Collections

Generate images

These models generate images from text prompts. Many of these models are based on Stable Diffusion.

Read our guide to learn more about using Stable Diffusion.

Models we recommend

stability-ai/stable-diffusion

A latent text-to-image diffusion model capable of generating photo-realistic images given any text input

107.1M runs

stability-ai/sdxl

A text-to-image generative AI model that creates beautiful images

40.5M runs

stability-ai/stable-diffusion-inpainting

Fill in masked parts of images with Stable Diffusion

16.1M runs

ai-forever/kandinsky-2.2

multilingual text2image latent diffusion model

7.5M runs

ai-forever/kandinsky-2

text2img model trained on LAION HighRes and fine-tuned on internal datasets

5.8M runs

fofr/sdxl-emoji

An SDXL fine-tune based on Apple Emojis

3.3M runs

tstramer/material-diffusion

Stable diffusion fork for generating tileable outputs using v1.5 model

2M runs

fofr/latent-consistency-model

Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet

653.3K runs

lucataco/ssd-1b

Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of SDXL, offering a 60% speedup while maintaining high-quality text-to-image generation capabilities

651.5K runs

batouresearch/sdxl-controlnet-lora

'''Last update: Now supports img2img.''' SDXL Canny controlnet with LoRA support.

248.9K runs

lucataco/realvisxl-v2.0

Implementation of SDXL RealVisXL_V2.0

208.3K runs

playgroundai/playground-v2-1024px-aesthetic

Playground v2 is a diffusion-based text-to-image generative model trained from scratch by the research team at Playground

191.9K runs

lucataco/realvisxl2-lcm

RealvisXL-v2.0 with LCM LoRA - requires fewer steps (4 to 8 instead of the original 40 to 50)

181.7K runs

fofr/sdxl-multi-controlnet-lora

Multi-controlnet, lora loading, img2img, inpainting

115.4K runs

lucataco/proteus-v0.2

Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.

113.1K runs

lucataco/sdxl-lightning-4step

SDXL-Lightning by ByteDance, is a fast text-to-image model that makes high-quality images in 4 steps

91.9K runs

ai-forever/kandinsky-2-1

Kandinsky 2.1 Diffusion Model

79.7K runs

fofr/realvisxl-v3-multi-controlnet-lora

RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting

78.6K runs

lucataco/dreamshaper-xl-turbo

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

67.6K runs

lucataco/open-dalle-v1.1

A unique fusion that showcases exceptional prompt adherence and semantic understanding, it seems to be a step above base SDXL and a step closer to DALLE-3 in terms of prompt comprehension

66.6K runs

nightmareai/disco-diffusion

Generate images using a variety of techniques - Powered by Discoart

63.8K runs

lucataco/pixart-xl-2

PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system trained on text embeddings from T5

34.1K runs

fofr/any-comfyui-workflow

Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui

29.2K runs

adirik/realvisxl-v3.0-turbo

Photorealism with RealVisXL V3.0 Turbo based on SDXL

26.9K runs

lucataco/thinkdiffusionxl

ThinkDiffusionXL is a go-to model capable of amazing photorealism that's also versatile enough to generate high-quality images across a variety of styles and subjects without needing to be a prompting genius

10.9K runs

artificialguybr/nebul.redmond

Nebul.Redmond - Stable Diffusion SD XL Finetuned Model

6.8K runs

lucataco/realistic-vision-v5

Realistic Vision v5.0 with VAE

6.7K runs

lucataco/proteus-v0.3

ProteusV0.3: The Anime Update

5.5K runs

fofr/txt2img

Many models: RealVisXL, Juggernaut, Proteus, DreamShaper, etc.

4.9K runs

lucataco/playground-v2.5-1024px-aesthetic

State-of-the-art text to image

4.3K runs

lucataco/sdxl-deepcache

SDXL using DeepCache

2.8K runs

adirik/masactrl-sdxl

Editable image generation with MasaCtrl-SDXL

2.7K runs

adirik/kosmos-g

Kosmos-G: Generating Images in Context with Multimodal Large Language Models

2.1K runs

adirik/realvisxl-v4.0

Photorealism with RealVisXL V4.0

1.9K runs

lucataco/playground-v2

Playground v2 is a diffusion-based text-to-image generative model trained from scratch. Try out all 3 models here

1.7K runs