Igawa Sakura is on NoobAI-XL, PonyXL and 1.5 animefull now!

Note about 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 use NoobAI-Xl Epsilon!

NoobAI-XL tags:

Igawa Sakura, 1girl,

orange hair, short hair, flipped hair, blue eyes,

Outfit:
black leotard, highleg leotard, elbow gloves, fishnets, showgirl skirt, thigh boots,

Alternative outfit:

black leotard, highleg leotard, elbow gloves, pantyhose, thigh boots

optional:

holding sword, short sword, dual wielding, sword on back

torn leotard, torn clothes

Casual sweater:

off-shoulder sweater, short shorts, denim, socks, sneakers

School uniform:

school uniform, green jacet, miniskirt, pleated skirt, white thighhighs, loafers

PonyXL / SD1.5 tags

Main:

IgawaSakura, 1girl ,orange hair, short hair, flipped hair, blue eyes, curvy, huge breasts, thighs,

optional: holding short sword
Taimanin outfit:
black highleg leotard, elbow gloves, fishnets, showgirl skirt, thigh boots,

optional: change showgirl skirt on pantyhose for another version

Casual clothes:

off-shoulder sweater, short shorts, denim, socks, sneakers

Also you can use another prompt like "wedding dress, bridal gauntlets"

NoobAI-XL quality settings:

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 article.

PonyDiffusion v6 (XL) settings:

Style settings (very important):

score_9, score_8_up, score_7_up, score_6_up, score_5_up, source_anime, uncensored,

Negative prompt (recommended):

dutch angle, censored, mosaic censoring, jpeg artifacts, muscular

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: 0.3

Adetailer: denoising strength 0.3. Detection model confident threshhold: 0.7-0.8.

Best sampling method is euler / euler a, 25-40 sampling steps, You don't need any DPM++

Don't forget to like LoRA model :3

https://tensor.art/u/604375505701151021