Skip to content

Models

The API provides access to several text-to-image models, each with its own strengths and weaknesses. There are two main categories: generalist models and finetuned models.

  • Generalist models can generate a wide range of images from various domains, including photography and digital art in different styles and subjects.
  • Finetuned models, on the other hand, are specialized models that have been trained to perform particularly well in a specific domain (ex: anime, photorealism, 3D renders, ...)

This article presents examples of image generation using different models. Please note that while some models may appear to perform better based on these examples, it is possible that other models may perform better with different prompts. As one image is not enough to represent the entirety of a model's capabilities, it is up to you to determine which models are most suitable for your use case based on your own judgment.

Native resolutions

Each model is associated to what is called its "native resolution". This is the resolution at which the model was trained, and the resolution at which it will perform best.

You can request images at any resolution, regardless of the native resolution of the model, smaller or larger. But the further you stray from the native resolution, the more the image may be degraded. For example, with very large resolutions, the image may lack coherence and the subject may be duplicated.

That being said, small deviations from the native resolution are usually fine.

Trigger prompts

Some models were trained to respond to particular "trigger prompts", which means that to activate their unique capabilities, you will need to include this trigger in your prompt, preferably towards the beginning.

Since the API offers you direct access to each model, you have the choice whether to include the trigger words in your prompt or not.

  • some models like openjourney work well at generating the intended style without any trigger word (and just "amplify" the style if the words are included).
  • most models require it
  • some models might even offer multiple trigger words to choose from, offering multiple style variations. (like synthwavepunk_v2)

But generally speaking, we recommend to always include the trigger words in your prompt, at the beginning.

If the trigger contains *subject*, it is recommended to replace this by your intended subject. For example if the trigger is RAW photo, *subject*, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, and you want to generate an image of a dog playing catch,

then your final prompt should be RAW photo, dog playing catch, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3

Model metadata API

You can programmatically request the list of available models and their metadata using the following API endpoint: GET /info

The response will be a JSON object, with the models listed in the models property, in the following format:

  • id: the model ID, which you will need to use in your API requests
  • name: the human-readable name of the model
  • family: this defines the model's architecture (ex: sd1, sd2, sdxl)
  • license: the license under which the model is distributed
  • description: a short description of the model
  • categories: a list of categories that the model belongs to
  • function: a list of endpoints that the model supports (for example, most models are available with text2image and image2image, and the inpainting models are only available with inpainting)
  • nativeResolution: {"width": ..., "height": ...}: the native resolution of the model
  • triggers: a list of trigger prompts that the model supports, or null if the model does not support triggers

Models (Stable Diffusion XL)

Example image Model ID Description Native resolution Available Triggers
bluepencilxl_1024px High-resolution anime pictures 1024x1024 n/a
dreamshaperxl_1024px High-resolution generalist model with the quality “dreamshaper” style 1024x1024 n/a
juggernautxl_1024px High-resolution photorealistic pictures 1024x1024 n/a
juggernautxl_rundiffusion_8_1024px High-resolution photorealistic pictures 1024x1024 n/a
sdxl_1024px High-resolution generalist model 1024x1024 n/a
tshirtdesignredmond_1024px Generate awesome tshirt designs! 1024x1024 "TshirtDesignAF"

Models (Stable Diffusion)

Example image Model ID Description Native resolution Available Triggers
absolute_reality_1 Generate high-quality realistic pictures 512x512 n/a
absolute_reality_1_6 Generate high-quality realistic pictures 512x512 n/a
absolute_reality_1_8_1 Generate high-quality realistic pictures 512x512 n/a
absolute_reality_1_8_1_inpaint A generalist inpainting model 512x512 n/a
abyss_orange_mix_2 An AI model capable of generating high-quality, highly realistic illustrations. It can generate elaborate and detailed illustrations that cannot be drawn by hand. It can also be used for a variety of purposes, making it extremely useful for design and artwork. 512x512 n/a
analog_diffusion Analog photographs 512x512 "analog style"
analogmadness_7 Generate high-quality realistic pictures 512x512 n/a
anylora A model with a style neutral enough to get accurate styles with any style LoRA. 512x512 n/a
anything_3_0 Very versatile high-quality anime style generator 512x512 n/a
anything_4_0 This model is intended to produce high-quality, highly detailed anime style with just a few prompts. Like other anime-style Stable Diffusion models, it also supports danbooru tags to generate images. 512x512 n/a
anything_4_5_inpaint An inpainting model specialized for anime 512x512 n/a
anything_5_0 Very versatile high-quality anime style generator 512x512 n/a
basil_mix 512x512 n/a
blood_orange_mix Generate high-quality anime images 512x512 n/a
cyberrealistic_1_3 Generate realistic photos 512x512 n/a
cyberrealistic_3_1 Generate high-quality realistic pictures 512x512 n/a
cyberrealistic_3_3 Generate high-quality realistic pictures 512x512 n/a
cyberrealistic_3_3_inpaint A generalist inpainting model 512x512 n/a
deliberate This model provides you the ability to create anything you want using very detailed prompts. 512x512 n/a
deliberate_2 This model provides you the ability to create anything you want using very detailed prompts. 512x512 n/a
dh_classicanime A model finetuned on retro anime images 512x512 n/a
disco_diffusion_style Imitate the style of the Disco Diffusion AI 512x512 "a photo of ddfusion style"
double_exposure_diffusion Creates double exposure photography 512x512 "dublex style"
dreamix_1 This model was made to make awesome stylish 3d characters 512x512 n/a
dreamshaper Generate high-quality digital paintings 512x512 n/a
dreamshaper_5 Generate high-quality digital paintings 512x512 n/a
dreamshaper_6 Generate high-quality digital paintings 512x512 n/a
dreamshaper_7 Generate high-quality digital paintings 512x512 n/a
dreamshaper_8 Generate high-quality digital paintings 512x512 n/a
dreamshaper_8_inpaint A generalist inpainting model 512x512 n/a
duchaiten_anime Generate anime images with a subtle 3D effect 512x512 n/a
duchaiten_darkside DucHaitenDarkside is the dark side version of DucHaitenAIart, it does well with images with heavy atmosphere, as well as being able to create dramatic images like in the movies. 512x512 n/a
duchaiten_dreamworld Generate anime images with a subtle 3D effect 512x512 n/a
eimis_anime_diffusion_1 High-quality and detailed anime images 512x512 n/a
ely_orange_mix Generate high-quality anime images 512x512 n/a
emoji_diffusion Emoji’s 512x512 "emoji"
epic_diffusion_1 General purpose model focused on providing high quality output in a wide range of different styles, 512x512 n/a
epic_diffusion_1_1 General purpose model focused on providing high quality output in a wide range of different styles, 512x512 n/a
foto_assisted_diffusion Photorealistic modern HDR photography style 512x512 n/a
furrytoonmix A model specialized to generate furry characters 512x512 n/a
future_diffusion High quality 3D images with a futuristic Sci-Fi theme. 512x512 "future style"
hasdx General purpose model for realistic images / photography / portraits 512x512 n/a
icbinp Generate high-quality realistic pictures 512x512 n/a
icbinp_seco Generate high-quality realistic pictures 512x512 n/a
icbinp_seco_inpaint A generalist inpainting model 512x512 n/a
iconsmi_appiconsmodelforsd Mobile app icons 512x512 "IconsMi"
inkpunk_diffusion Ink drawings in cyberpunk style 512x512 "nvinkpunk"
instruct_pix2pix General instruction-following image model 512x512 n/a
kidsmix Beautiful drawings to illustrate children's stories 512x512 n/a
lowpoly_world Generate small low poly worlds 512x512 "a photo of lowpoly_world"
nightmareshaper Welcome to Unstable Diffusers a collection of checkpoints where limitations cease to exist, and creativity knows no bounds. This checkpoint defies restrictions and empowers you to generate anything your imagination desires 512x512 n/a
openjourney Model fine tuned on the Midjourney style 512x512 "mdjrny-v4 style"
openjourney_2 Model fine tuned on the Midjourney style 512x512 n/a
openniji Generate anime images 512x512 n/a
paint_journey_2_768px Oil paintings artwork characterized by intricate details, vibrant colors, and light that brings artwork to life. 768x768 "((oil painting))"
papercut Images of paper cut art 512x512 "mdjrny-pprct"
pastel_mix This model is made with the thought of imitating pastel-like art. 512x512 n/a
portrait_plus A model specialized to produce consistent portrait composition and consistent eyes. 512x512 "portrait+ style"
realcartoon3d_13 Generate high-quality digital paintings 512x512 n/a
realcartoonanime_10 High-resolution anime pictures 512x512 n/a
realdream_12 Generate high-quality realistic pictures 512x512 n/a
realistic_vision_1_3 Generate realistic photos 512x512 "RAW photo, *subject*, high detailed skin, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"
realistic_vision_5_1 Generate high-quality realistic pictures 512x512 n/a
realistic_vision_5_1_inpaint A generalist inpainting model 512x512 n/a
redshift_diffusion High resolution 3D artworks in the style of Cinema4D’s Redshift rendering engine 512x512 "redshift style"
redshift_diffusion_768px High resolution 3D artworks in the style of Cinema4D’s Redshift rendering engine 768x768 "redshift style"
rpg_5 This model focuses on stylistic RPG game portraits & characters. 512x512 n/a
something_2 This model is intended to produce vibrant but soft anime style images. 512x512 n/a
stable_diffusion_fluidart Create images with stylish fluid art 512x512 "FluidArt"
stable_diffusion_papercut Images of paper cut art 512x512 "PaperCut"
stable_diffusion_voxelart Create images with voxel art 512x512 "VoxelArt"
stablediffusion_1_4 A generalist Stable Diffusion model 512x512 n/a
stablediffusion_1_5 A generalist Stable Diffusion model 512x512 n/a
stablediffusion_2_0_512px A generalist Stable Diffusion model 512x512 n/a
stablediffusion_2_0_768px A generalist Stable Diffusion model tuned for images of at least 768 pixels. 768x768 n/a
stablediffusion_2_1_512px A generalist Stable Diffusion model 512x512 n/a
stablediffusion_2_1_768px A generalist Stable Diffusion model tuned for images of at least 768 pixels. 768x768 n/a
stablediffusion_inpaint_1 A generalist inpainting model 512x512 n/a
stablediffusion_inpaint_2 A generalist inpainting model 512x512 n/a
steampunk_diffusion Specialized for steampunk-style images 512x512 "Steampunk-Character"
synthwavepunk_v2 Cyperpunk / Synthwave style 512x512 "snthwve style" "nvinkpunk"
texture_diffusion Flat diffuse textures with very little visible lighting/shadows. 512x512 "pbr"
toonify_2 Toonify is an excellent model if you're looking for cartoonish renders. 512x512 n/a
trinart_2_0 Generate anime images 512x512 n/a
tshirt_diffusion Stunning designs intended to be printed on t-shirts 512x512 "(as a t-shirt logo in the style of <magifactory> art)"
vectorartz_diffusion Generate beautiful vector illustration 512x512 "vectorartz"
vintedois_diffusion_v0_1 Beautiful images with simple prompts 512x512 "estilovintedois"
vox_2 Objects made out of voxels 512x512 "voxel-ish"
waifudiffusion_1_3 Anime images using danbooru tags 512x512 n/a
waifudiffusion_1_4 High-quality anime images 512x512 n/a
yesmix_4 Anime style images 512x512 n/a