Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

Sketchy DreamS v2

Components were retrained as a Dreambooth, took a while, but hey, gotta do what you gotta do for that edge in quality e_e

SketchyDreamS Rev2 (SDS Rev2)

Updated recipe of SDS, less damaging to understanding, so it follows prompt better.

It is less suitable for expressive sketches and lineart, if you want them - use first version.

S12 used is v4.6.2, trained on 768 reso.

While it is less abstract and expressive, it is capable of more sophisticated composition, because it doesn't get garbled up in sketchy stuff that would make trypophobes delete this model immediately.

SketchyDreamS (SDS)

Overhaul, rather than a direct continuation of ElusiveDreamS. Respects anime style much better, increased compatibility with loras, etc, etc.

I love how it works with sketchy styles, well, that was one of the points when i made it.

It utilizes Dreamwave v2 and Sketchy(unreleased) loras, + polishing by S12.

ElusiveDreamS (EDS)

This model is a sort of continuation of ACMAR G Mix, as this is it, but spiced up with 3 trainings on top of it, combined using deep merge in 3 steps.

S3Full - Full merge of S12 on OUT0-11. Might have less leak, more abstraction, and a bit better control, but will surely have higher presence of various particles. Requires stron negative on (3d, realistic) to produce flat, or positive flat color.

S3Half - Half merge of S12 on OUT0-11. Might have less control, but will be less leaky in abstraction, i think. Doesn't demand negative (3d, realistic) to say 2.5d/anime.

Highlights

Usually quite aesthetically pleasing.

Partially capable of high level understanding of combination of various concepts, thanks to S12 being a cherry on top of this. + Possibility of high level of compositional abstraction.

Absolutely fire sketchy look, imho.

Refer to S12 for possible new capabilities.

Downsides

```Note: downsides are not stacked, but unique for each model, so read only section for one you're choosing.```

SDS rev2:

Honestly, not much. Solid model that is now my favorite for generating wide variety of semi-abstract things, or unique compositions.

It might be too abstract and a bit unstable compared to common models, but other than that it's very solid.

SDS:

Meant for extremely sketchy things, so low-level(small) details are lost in most cases, and attempts at detailed background are met with abstract walls of color.

EDS:

Quite rigid by default, so you will need to use more detailed prompts, which most of you already do anyway.

Is biased towards female characters, so you'll have to increase weight, and/or put appropriate tags in negative to have consistent male output.

Bias towards flowers. While they are aesthetically pleasing, sometimes you don't want them. Use nagative flowers for that.

Possibly could be hard to adapt to loras, but that needs testing.

Best used for 2.5, or 2d, as it's a bit f'ed up in terms of faces, if you promt realistic, 3d

TLDR Information

This model is based on ACMAR G Mix, and both EDS and SDS contain 3 additional trainings, which were added through deep merge technique:
EDS: Dreamwave(Full), ElusiveWorld, S12(4.2 NAI)

SDS: Dreamwave(v2), Sketchy(unreleased), S12(4.2 NAI)

SDS rev2: Dreamwave(v2), Sketchy(unreleased), S12(4.6.2, unreleased)

EDS: Dreamwave and Elusive are used for dreamy looks and aestethics, while S12 is a polisher on top, that adds conceptual understanding. It is merged at very high percentages at some, and with gradual stepping on rest to stabilize style at anime, rather than what Dreamwave and Elusive look like, while adding control over output style.

SDS: Sketchy and v2 Dreamwave provide exceptional sketchy look, if you want to get it. That model excels at such. It is, however, not good at deep details, as they are going to get lost in sketchy style. Fixed in rev 2, but sketchy no more.

Images Generated With This Model

cinematic, interdimensional (female:0.5) creature, biomechanical ghost, mesmerizing visual puzzle, hyper-detailed, artistic style, neural network, bioluminescent
N/A
Hidden For Public Users
cinematic, interdimensional (female:0.5) creature, biomechanical ghost, mesmerizing visual puzzle, hyper-detailed, artistic style, neural network, bioluminescent
Abandoned haunted carnival Beautiful goblin woman portrait wearing blue, elaborate updo hairstyle, auburn hair, adorned, 16K, UHD, HDR, Silent rides, eerie lights, fog, overgrown, spooky vibe
N/A
Hidden For Public Users
Abandoned haunted carnival Beautiful goblin woman portrait wearing blue, elaborate updo hairstyle, auburn hair, adorned, 16K, UHD, HDR, Silent rides, eerie lights, fog, overgrown, spooky vibe
masterpiece, best quality, 1girl, flowers, flat color, lineart, dreamwave, aesthetic
N/A
Hidden For Public Users
masterpiece, best quality, 1girl, flowers, flat color, lineart, dreamwave, aesthetic
a large circle of a person above a tree in an image, in the style of vibrant fantasy landscapes, teal and bronze, energy-filled illustrations, hikecore, sublime wilderness, poster art, i can't believe how beautiful this is
N/A
Hidden For Public Users
a large circle of a person above a tree in an image, in the style of vibrant fantasy landscapes, teal and bronze, energy-filled illustrations, hikecore, sublime wilderness, poster art, i can't believe how beautiful this is
lush vegetation inside a huge sci-fi space station, trees with roots braid the walls, vegetation, gigantism, sci-fi multistory space, in the background of endless space, location, dusk, dystopian environment, game art, Tsutomu Nihei style, Blame!, Sidonia no Kishi, anime, manga graphics, drawing, lots of small details, hyperdetail, highest quality, highest detail, flashing lighting, ambient lighting, third person view, 8K, Ultra-HD, Optical Fiber, no Person, no humans
N/A
Hidden For Public Users
lush vegetation inside a huge sci-fi space station, trees with roots braid the walls, vegetation, gigantism, sci-fi multistory space, in the background of endless space, location, dusk, dystopian environment, game art, Tsutomu Nihei style, Blame!, Sidonia no Kishi, anime, manga graphics, drawing, lots of small details, hyperdetail, highest quality, highest detail, flashing lighting, ambient lighting, third person view, 8K, Ultra-HD, Optical Fiber, no Person, no humans
([balloons:Small planets:0.5]:1.4), (Small_planets inside of balloons:1.4), (lots of colorful Small_planets:1.35), (colorful planets, earth, floating petals, big balloons:1.22), 1 girl, cute face, Full body, sitting, detailed beautiful eyes, bare legs, costume combination, Goddess, perfect body, [nsfw:0.88], (sitting on ice_planet:1.22), (lots of [floting blue Butterflies:floting ice:0.4]:1.22), (detailed light), (an extremely delicate and beautiful), volume light, best shadow, cinematic lighting, Depth of field, dynamic angle, Oily skin
N/A
Hidden For Public Users
([balloons:Small planets:0.5]:1.4), (Small_planets inside of balloons:1.4), (lots of colorful Small_planets:1.35), (colorful planets, earth, floating petals, big balloons:1.22), 1 girl, cute face, Full body, sitting, detailed beautiful eyes, bare legs, costume combination, Goddess, perfect body, [nsfw:0.88], (sitting on ice_planet:1.22), (lots of [floting blue Butterflies:floting ice:0.4]:1.22), (detailed light), (an extremely delicate and beautiful), volume light, best shadow, cinematic lighting, Depth of field, dynamic angle, Oily skin
masterpiece, best quality, intricate details, glamour shot of upper body of a woman with white hair (detailed face) wearing a dress in church, style-swirlmagic, (vivid colors:1.3), (sharp focus, realistic:1.3), (extremely complex:1 2) intricate and fine details, her long iridescent white hair is coiled into a bun, surrounded by fiery swirling magic
N/A
Hidden For Public Users
masterpiece, best quality, intricate details, glamour shot of upper body of a woman with white hair (detailed face) wearing a dress in church, style-swirlmagic, (vivid colors:1.3), (sharp focus, realistic:1.3), (extremely complex:1 2) intricate and fine details, her long iridescent white hair is coiled into a bun, surrounded by fiery swirling magic
[skeleton:1girl:0.9](3d model of a girl with a sugar skull head:1.1), in the style of inventive character designs, close-up intensity, animated gifs, made of flowers, (mexican muralism:1.2), playstation 5 screenshot, dark violet and white
N/A
Hidden For Public Users
[skeleton:1girl:0.9](3d model of a girl with a sugar skull head:1.1), in the style of inventive character designs, close-up intensity, animated gifs, made of flowers, (mexican muralism:1.2), playstation 5 screenshot, dark violet and white
Aroma diffuser, inspired by the grandeur and opulence of the Palace of Versailles, with a golden metal exterior and intricate floral engravings, detailed, in style of artstation, digital art, hyper detailed, hyper realistic, white background, unreal engine, png 8K, depth of field
N/A
Hidden For Public Users
Aroma diffuser, inspired by the grandeur and opulence of the Palace of Versailles, with a golden metal exterior and intricate floral engravings, detailed, in style of artstation, digital art, hyper detailed, hyper realistic, white background, unreal engine, png 8K, depth of field
(olis, sharp:1.2),(masterpiece:1), (best quality:1),1girl, flowers, (blue theme:1.2), (powerful:1), high contrast
N/A
Hidden For Public Users
(olis, sharp:1.2),(masterpiece:1), (best quality:1),1girl, flowers, (blue theme:1.2), (powerful:1), high contrast
masterpiece, best quality, 1girl,  flowers, (lineart, sketch:1.3)
N/A
Hidden For Public Users
masterpiece, best quality, 1girl, flowers, (lineart, sketch:1.3)
masterpiece, best quality, retro car, powerful, fire, splash art, (black background:1.4)
N/A
Hidden For Public Users
masterpiece, best quality, retro car, powerful, fire, splash art, (black background:1.4)

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.