Generate images

These models generate images from text prompts. Many of these models are based on Stable Diffusion and FLUX.1.

Learn more about the latest FLUX.1 Kontext.

Our Picks

Best overall image generation model: bytedance/seedream-3

The best overall image generation model is bytedance/seedream-3. It offers state-of-the-art performance in prompt following, visual quality, image detail, and output diversity.

Best fast image generation model: black-forest-labs/flux-schnell

Use this fast version of black-forest-labs/flux-schnell when speed and cost are more important than quality

Best model for generating images with text: ideogram-ai/ideogram-v3-turbo

Ideogram models are strong in many areas, but they’re especially known for their ability to generate realistic, legible text. See our blog on Ideogram v3.

Best model for generating images with SVGs: recraft-ai/recraft-v3-svg

The Recraft V3 SVG model is the first major text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.

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 fine-tunes

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

Featured models

fofr / any-comfyui-workflow

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

Updated 4 days, 14 hours ago

6.3M runs

google / imagen-4-fast

Use this fast version of Imagen 4 when speed and cost are more important than quality

Updated 2 weeks ago

209.1K runs

bytedance / seedream-3

A text-to-image model with support for native high-resolution (2K) image generation

Updated 1 month, 1 week ago

267.7K runs

black-forest-labs / flux-schnell

The fastest image generation model tailored for local development and personal use

Updated 1 month, 1 week ago

426.5M runs

ideogram-ai / ideogram-v3-turbo

Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles

Updated 3 months ago

606.6K runs

recraft-ai / recraft-v3-svg

Recraft V3 SVG (code-named red_panda) is a text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.

Updated 4 months, 1 week ago

193.6K runs

Recommended models

luma / photon-flash

Accelerated variant of Photon prioritizing speed while maintaining quality

Updated 1 week ago

127.5K runs

prunaai / flux.1-dev

This is the fastest Flux Dev endpoint in the world, contact us for more at pruna.ai

Updated 1 week ago

11.6M runs

black-forest-labs / flux-kontext-max

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts

Updated 1 week, 1 day ago

3.4M runs

black-forest-labs / flux-kontext-pro

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language

Updated 1 week, 1 day ago

12.6M runs

nvidia / sana-sprint-1.6b

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Updated 1 week, 2 days ago

630.6K runs

google / imagen-4-ultra

Use this ultra version of Imagen 4 when quality matters more than speed and cost

Updated 2 weeks ago

180.5K runs

google / imagen-4

Google's Imagen 4 flagship model

Updated 2 weeks ago

1.4M runs

google / imagen-3-fast

A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality

Updated 2 weeks ago

292.4K runs

google / imagen-3

Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty

Updated 2 weeks ago

1.3M runs

prunaai / wan-image

This model generates beautiful cinematic 2 megapixel images in 3-6 seconds and is derived from the wan2.1 model through optimisation techniques from the pruna package

Updated 2 weeks, 1 day ago

11.6K runs

bria / image-3.2

Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market

Updated 2 weeks, 2 days ago

1.4K runs

prunaai / hidream-l1-full

This is an optimised version of the hidream-full model using the pruna ai optimisation toolkit!

Updated 2 weeks, 6 days ago

26.2K runs

prunaai / hidream-l1-dev

This is an optimised version of the hidream-l1-dev model using the pruna ai optimisation toolkit!

Updated 2 weeks, 6 days ago

37.3K runs

prunaai / hidream-l1-fast

This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!

Updated 2 weeks, 6 days ago

1.7M runs

black-forest-labs / flux-dev-lora

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

Updated 1 month, 1 week ago

3.5M runs

black-forest-labs / flux-dev

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

Updated 1 month, 1 week ago

23.3M runs

prunaai / sdxl-lightning

This is the fastest sdxl-lightning endpoint in the world on A100, contact us for more at pruna.ai

Updated 1 month, 3 weeks ago

266 runs

ideogram-ai / ideogram-v3-balanced

Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles

Updated 3 months ago

138.4K runs

ideogram-ai / ideogram-v3-quality

The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles

Updated 3 months ago

391.5K runs

minimax / image-01

Minimax's first image model, with character reference support

Updated 3 months, 1 week ago

1.1M runs

black-forest-labs / flux-1.1-pro-ultra

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.

Updated 4 months ago

15.5M runs

black-forest-labs / flux-1.1-pro

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.

Updated 4 months ago

46.7M runs

black-forest-labs / flux-pro

State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.

Updated 4 months ago

12.6M runs

recraft-ai / recraft-v3

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis

Updated 4 months, 1 week ago

4.6M runs

bytedance / sdxl-lightning-4step

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

Updated 4 months, 2 weeks ago

1B runs

ideogram-ai / ideogram-v2a-turbo

Like Ideogram v2 turbo, but now faster and cheaper

Updated 5 months ago

326.5K runs

ideogram-ai / ideogram-v2a

Like Ideogram v2, but faster and cheaper

Updated 5 months ago

1.1M runs

nvidia / sana

A fast image model with wide artistic range and resolutions up to 4096x4096

Updated 7 months, 3 weeks ago

170.8K runs

luma / photon

High-quality image generation model optimized for creative professional workflows and ultra-high fidelity outputs

Updated 7 months, 3 weeks ago

1.6M runs

stability-ai / stable-diffusion-3.5-medium

2.5 billion parameter image model with improved MMDiT-X architecture

Updated 9 months ago

61.2K runs

stability-ai / stable-diffusion-3.5-large-turbo

A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps

Updated 9 months, 1 week ago

699.9K runs

stability-ai / stable-diffusion-3.5-large

A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.

Updated 9 months, 1 week ago

1.6M runs

ideogram-ai / ideogram-v2-turbo

A fast image model with state of the art inpainting, prompt comprehension and text rendering.

Updated 9 months, 1 week ago

2.4M runs

ideogram-ai / ideogram-v2

An excellent image model with state of the art inpainting, prompt comprehension and text rendering

Updated 9 months, 1 week ago

1.7M runs

stability-ai / sdxl

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

Updated 1 year, 2 months ago

81M runs

fofr / sticker-maker

Make stickers with AI. Generates graphics with transparent backgrounds.

Updated 1 year, 3 months ago

1.3M runs

ai-forever / kandinsky-2

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

Updated 1 year, 3 months ago

6.2M runs

ai-forever / kandinsky-2.2

multilingual text2image latent diffusion model

Updated 1 year, 3 months ago

10M runs

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

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

Updated 1 year, 4 months ago

2.6M runs

datacte / proteus-v0.3

ProteusV0.3: The Anime Update

Updated 1 year, 5 months ago

4.2M runs

fermatresearch / sdxl-controlnet-lora

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

Updated 1 year, 6 months ago

929K runs

datacte / 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.

Updated 1 year, 6 months ago

10.4M runs

adirik / realvisxl-v3.0-turbo

Photorealism with RealVisXL V3.0 Turbo based on SDXL

Updated 1 year, 6 months ago

378.4K runs

fofr / latent-consistency-model

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

Updated 1 year, 6 months ago

1.5M runs

fofr / realvisxl-v3-multi-controlnet-lora

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

Updated 1 year, 6 months ago

1.8M 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

Updated 1 year, 7 months ago

128.4K runs

fofr / sdxl-multi-controlnet-lora

Multi-controlnet, lora loading, img2img, inpainting

Updated 1 year, 7 months ago

212.2K 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.

Updated 1 year, 7 months ago

224.5K 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

Updated 1 year, 8 months ago

1M runs