Model Details

SDXL Model that doesn't require a refiner.

Following on from Gorilla With A Brick, merged in 10 more photorealistic models at various weights, and some more noise offset to create something that when prompted for photorealism will make you go 'I Can't Believe It's Not Photography'. It will happily create CGI characters and awesome landscapes as well.

Highly detailed Anime styled generations

Anime model based on Pony Diffusion XL - remember to use the score prompts to get this to go properly

Pony Diffusion V6 is a versatile SDXL finetune capable of producing stunning SFW and NSFW visuals of various anthro, feral, or humanoids species and their interactions based on simple natural language prompts.

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

The SDXL follow up to ICBINP, now with higher resolution and better realism

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

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 model is a mix of various furry models.

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

The base SDXL 1.0 model.

Very popular realistic model

DreamShaper is a general purpose SD model that aims at doing everything well, photos, art, anime, manga. It's designed to go against other general purpose models and pipelines like Midjourney and DALL-E.

Model for creating photorealistic humans

Model for creating photorealistic humans

For creating images of nude solo women

This blend model aims to achieve versatility in generating images that are almost realistic but with a touch of fantasy and a polished aesthetic. It performs well with both illustrations and simulated photographs, but it particularly excels with the latter

A good looking model, suitable for NSFW and dark scene.

Based on the already popular model Deliberate, this model is a more refined version of it.

SDXL Model for cartoony style. If it's not cartoony enough, you may need to add 'anime, cartoon' to the front of the positive prompt to push the image in the right direction

Realistic finetune of Pony Diffusion V6, with an emphasis on asian likeness.

the unstable models are a collection of checkpoints where limitations cease to exist and creativity knows no limits. This checkpoint defies restrictions and empowers you to generate anything your imagination desires

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

NSFW Model for realistic and Hentai images

Hyper Realistic Looking

Semi-realistic model, Camellia Mix 2.5D V2

This model is a mix of various furry models.

The inpainting version of Realistic Vision

The inpainting version of Deliberate

The inpainting version of DreamShaper

Another model from RCNZ, this one is a true generalist, able to do realism, anime, and cartoons

Animagine XL is the sophisticated open-source anime text-to-image model, building upon the capabilities of its predecessor, Animagine XL 2.0. Developed based on Stable Diffusion XL, this iteration boasts superior image generation with notable improvements in hand anatomy, efficient tag ordering, and enhanced knowledge about anime concepts. Unlike the previous iteration, we focused to make the model learn concepts rather than aesthetic.

Kink/NSFW oriented furry styled generations.

Robot oriented drawing style

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

This model was for creating people

A merge with over 23 other models with a methodical, careful and genuine approach. Freedom of prompting art or photo or both, landscapes or backgrounds or interiors, people or entities or scenes, stiff poses or movement or even mouth and facial emotions.

DucHaiten's character generation model

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.

A spin off from Level4. Built to produce high quality photos. Sometimes photos will come out as uncanny as they are on the edge of realism.

Counterfeit is anime style Stable Diffusion model

A model trained to make detailed, anatomically-accurate (hands, faces, genitals, etc) illustrations of humans and non-humans alike

A model trained to create CG anime characters

AbyssOrangeMix trained for creating NSFW images

Grapefruit aims to be a hentai model with a bright and more softer anime style.

This model is mainly intended for Portraits and Full Body Anime-like pictures. Fantasy landscapes are decent.

The goal of this model was to anchor 526Mix's whimsical and artistic personality into anime. 526Mix can do a pretty cool anime style (and other 2D styles), but it can be a bit unreliable at times. This simple mix increases the reliability, depth, and nuance in 526Mix's anime and anime-esque capabilities.

This model gives a very good detail of skin and textures. Great for close-up photorealistic portraits as well as various characters and models.

The pursuit of perfect balance between realism and anime, a semi-realistic model aimed to achieve beautiful realistic faces with sexy hentai bodies.

This model is generally designed for portraits and full-length anime style photos. Fantastic landscapes are quite decent. And it doesn't require kilometer-long queries to get a high-quality result.

Trained on countless pictures of Beautiful Asian women. (some nsfw images included)

This model is the result of merging several checkpoint models. See homepage for details.

MeinaMix objective is to be able to do good art with little prompting.

It creates realistic and expressive characters with a disney twist.

This is an NSFW prone model. It is meant to generate primarily women and NSFW scenarios. This was made with the new base model merged together, alongside several style LoRA's.

A very versatile model, the more powerfull prompts you give, the better results. Capable of creating both NSFW and SFW images but also great scenery, both in landscape and portrait.

A realistic model, see homepage for details.

This Checkpoint works well on both SFW and NSFW

Hassaku aims to be a model with a bright, clear anime style. Model focus are nsfw images, but also with a high emphasis for good looking sfw images as well.

The inpainting version of A-Zovya RPG

As it is a semi-realistic model, we do not recommend inappropriate exposure.

A realistic model.

The inpainting version of Epic Diffusion

The inpainting version of Anything Diffusion

Reliberate is not a new version of Deliberate. I separate both evolutions / elaborations from each other, and made Reliberate model for those who need to work with photographic style. Yes, you can still create artwork, but it will look more like real artwork than digital.

The inpainting version of iCoMix

This is good for inference (again, especially with styles) even if I made it mainly for training. It ended up being super good for generating pics and it's now my go-to anime model. It also eats very little vram.

Another fantastic realism model

That feeling when you wake up after a dream. This is a fantastic sd1.5 realism bought to you by the creator of DreamShaper

A model for European Comic lovers

Anime screencap model, brought to you by the creator of DreamShaper

This model is built upon the Wurstchen architecture and its main difference to other models like Stable Diffusion is that it is working at a much smaller latent space.

Anime styled generations.

Furry styled generations.

Furry styled generations.

Popular animation studio classic style generations.

Western Comic book style

Tron Legacy movie style

A remake of the old microworld with cleaned up datasets that have no text or labels.

Stable Diffusion fine tuned on Midjourney v4 images

Stable Diffusion fine tuned on Paper cut images

Stable Diffusion fine tuned on pixel art sprites and scenes

Stable Diffusion fine tuned on JWST imagery

Dreambooth model fine tuned on mobile app icons

SD 1.5 merged with 17 other models

Generates D&D styled characters, trained on art commissions. *many* species and classes available, see homepage

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

Generate beautiful vector illustration

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

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

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

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

Midjourney v4 painting style

portraits of charecters in the style of the game Baldur's Gate. check homepage for a massive prompt guide

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

This model is trained with high quality and detailed anime images

generates metalic/chrome looking images

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

A dreambooth model trained on a diverse set of analog photographs

Stable Diffusion fine tuned on Funko Pop, by PromptHero.

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

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

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

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.

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.

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

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

finetuned on dark, moody, victorian imagery

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

You can use this model to generate modernart style images

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.

One Step Closer to Reality

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

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.)

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.

A do (almost) anything model

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

This is a model of ancient Chinese style, and it also belongs to the model series with ink and water orientation

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

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

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

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

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

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

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

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.

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