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

🍁 Fresh Fruits Models 🍁In this project I aim to offer several versions, each different from the others; don't be surprised if a later update has a very different style.To learn more about each version, I recommend checking the version section; it explains in more detail what each one does.

The Grape 🍇 version is here.Recommended parameters:Sampler: Euler a / DPM++ 2M KarrasSteps: 25 – 35 (color) / 20 – 30 (B/W sleeve)CFG Scale: 5 – 7Resolution: 832×1216 (portrait), 1216×832 (landscape), 1024×1024 (square)Clip Skip: 2The negatives I used in each sample image: low quality, bad anatomy, bad hands, extra fingers, missing fingers, fused fingers, malformed limbs, extra limbs, bad face, asymmetrical eyes, cross-eyed, watermark, signature, text, logo, blur, jpeg artifacts, print, text

Grape🍇

🍊 Fresh Fruit — Orange [v-pred]A v-prediction version based on NoobAI, designed to generate highly colorful and vibrant anime-style images. If you include "anime style" tags in your prompt, it interprets them perfectly, creating images that look like actual anime scenes.✨ Features🎨 Intense colors and vibrant palettes.🎬 Captures anime-style prompts as if they were scenes from a series.👁️ Detailed eyes and highly expressive faces.📷 Excellent for portraits, close-ups, and dynamic angles (hands, heads, extreme perspectives).🌆 Detailed backgrounds: neon, skies, urban settings, and citrus themes.⚙️ Recommended SettingsSamplers: Euler a / Euler — Also works with › DPM++ 2M Karras · DPM++ SDE (Karras)Steps: 20 – 35CFG: 4 – 7Resolution: 832×1216 or 1024×1024Positive promt: masterpiece, best qualityNegative promt: worst quality, bad anatomy, bad hands, extra digits, text, watermark, blurry,

Orange🍊

Pineapple🍍The pineapple version is based on NoobAI, a mix between Illustrious and NoobAI. It was rigorously tested to achieve the best possible results during generation.Since this is the first NoobAI model I've created, I wanted it to have the best possible outcome.It has a very colorful, 2.5D anime style.My recommended settings:- Sampler Method: Euler - Euler a- Sampler Steps: 15 - 30- Text Strength: 5 - 6- Clip Skip: 2Negative: worst quality, low quality, normal quality, lowres, bad , bad hands, mutated hands, missing fingers, extra digits, fewer digits, text, signature, username, watermark, logo, blurry, jpeg artifacts, deformed, disfigured, ugly, duplicate, cropped, out of frame

Pineapple🍍

🌵 Fresh Fruits Models 🌵

ChatGPT Image 13 ago 2026, 21_33_12 (1).png

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

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

lingerie

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

Base Model Creators