Every sticker you own, every image you have stickered, and every sticker your work has collected. It is a new tab on your profile.

Sticker Book

Build your own image feed out of the creators and models you care about. It's a trial, so tell us how it goes.

Hubs

You set your own price now, up to the top rate on every tier. What's limited instead is how many new model versions you can price each month.

Licensing Fees: The Cap Is Gone

We're a Day-0 launch partner for MiniMax H3, a next-gen open-weights multimodal video model - and it's already in the generator. No waitlist. Open weights land in a few days.

MiniMax H3 is live: open-weights video, generate now

Krea 2 facial-expression control LoRA trained on adult East Asian female portrait references. No trigger word is required. Describe expressions naturally using gaze direction, eyelid openness, eyebrow position, mouth shape, cheek tension, tears, asymmetry, head angle, and intensityThis is a early .version do let me know any request I’m working on making it as complete as I can

This version is a major refinement over the original Nuance Female Emotion LoRA.What’s ImprovedStronger facial mechanics control V3.1 focuses much more on precise, readable facial actions instead of broad emotion labels. You’ll get clearer results on:<ul><li>Eye direction and eyelid position</li><li>Brow tension and asymmetry</li><li>Mouth shape (parted, pressed, asymmetrical smiles)</li><li>Tongue position and subtle lip gestures</li><li>Micro-expressions and held emotions</li></ul>Better expression range Compared to V1, this version handles a wider spread of nuanced states more reliably:<ul><li>Sleepy / half-lidded / just-awake</li><li>Coy and over-the-shoulder glances</li><li>Uneven winks</li><li>Restrained laughter</li><li>Soft relief and quiet vulnerability</li><li>Micro disgust / aversion</li><li>Soft cognition / realization</li><li>Puffed cheeks and playful asymmetry</li></ul>Cleaner trigger behavior The new trigger nuexpress is more consistent. Pairing it with specific facial descriptions (the way the training captions were written) activates the LoRA more reliably than the broader prompting style needed for V1.Higher data quality<ul><li>171 carefully filtered pairs</li><li>No exact duplicates</li><li>Controlled intensity ladders</li><li>Stronger focus on East Asian facial features and natural skin texture</li><li>Better balance between subtle and exaggerated expressions</li></ul>Recommended UseFor best results, start prompts with:nuexpress, early-20s East Asian woman, [specific facial mechanics]...Describing the actual eye, brow, and mouth positions works better than just writing “sad” or “happy.”

v2.0

nuance female emotion

35ce5dd0-0e60-4ea8-aa8f-4c9a1725f0a4.jpeg

physical violence

weapon violence

wide hips

revealing clothes

downblouse

convenient censoring

pg-13

corpses

suggestive

oral invitation

pg13

sexy

huge breasts

thick thighs

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

female underwear

nude

nsfw

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy

Concept Creators