T-Shirt Diffusion

colorbook

Papercutcraft

Redshift Diffusion

HASDX

Mega Merge Diffusion

Healy's Anime Blend

Sci-Fi Diffusion

Borderlands

Voxel Art Diffusion

Sygil-Dev Diffusion

Elden Ring Diffusion

Future Diffusion

Cyberpunk Anime Diffusion

Vintedois Diffusion

Microworlds

mo-di-diffusion

Min Illust Background

Robo-Diffusion

Concept Sheet

Zeipher Female Model

AIO Pixel Art

Dungeons and Diffusion

trinart

Yiffy

DreamLikeSamKuvshinov

Midjourney PaintArt

App Icon Diffusion

Smoke Diffusion

Inkpunk Diffusion

Moedel

DnD Item

Zack3D

Fantasy Card Diffusion

stable_diffusion

Synthwave

Anygen

Furry Epoch

Asim Simpsons

PortraitPlus

Anything Diffusion

Tron Legacy Diffusion

stable_diffusion_2.0

Clazy

Realistic Vision

Valorant Diffusion

GTM Ultimate Blend

Stable Diffusion 2 Depth

Papercut Diffusion

Deliberate

ChromaV5

stable_diffusion_2.1

DucHaiten

Dark Victorian Diffusion

Analog Diffusion

Guohua Diffusion

CharHelper

vectorartz

Classic Animation Diffusion

Eimis Anime Diffusion

Microscopic

Ranma Diffusion

Dreamlike Diffusion

3DKX

Poison

Midjourney Diffusion

kurzgesagt

Samdoesarts Ultmerge

Dreamshaper

Elldreth's Lucid Mix

Dreamlike Photoreal

Trinart Characters

Arcane Diffusion

JWST Deep Space Diffusion

Hassanblend

Lawlas's yiff mix

waifu_diffusion

ModernArt Diffusion

Sonic Diffusion

Darkest Diffusion

Balloon Art

BubblyDubbly

Comic-Diffusion

Eternos

MoistMix

Marvel Diffusion

Van Gogh Diffusion

Double Exposure Diffusion

Squishmallow Diffusion

Funko Diffusion

Zelda BOTW

Hentai Diffusion

Protogen Infinity

Epic Diffusion

Ghibli Diffusion

Seek.art MEGA

Knollingcase

Spider-Verse Diffusion

SFW model with limited nsfw capabilities (suggestive nsfw) that is highly versatile for 3D renders.

An improved version of Anything v3 made with ACertainThing, focusing on scenes rather than characters

ACertainThing

Stable Diffusion fine tuned on pixel art sprites and scenes

A dreambooth model trained on a diverse set of analog photographs

A best of both worlds - merging the anime of Anything v3 with Protogens photorealism - VAE is included

Dreambooth model fine tuned on mobile app icons

Based on the Archer's TV show animation style

Archer Diffusion

This is the fine-tuned Stable Diffusion model trained on Twisted Balloon images

Based on Borderlands video game style, trained on characters and scenes

This model was trained on a digital painting style mainly with characters and portraits. The main objective is to train a model to be a tool to help with character design ideas

Popular animation studio classic style generations.

This model is just the first dreambooth iteration for concept-sheet/old-books style. Based on SD 2.1

Dreambooth model based on Vintedois, trained on a dataset of DGSpitzer art. Styles included are outline, sketch, anime, painting and landscape

DGSpitzer Art Diffusion

Model trained with a dataset of DanMumford Style images, courtesy of Flonix

Dan Mumford Style

finetuned on dark, moody, victorian imagery

A free and open source Stable Diffusion model created by AI-Characters, trained on the artstyle of the game 'Darkest Dungeon'

This model provides you the ability to create anything you want. The more power of prompt knowledges you have, the better results you'll get. It basically means that you'll never get a perfect result with just a few words. You have to fill out your prompt line extremely detailed

This is a model (dnditem) for creating magic items, for the game Dungeons and Dragons! It was trained to be very similar to the official results that are available here: https://www.dndbeyond.com/magic-items

The Double Exposure Diffusion model, trained specifically on images of people and a few animals

A mixture of Dreamlike Diffusion 1.0, SamDoesArt V3 and Kuvshinov style models.  Created mostly for exploring different character concepts with a focus on drawings, but the mix happened to be pretty good at realistic-ish images, all thanks to wonderful models that it uses.

Dreamlike Diffusion 1.0 is SD 1.5 fine tuned on high quality art, made by dreamlike.art

Dreamlike Photoreal 1.0 is a photorealistic Stable Diffusion 1.5 model fine tuned on high quality photos, made by dreamlike.art.

Merged model mix of Midnight mixer, roboEtics, f222, elldrethSLucidMix, Seek.ART Mega, rpg, hassanBlend, modelshoot and roboDiffusion

Generates D&D styled characters, trained on art commissions

This model is trained with high quality and detailed anime images

It's an all-around easy-to-prompt general purpose semi-realistic to realistic model that cranks out some really nice images. No trigger words required

Epic Diffusion is a general purpose model based on Stable Diffusion 1.x intended to replace the official SD releases as your default model. It is focused on providing high quality output in a wide range of different styles, with support for NFSW content.

fantasy trading card style art, trained on all currently available Magic: the Gathering card art

Stable Diffusion fine tuned on Funko Pop, by PromptHero.

This creates high quality 3D images with a futuristic Sci-Fi theme

This model was trained on the loading screens, gta storymode, and gta online DLCs artworks. Which includes characters, background, chop, and some objects. The model can do people and portrait pretty easily, as well as cars, and houses. For some reasons, the model stills automatically include in some game footage, so landscapes tend to look a bit more game-like.

GTA5 Artwork Diffusion

GalaxyTimeMachine's GTM Ultimate Blend - a generalist model good at portraits, scenery with a fantasy vibe

fine-tuned Stable Diffusion model trained on images from Studio Ghibli feature films

fine-tuned Stable Diffusion model trained on traditional Chinese paintings

He merged a few checkpoints and got something buttery and amazing. Does great with things other then people too. It can do anything really. It doesn't need crazy prompts either. Keep it simple. No need for all the artist names and trending on whatever.

This is a blend of some anime models mixed with 'realistic' stuff

Anime focused model with better hands, obscure poses/camera angles and consistent style

inspired by Gorillaz art, FLCL and Yoji Shinkawa. Trained on images generated from Midjourney

Stable Diffusion fine tuned on JWST imagery

generates a glass display case with objects inside, inspired by Sean Preston. Trained on Midjourney images

Based on yiffy-e18 and Anything, produces sfw/nsfw furry anthro artworks of different styles with consistant quality, while maintaining details on stuff like clothes, background, etc. with simpler prompts.

This model was trained on images from the animated Marvel Disney+ show What If, which includes characters, background, and some objects

This is the fine-tuned Stable Diffusion model trained on microscopic images

Stable Diffusion fine tuned on Midjourney v4 images

This fine-tuned Stable Diffusion v1.5 model was trained on a selection of artistic works by Sin Jong Hun

You can use this model to generate modernart style images

Moe.del produces cute female characters. It is also a mix of Stable Diffusion 1.4/1.5 in different proportions so you can challenge it to generate for you pretty much anything using regular SD prompts (like cute dogs, cats etc.)

Multi-Style model trained on Arcane, Archer and Mo-Di

Nitro Diffusion

NSFW Model for realistic and Hentai images

PPP is a realistic model merge, tested and tweaked for human females. Mostly based on NSFW models

Stable Diffusion fine tuned on Paper cut images

Paper Cut Craft is a fine tuned Stable Diffusion model trained on Midjourney images

Anything Diffusion fine-tuned to produce high-quality realistic anime styled images

This model was trained on Gen 1-8 Pokemon low poly renders

Pokemon3D

This is a dreambooth model trained on a diverse set of close to medium range portraits of people.

ProtoGen

Protogens photorealism mixed with more science fiction, comic, and synthwave to make ultimate awesomeness

portraits of charecters in the style of the game Baldur's Gate

imitates the style of late '80s early 90's anime, Anything v3 base

Dreambooth model trained on high resolution 3D artworks

Portraits in the style of Sam Yang, merged with chewtoy and orange code's models

A Sci-Fi themed model trained on SD 1.5 with a 26K+ image dataset

Seek.art MEGA is a general use 'anything' model that significantly improves on 1.5 across dozens of styles. Created by Coreco at seek.art

This is the fine-tuned Stable Diffusion model trained on images of smoke

SonicDiffusionV2.ckpt was trained on AnythingV3 for 200 epochs of 203 hand captioned Sonic images from various artists

Based on the Into the Spider-Verse movie's animation style

This is a fine-tuned Stable Diffusion model (based on v1.5) trained on screenshots from Gerry Anderson Supermarionation stop motion animation movie, basically from Thunderbirds tv series

Supermarionation

This model is a Stable Diffusion v1.5 fine-tune trained on the Imaginary Network Expanded Dataset. It is an advanced version of Stable Diffusion and can generate nearly all kinds of images, no matter humans, reflections, cities, architecture, fantasy, digital arts, landscapes, or nature views.

Stable Diffusion model to create images in Synthwave/outrun style

Generates t-shirt logos, base model is vintedois-diffusion with additional training on t-shirt logos size 640x640px

Derrida (formerly TrinArt Characters v2) is a stable diffusion v1-based model that was further improved on the previous characters v1 model. While this is still a versatility and compositional variation anime/manga model like other TrinArt models, when compared to the v1 model, Derrida was focused on more anatomical stability and slightly less on variation due to further multi-epoch training and finetuning.

This model will add a LOT of skin detail compared to SD 2.1. Sometimes this makes images look more realistic, sometimes less realistic!

Ultraskin

This model was trained on the Valorant agents splash arts, and some extra arts on the official website

Stable Diffusion model trained on screenshots from the film Loving Vincent, best results with k_euler sampler

Vintedois (22h) Diffusion model trained by Predogl and piEsposito with open weights, configs and prompts (as it should be).  This model was trained on a large amount of high quality images with simple prompts to generate beautiful images without a lot of prompt engineering.

Stable Diffusion fine-tuned on voxel art style

dreambooth model trained on a very diverse dataset ranging from photographs to paintings

Wavyfusion

Xynthii-Diffusion (cyclops monster girls)

Xynthii-Diffusion

Kink/NSFW oriented furry styled generations.

For creating images of nude solo women. Also known as f222

based off work of great artworks from Legend of Zelda: Breath of The Wild

A DreamBooth finetune of Stable Diffusion v1.5 model trained on a bunch of stills from Kurzgesagt videos

Popular animation studio modern style generations.

Generalist AI image generating model. The baseline for all finetuned models.

ArtBot

Create new image