Available Models

Flux 1.1 Pro Ultra
FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels.
Recraft V3
Recraft v3 (code-named red_panda) is a state-of-the-art text-to-image model from https://recraft.ai
Ideogram 2.0
Flux 1.1 Pro
State-of-the-art image generation with top of the line prompt following and visual quality
Stable Diffusion 3.5 Large
Stability AI's latest model with greatly improved performance in multi-subject prompts, image quality.
Stable Diffusion 3
Stability AI's latest model with greatly improved performance in multi-subject prompts, image quality.
Watercolor
State-of-the-art image generation with top of the line prompt following and visual quality
Ghibsky Illustration
State-of-the-art image generation with top of the line prompt following and visual quality
Red Cinema
State-of-the-art image generation with top of the line prompt following and visual quality
Half Illustration
State-of-the-art image generation with top of the line prompt following and visual quality
Black Light
State-of-the-art image generation with top of the line prompt following and visual quality
Monkey Island
State-of-the-art image generation with top of the line prompt following and visual quality
Dreamscape
State-of-the-art image generation with top of the line prompt following and visual quality
Childbook Illustration
State-of-the-art image generation with top of the line prompt following and visual quality
Neon Tokyo
State-of-the-art image generation with top of the line prompt following and visual quality
Stable Diffusion SDXL
SDXL 1.0 (Latest)
DALL·E-3
OpenAI's DALL·E-3 model
Poster Prints
Minimalist Japanese block print style
Voxel Assets
Create characters in voxel style
Sticker
Create fun stickers on a plain background
Playground v2.5
State-of-the-art open-source model in aesthetic quality. Outperforms SDXL, DALL-E-3, & MJ 5.2
SDXL Lightning
4 step inference SDXL model for faster generations
Studio Ghibli
Stable Diffusion SDXL fine tuned on Studio Ghibli movies.
JuggernautXL v9
Create high resolution photorealistic images
OpenDALL·E 1.1
A mix between DALL·E 3 & SDXL
RealVisXL 3
Amazing photorealism with RealVisXL_V3.0, based on SDXL
Scribble Portraits
Generate portraits in a scribble art style
Playground v2
A diffusion-based text-to-image generative model trained from scratch by the research team at Playground
Hiroshinagai
SDXL model trained on Hiroshi Nagai's illustrations
Manga
SDXL model trained on manga illustrations
Minimalist Design
SDXL model trained on images of minimalist interior design
Overwatch
SDXL model trained on images of Overwatch characters
Kandinsky
Kandinsky 2.2
Barbie
Stable Diffusion SDXL fine tuned on Barbie images.
Polaroid
SDXL fine tuned on Polaroid images
Money
SDXL fine tuned on images of bank notes
DALL·E-2
OpenAI's DALL·E-2 model
Mascot Avatar
SDXL fine tuned on mascot avatars
Würstchen
Würstchen v2 - A high performance diffusion model
Think Diffusion XL
Think Diffusion XL - capable of amazing photorealism
LCM
Latent Consistency model focused on creating high resolution images with Few-Step inference
Openjourney
Model trained with Midjourney V4 images
Sci-Fi
Stable Diffusion SDXL fine tuned on 70's Sci-Fi theme
Loteria Card
A SDXL fine tuned model that generates Loteria cards with in-painting
Icons
SDXL fine tuned to generate slick Icons and Flat Pop Constructivist Graphics with thick edges.
Fooocus
Fooocus - a mix of Midjourney and Stable Diffusion.
Deliberate
All in One - general purpose model
Classic Animation
Disney style generations
Realistic Vision v5
Generations focused on photorealism
Davinci
SDXL fine tuned on Davinci's illustrations
GTA V
Stable Diffusion SDXL fine tuned on the game Grand Theft Auto V
Emoji
Stable Diffusion SDXL fine tuned on emojis
Panorama
Stable Diffusion SDXL fine tuned on panoramic images.
Tron
Stable Diffusion SDXL fine tuned on Tron theme
Sonic
Stable Diffusion SDXL fine tuned on Sonic the Hedgehog
Dreamshaper
Model focused on anime, characters, and landscape