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
![](https://tjzk.replicate.delivery/models_models_featured_image/779f3f58-c3db-4403-a01b-3ffed97a1449/out-0-1.jpg)
bytedance/sdxl-lightning-4step
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
![](https://tjzk.replicate.delivery/models_models_featured_image/710f5e9f-9561-4e4f-9d1e-614205f62597/stable-diffusion.webp)
stability-ai/stable-diffusion
A latent text-to-image diffusion model capable of generating photo-realistic images given any text input
![](https://tjzk.replicate.delivery/models_models_featured_image/9065f9e3-40da-4742-8cb8-adfa8e794c0d/sdxl_cover.jpg)
stability-ai/sdxl
A text-to-image generative AI model that creates beautiful images
![](https://replicate.delivery/pbxt/xs0pPOUM6HKmPlJJBXqKfE1YsiMzgNsCuGedlX0VqvPYifLgA/out-0.png)
stability-ai/stable-diffusion-inpainting
Fill in masked parts of images with Stable Diffusion
![](https://tjzk.replicate.delivery/models_models_featured_image/618e68d3-fba3-4fd0-a060-cdd46b2ab7cf/out-0_2.jpg)
ai-forever/kandinsky-2.2
multilingual text2image latent diffusion model
![](https://tjzk.replicate.delivery/models_models_featured_image/e58cec51-6215-4d30-8c03-80f3ea0994d0/einstein.png)
ai-forever/kandinsky-2
text2img model trained on LAION HighRes and fine-tuned on internal datasets
![](https://tjzk.replicate.delivery/models_models_featured_image/8629c6ba-b94c-4cbd-93aa-bda2b8ebecd9/F5Mg2KeXgAAkfre.jpg)
fofr/sdxl-emoji
An SDXL fine-tune based on Apple Emojis
![](https://replicate.delivery/pbxt/1nrcrEszpsb0Kpv0qNBJrtQjoefjHJ3xSh3whVOJcklSFxPSA/out-0.png)
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.
![](https://replicate.delivery/pbxt/XcklpSF1o7Z1I91xQQQHFvJfltWEa3HuQpoeVVTvN7GVJhffA/out-0.png)
tstramer/material-diffusion
Stable diffusion fork for generating tileable outputs using v1.5 model
![](https://tjzk.replicate.delivery/models_models_featured_image/859c8ec6-4046-4d4e-9826-b7b575e5b79f/cover.webp)
fofr/latent-consistency-model
Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet
![](https://tjzk.replicate.delivery/models_models_featured_image/82a7b2d0-d2bf-4ccd-bbe7-6a9ddbd44774/out-0-33.webp)
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
![](https://tjzk.replicate.delivery/models_models_featured_image/b849582a-8699-4965-8016-3a51dc1da3d4/playground.jpeg)
playgroundai/playground-v2.5-1024px-aesthetic
Playground v2.5 is the state-of-the-art open-source model in aesthetic quality
![](https://replicate.delivery/pbxt/oDtYIK2lDoaKMtdE4E5ozQSa61BU3gc4aRvGF3xmFpdwCxbE/out-0.png)
batouresearch/sdxl-controlnet-lora
'''Last update: Now supports img2img.''' SDXL Canny controlnet with LoRA support.
![](https://replicate.delivery/pbxt/mUtp8mKk8yI0EJ5olzsnpkeTbAcmy2OTEqnXXc8EFGLhhuEJA/out-0.png)
fofr/realvisxl-v3-multi-controlnet-lora
RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting
![](https://tjzk.replicate.delivery/models_models_featured_image/b7f3dda4-03ee-4dc0-b854-d8f740c153d6/cover.a1ee0b3e.jpg)
fofr/any-comfyui-workflow
Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui
![](https://tjzk.replicate.delivery/models_models_featured_image/fb7cf2ea-aacd-458d-9d19-76dda21f9748/sticker-maker.webp)
fofr/sticker-maker
Make stickers with AI. Generates graphics with transparent backgrounds.
![](https://tjzk.replicate.delivery/models_models_featured_image/e61adb01-bb73-448f-b2d5-3e8827577128/out-0.png)
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
![](https://replicate.delivery/pbxt/ILTzFdAenk1JLKVb7jZbEDUOUJGz7hSFFSArhCnxin7ICY8IA/out-0.png)
lucataco/realvisxl2-lcm
RealvisXL-v2.0 with LCM LoRA - requires fewer steps (4 to 8 instead of the original 40 to 50)
![](https://replicate.delivery/pbxt/eCTbwmWQ00UbQiZdRMfgLhTRIKFUkBPei9fOQ2taGKw3NpaHB/out-0.png)
lucataco/realvisxl-v2.0
Implementation of SDXL RealVisXL_V2.0
![](https://replicate.delivery/pbxt/GR5kmreA4fjf9JZIFh0GhIoEGEnJj6SmwYTszYVezXWm7EpHB/out-0.png)
fofr/sdxl-multi-controlnet-lora
Multi-controlnet, lora loading, img2img, inpainting
![](https://replicate.delivery/pbxt/VHFfxS2zJYVMVy4Itjzw4ChNdQtEah9wkcUvyPDcPud72eDSA/out-0.png)
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.
![](https://replicate.delivery/pbxt/7QcJQaHWyoqbDJxOHReq5UtphruA3RfbLvK1NhSYXVq7sXGSA/out-0.png)
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
![](https://replicate.delivery/pbxt/aOZ4ywUeyeiyqEz5l7lixq0e5rAbs3qTStetOGXNKZd4g6QEB/out-0.png)
ai-forever/kandinsky-2-1
Kandinsky 2.1 Diffusion Model
![](https://tjzk.replicate.delivery/models_models_featured_image/2ee23581-2653-483d-9d7c-69b1467b9168/out-0.png)
adirik/realvisxl-v3.0-turbo
Photorealism with RealVisXL V3.0 Turbo based on SDXL
![](https://tjzk.replicate.delivery/models_models_featured_image/4400b1ac-decf-472f-94de-29122df7ef32/6af357b1-11dc-4954-ad45-4f17b3.png)
nightmareai/disco-diffusion
Generate images using a variety of techniques - Powered by Discoart
![](https://replicate.delivery/pbxt/nSBVHLqeoD1KECVJ5OJSm90ihtI0zm4qeBvQ9ACZNMQUfg9jA/out-0.png)
lucataco/pixart-xl-2
PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system trained on text embeddings from T5
![](https://replicate.delivery/pbxt/koQLfGV4o8yWGi4reeIvJQwCxmxrD3S7iQFGre8IfISrpnCTC/out-0.png)
adirik/realvisxl-v4.0
Photorealism with RealVisXL V4.0
![](https://replicate.delivery/pbxt/C3LYYa30997dKRdeNDSXNjIK01CH5q8CSto12eWundnPPtWSA/out-0.png)
lucataco/proteus-v0.3
ProteusV0.3: The Anime Update
![](https://tjzk.replicate.delivery/models_models_cover_image/1fa674fa-a368-4c79-bb00-6cd39e6faac4/output.png)
lucataco/realistic-vision-v5
Realistic Vision v5.0 with VAE
![](https://replicate.delivery/pbxt/mfzcQjPBtjUCMaIKko5AqlwS6DL4VRB8DqBUq1fc8q8Bgy1RA/out-0.png)
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
![](https://replicate.delivery/pbxt/RekGnfLBwXkQjkgIk7mqxsn41IRtzyV25iZuxQF1k7FYvFPSA/out-0.png)
artificialguybr/nebul.redmond
Nebul.Redmond - Stable Diffusion SD XL Finetuned Model
![](https://replicate.delivery/pbxt/jPiwHtgNYgrFPtoXfJeeWKiDRX6sGfyCp3c8yXEZBobevNASC/ComfyUI_00001_.png)
fofr/txt2img
Many models: RealVisXL, Juggernaut, Proteus, DreamShaper, etc.
![](https://replicate.delivery/pbxt/aYXKkkuCWM6WN96DfeKBlVFTle875XmLLmMkJFp7rkNryqfHB/0.png)
adirik/kosmos-g
Kosmos-G: Generating Images in Context with Multimodal Large Language Models
![](https://replicate.delivery/pbxt/cj5eFwQqZPwROSKox75sbAVEJvfs58GX2Tswlu5tYzWwdLKSA/out-0.png)
lucataco/sdxl-deepcache
SDXL using DeepCache
![](https://replicate.delivery/pbxt/BdCKezxEeWgtLEtRdeCKrgyMg6ekeEFv8XYcM1khNUfgf1ffjA/out-0.png)
lucataco/playground-v2
Playground v2 is a diffusion-based text-to-image generative model trained from scratch. Try out all 3 models here
![](https://replicate.delivery/pbxt/09z14i0H7QZhDtBvCnC1WtH05GpU60ZEliQ3ZNRW4WqEf9fRA/output1.png)
adirik/masactrl-sdxl
Editable image generation with MasaCtrl-SDXL