Leona Morimoto from Discipline: Record of a Crusade is on NoobAI-XL V-pred / Epsilon / IL / Pony and SD1.5 now!
TAGS:
Leona Morimoto, 1girl, blonde hair, long hair, twin drills, blue eyes, half updo, hair bow, white bow
School uniform:
purple school uniform, two-tone jacket, necktie, pleated skirt, purple thighhighs, yellow trim, red armband
Red latex dominatrix outfit:
o-ring top, bondage outfit, red panties, elbow gloves, red gloves, highleg panties, latex, thigh boots
Chastity outfit:
chastity bra, chastity belt, black collar, padlock, padlock on chastity belt, orange cloak
NoobAI-XL quality prompt:
Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.
Use euler, cfg 4-6. 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,
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: 12-16
Denoising strength: 0.2-0.3
Adetailer: denoising strength 0.25-0.3. Detection model confident threshhold: 0.7-0.8.
Best sampling methods (with 25-40 sampling steps for txt2img):
euler a SGM Uniform, CFG 5-6;
euler ancestral CFG++ SGM Uniform / Simple, CFG 1.2-1.5.
You don't need any DPM++.
I will be glad to receive feedback from you and a demonstration of your art with my LoRA!
Description
SD1.5 animefull
FAQ
Comments (11)
Great! <3
Next all caracter girls from Discipline
Did Matsuno Kaori :3 https://civitai.com/models/1750540
Otokawa saori please...
And can you make for character ichinose sayaka from cleavage hentai? 😍
Where did you find such clear images, with such good resolution? The only ones I could find are those of the "H" but upscaled with AI.
I upscaled them with good upscalers and resized for training resolution.
Also cyberfix model significantly improves quality (like remastering) in comparison with pure NoobAI-XL because base V-pred version is too close in style with source and it's bad for old hentai characters (but good for good quality datasets like my rude frog lora).
Enigmata One more question, what do you recommend? I want to make a LoRA with the discipline characters. I don't know if I should do it for each character or all together. There are around 700 images and it could reach 800.
VoltorReaper Multiple characters in one lora can cause bleed. I prefer to train one lora with one character. They only exceptions are style loras because characters usually are side effect (but characters are less detailed).