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.

  • Text-to-image - Convert text prompts to photorealistic images. Useful for quickly visualizing concepts
  • Control over style - Adjust image properties like lighting and texture via prompts
  • In-painting - Expand, edit, or refine images by filling in missing regions

Our Picks

Best overall image generation model: stability-ai/sdxl

The best overall image generation model is stability-ai/sdxl. It supports LoRA fine-tuning, which means you can customize the model to produce specific styles or subjects. For more information about how to fine-tune SDXL, read our detailed guide about fine-tuning Stable Diffusion

Best ComfyUI model: fofr/any-comfyui-workflow

If you’re a fan of ComfyUI, you can export any of your favorite ComfyUI workflows to JSON and run them on Replicate using the fofr/any-comfyui-workflow model. For more information, check out our detailed guide to using ComfyUI.

Best fast image generation model: lucataco/sdxl-lightning-4step

The best-looking fast image generation model is lucataco/sdxl-lightning-4step, it will spit out an image in 1.6 seconds. The fastest image generation model is fofr/latent-consistency-model which will generate an image in 0.6 seconds.

Best fine-tunes

Make sure to check out our SDXL fine-tunes collection, which includes all publicly available SDXL fine-tunes hosted on Replicate. This collection should help you get a feel for the sorts of things you can do with fine-tuning.

Recommended models


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

108M runs


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

64.3M runs


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

51.9M runs


Fill in masked parts of images with Stable Diffusion

16.8M runs


multilingual text2image latent diffusion model

9.2M runs


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

6.1M runs


An SDXL fine-tune based on Apple Emojis

4.4M runs


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

2.1M runs


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.

1.6M runs


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

929.5K runs


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

912.6K runs


Playground v2.5 is the state-of-the-art open-source model in aesthetic quality

444K runs


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

415.9K runs


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

301.3K runs


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

285.9K runs


Make stickers with AI. Generates graphics with transparent backgrounds.

268.8K runs


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

265.4K runs


Implementation of SDXL RealVisXL_V2.0

259.8K runs


Run any ComfyUI workflow. Guide:

241.3K runs


Multi-controlnet, lora loading, img2img, inpainting

173.8K runs


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.

123.4K runs


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

86.9K runs


Kandinsky 2.1 Diffusion Model

82.1K runs


Generate images using a variety of techniques - Powered by Discoart

64K runs


Photorealism with RealVisXL V3.0 Turbo based on SDXL

57.3K runs


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

42.1K runs


Photorealism with RealVisXL V4.0

16.5K runs


ProteusV0.3: The Anime Update

16.3K runs


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

13.3K runs


Realistic Vision v5.0 with VAE

12.2K runs


Nebul.Redmond - Stable Diffusion SD XL Finetuned Model

10.8K runs


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

8.1K runs


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

3.6K runs


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

3.2K runs


Editable image generation with MasaCtrl-SDXL

3.1K runs


SDXL using DeepCache

3.1K runs