasted picture and cfg 4-5 didn't help you can try to put in negative "colorful".
For NoobAI-XL V-pred:
Check my guide about V-pred image generating!
The best model to use V-pred is Cyberfix! But pure NoobAI-XL V-pred is also good.
For Illustrious mixes and NoobAI-XL Epsilon: use NoobAI-Xl Epsilon (especially mixes based on NoobAI-XL Epsilon!).
Guide about NoobAI-XL Epsilon
PonyDiffusion v6 (XL) quality settings:
Style settings for PonyXL before prompt (important):
score_9, score_8_up, score_7_up, score_6_up, uncensored, BREAK
Negative prompt for PonyXL (recommended):
dutch angle, censored, watermark, jpeg artifacts, muscular female
SD1.5 quality settings:
masterpiece, high quality
in negative: (worst quality, low quality:1.2)
Upscaler / adetailer settings:
Hires.fix: Upscaler foolhardy_remacri (download and put in "ESRGAN" folder in "models" if you are using automatic1111 or forge).
Hires steps: 14-18
Denoising strength: 0.2-0.3
Adetailer: denoising strength 0.3. Detection model confident threshhold: 0.7-0.8.
Best sampling method is euler a (SGM Uniform), 25-40 sampling steps. cfg 5-6, You don't need any DPM++.
Euler A CFG++ SGM Uniform is also good with cfg 1.2 - 1.7.
I will be glad to receive feedback from you and a demonstration of your art with my LoRA!
Description
XL version
FAQ
Comments (11)
oh ，yes
Make more of this I loved it. Big fan of nappi art.
Thank you :3 I think I make.
thank you so much
Thank you for the excellent lora you've made. but I have a request if your okay with it. Can you make a lora of a another similar character named 'Ritsuko Sanada' by a artist named @madamdamashii (here his Pixiv link:マダム魂 - pixiv). His artwork is similar to 'nappi.'
thank you :3 But she is literally Minami Mitsuko in little different style... Or maybe I can't see arts. Also I can't find any arts on booru :/
@Enigmata Oh I see, that's understandable. I don't know if I'm wrong, but if you were able to login into the account, then you will see his arts of his 'character' (under the NSFW tag/filter). Hopefully the artist releases more arts, which would be helpfully easy to train.