Generate images

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

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

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

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

Google's latest image editing model in Gemini 2.5

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

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

This is the fastest Flux endpoint in the world.

Generate detailed images from scribbled drawings

Unified text-to-image generation and precise single-sentence editing at up to 4K resolution

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

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

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

Google's state of the art image generation and editing model 🍌🍌

An SDXL fine-tune based on Apple Emojis

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.

multilingual text2image latent diffusion model

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

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

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

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

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

Google's Imagen 4 flagship model

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

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

ProteusV0.3: The Anime Update

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

Implementation of Realistic Vision v5.1 with VAE

A sub 1 second text-to-image model built for production use cases.

Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge

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

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

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

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

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

Minimax's first image model, with character reference support

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

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

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

Like Ideogram v2, but faster and cheaper

Make stickers with AI. Generates graphics with transparent backgrounds.

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

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.

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

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.

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

This model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package

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

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

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

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

The highest fidelity image model from Black Forest Labs

Photorealism with RealVisXL V3.0 Turbo based on SDXL

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

Like Ideogram v2 turbo, but now faster and cheaper

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

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.

Accelerated variant of Photon prioritizing speed while maintaining quality

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

Artistic and high-quality visuals with improved prompt adherence, diversity, and definition

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.

Multi-controlnet, lora loading, img2img, inpainting

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

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

2.5 billion parameter image model with improved MMDiT-X architecture

A powerful native multimodal model for image generation (PrunaAI squeezed)

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

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

SOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.

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