Your favorite dommy mommy Marie Mamiya from Starless is on NoobAI-XL (Epsilon Illustrious / V-pred), PonyXL and SD 1.5 now!
Main tags:
Mamiya Marie, 1girl, mature female,
red hair, short hair, hair ornament, makeup, pink lips, yellow eyes, mole under eye,
key necklace, bracelet, choker,
Blue dress:
short dress, black thighhighs, short sleeves, ???? shoulders, lace, diamond \(shape\),
Babydoll:
babydoll, Negligee, barefoot, white panties, see-through,
Underwear:
Underwear only, brown panties, brown bra, lace
Main tokens:
Marie Mamiya, mature female, milf, red hair, hair ornament, lipstick, makeup, (mole under eye:0.8), choker, yellow eyes, earrings, fingernails
Main dress:
main dress, black thighhighs, highheels, ???? shoulders, necklace,
For her ???? night lingerie:
lingerie, (negligee, babydoll:1.1), necklace
Also you can try "party dress, side slit" but it work not so well as it drawn in 4 arts.
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".
More in my articles.
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,
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
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: 16-18
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, 25-40 sampling steps. cfg 7-9, You don't need any DPM++.
I will be glad to receive feedback from you and a demonstration of your art with my LoRA!
https://tensor.art/u/604375505701151021
