AI Image Generation

Every image model we serve — FLUX, Stable Diffusion, Imagen, Ideogram, Recraft, Kling, and more. Text-to-image, image-to-image, editing, upscaling, background removal. From diffusion models to custom architectures. Real pricing from someone who's integrated them all.

Live data from 19 image providers — updated daily

Showing 88 of 88 image models

Blur Background

Blur Background

Blur the background behind the subject

Try on Zubnet →

SOTA open-source image model. Native Chinese text support, 6B parameters.

Try on Zubnet →

Bring black-and-white photos to natural color

Try on Zubnet →

Crop to Subject

Crop to Subject

Remove the background and crop tightly around the subject

Try on Zubnet →

Enhance image quality with AI

Try on Zubnet →

Erase Foreground

Erase Foreground

Remove the main subject and fill in the background

Try on Zubnet →

Paint over an object to remove it from the image

Try on Zubnet →

Expand image beyond its borders with AI outpainting

Try on Zubnet →

Bria's licensed-data model for text-to-image and controllable edits with up to four reference images or a single-image mask.

Try on Zubnet →

Black Forest Labs

The best of FLUX, offering state-of-the-art performance image generation at blazing fast speeds

Try on Zubnet →

FLUX 1.1 [pro/ultra]

FLUX 1.1 [pro/ultra]

Black Forest Labs

Ultra / Raw Modes. Ultra Fast, More Pixels

Try on Zubnet →

Black Forest Labs

FLUX 3 image generation: text-to-image, multi-reference editing with up to ten references, and bounding-box placement.

Try on Zubnet →

FLUX Kontext [max]

FLUX Kontext [max]

Black Forest Labs

A premium model brings maximum performance across all aspects – greatly improved quality, consistency, and speed

Try on Zubnet →

FLUX Kontext [pro]

FLUX Kontext [pro]

Black Forest Labs

A unified model delivering local editing, generative modifications, and text-to-image capabilities

Try on Zubnet →

Black Forest Labs

Directly distilled from FLUX.1 [pro], an open-weight, guidance-distilled model for non-commercial use

Try on Zubnet →

Black Forest Labs

Specialized for typography and text rendering with adjustable guidance and generation steps

Try on Zubnet →

FLUX.2 [klein/4B]

FLUX.2 [klein/4B]

Black Forest Labs

Ultra-fast open-source FLUX model optimized for real-time generation at the lowest cost. Apache 2.0 licensed.

Try on Zubnet →

FLUX.2 [klein/9B]

FLUX.2 [klein/9B]

Black Forest Labs

Fastest FLUX model with sub-second inference. 9B params with Qwen3 text embedder for superior prompt understanding.

Try on Zubnet →

Black Forest Labs

Highest quality FLUX 2.0 with grounding search capability for photorealistic images up to 4MP

Try on Zubnet →

Black Forest Labs

Production-grade FLUX 2.0 with multi-reference image editing and precise control over colors, poses, and composition

Try on Zubnet →

Transform reference images with text prompts. Preserves identity while changing pose, lighting, background.

Try on Zubnet →

Gen-4 Image Turbo

Gen-4 Image Turbo

Fast reference-based image generation. 2.5x faster, preserves identity and style.

Try on Zubnet →

Generative Fill

Generative Fill

Paint a mask and fill the area with AI-generated content

Try on Zubnet →

Z.ai's image generation model with strong prompt adherence and text rendering.

Try on Zubnet →

OpenAI's latest image generation model (high-quality tier).

textimageimageimage_edit

Try on Zubnet →

GPT Image 2.5 Flare

GPT Image 2.5 Flare

OpenAI's ChatGPT Images 2.5, fast variant: everyday generation at about half the latency of GPT Image 2.

textimageimageimage_edit

Try on Zubnet →

GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst

OpenAI's ChatGPT Images 2.5, precision variant: detailed creative work and editing fidelity, slower than Flare.

textimageimageimage_edit

Try on Zubnet →

Fast text-to-image generation from xAI. Standard quality, lowest cost.

Try on Zubnet →

Grok Imagine 2.0

Grok Imagine 2.0

xAI's current image model. Higher fidelity than Grok Imagine, with stronger prompt adherence.

Try on Zubnet →

Grok Imagine HQ

Grok Imagine HQ

Higher-fidelity Grok Imagine. Better prompt adherence and detail, 2.5x the cost.

Try on Zubnet →

Previous generation model. Still excellent for text rendering at lower cost.

Try on Zubnet →

State-of-the-art image generation with exceptional text rendering. Best balance of quality and speed.

Try on Zubnet →

Ideogram 3.0 Quality

Highest quality Ideogram 3.0. Maximum detail and fidelity for final outputs.

Try on Zubnet →

Ideogram 3.0 Turbo

Faster Ideogram 3.0 variant. Quick generation for iterative workflows.

Try on Zubnet →

Ideogram 4.0 text-to-image generation with the best text rendering. The rendering speed is the priced tier: Turbo, Default or Quality.

Try on Zubnet →

4.5 Precise Edit

Ideogram 4.5 Precise Edit

Precise image editing on Ideogram 4.5: the first uploaded image is edited from the prompt (a mask marks what to change), up to four reference images steer the result, and unedited pixels are kept from the original.

textimageimageimage_edit

Try on Zubnet →

Kling 2.1 Image

Kling 2.1 Image

High-quality text-to-image generation with multiple aspect ratios

Try on Zubnet →

Kling 3 image generation, text-to-image and image-to-image.

Try on Zubnet →

Kling 3 Omni unified image model, text-to-image, image-to-image, and image editing.

Try on Zubnet →

Unified image model for text-to-image, image-to-image, and detail editing. Accepts up to 10 reference images for guided generation. Part of the O1 multimodal family.

Try on Zubnet →

Leonardo Anime XL

Leonardo Anime XL

High-speed anime-focused model excelling at a range of anime styles.

Try on Zubnet →

Leonardo Kino XL

Leonardo Kino XL

Cinematic-focused model excelling at film-like compositions and lighting.

Try on Zubnet →

Leonardo Lightning XL

Leonardo Lightning XL

High-speed generalist image generation model for fast iteration.

Try on Zubnet →

Leonardo model for vibrant, diverse imagery in HD output.

Try on Zubnet →

Leonardo high-speed model designed for photorealistic outputs.

Try on Zubnet →

High-efficiency image generation, optimized for speed and high-volume use.

Try on Zubnet →

Nano Banana 2 Lite

Nano Banana 2 Lite

Efficiency specialist of the Nano Banana family — ultra-low-latency, cost-effective image generation and editing.

Try on Zubnet →

Nano Banana 2.1New

Nano Banana 2.1

Google's high-efficiency image generation and editing model — improved visual quality, typography, and multi-turn consistency; 1K/2K/4K. The unit rate is the 1K price, as with the rest of the family (#544).

Try on Zubnet →

Nano Banana Pro

Nano Banana Pro

Google's native image generation with text rendering and multimodal understanding.

Try on Zubnet →

Leonardo foundational model preview with extreme prompt adherence and versatility.

Try on Zubnet →

Leonardo flagship foundational model with exceptional prompt adherence and text rendering.

Try on Zubnet →

Pruna's optimized text-to-image: fast, high-quality generation.

Try on Zubnet →

Pruna Image Edit

Pruna's optimized image editing: transform an input image with a prompt.

Try on Zubnet →

Alibaba's flagship text-to-image model — successor to the whole Qwen-Image family, with strong prompt following and text rendering (native DashScope, Singapore).

Try on Zubnet →

Qwen Image 2.0 Pro

Qwen Image 2.0 Pro

The higher-fidelity "pro" tier of Alibaba's Qwen Image 2.0 — stronger prompt following and text rendering (native DashScope, Singapore).

Try on Zubnet →

Alibaba's Qwen Image 3.0 — the next generation of the Qwen text-to-image family: denser layouts, images within images, sharper small text, native rendering in 12 languages (native DashScope, Singapore).

Try on Zubnet →

Qwen Image 3.0 Pro

Qwen Image 3.0 Pro

The higher-fidelity pro tier of Alibaba's Qwen Image 3.0 — prompts up to 4.5k tokens, dense information layouts, precise text down to 10 px (native DashScope, Singapore).

Try on Zubnet →

Retro Diffusion

Retro Diffusion's quick pixel-art model (formerly RD Flux): 15 styles, from retro and portrait to 1-bit and Minecraft textures. Great for drafts and game assets. 64-384px; the low-res and Minecraft styles 16-128px.

Try on Zubnet →

Retro Diffusion

Retro Diffusion's all-rounder with the largest style library: watercolor, cartoon, isometric, top-down maps, skill icons and more. 64-384px; classic and skill icons 32-192px, the low-res styles smaller.

Try on Zubnet →

Retro Diffusion

Retro Diffusion's highest-quality pixel art: the cleanest pixel work and the closest prompt following, from 12px sprites to dungeon maps, typography and UI panels. Up to 256px; hexagonal tiles, UI panels and inventory sheets are 256x256.

Try on Zubnet →

Recraft V3 (Red Panda), text-to-image, and image-to-image that restyles one input image: describe the result you want, not the change. 1024x1024.

Try on Zubnet →

Recraft V3 Vector

Recraft V3 for vector graphics, SVG output, text-to-image, and image-to-image that restyles one input image: describe the result you want, not the change.

Try on Zubnet →

Recraft's latest image generation model, photorealistic and illustration styles, text rendering, 1024x1024, ~10s generation.

Try on Zubnet →

Recraft's highest quality image model, 2048x2048 output, superior anatomy and detail, ideal for print-ready assets. ~30s generation.

Try on Zubnet →

Recraft V4 Pro Vector

Recraft's highest quality vector model, high-resolution SVG output with fine detail, ideal for logos and brand assets.

Try on Zubnet →

Recraft V4 Vector

Recraft V4 for scalable vector graphics, generates production-quality SVG with discrete color regions and clean geometry.

Try on Zubnet →

Remove Background

Remove Background

Remove image background with transparency

Try on Zubnet →

Replace Background

Replace Background

Replace image background with AI-generated scene

Try on Zubnet →

Restore Old Photo

Restore Old Photo

Repair and revive old or damaged photos

Try on Zubnet →

Balanced speed and quality for high-volume digital asset creation

Try on Zubnet →

Highest-quality photo-realistic image generation perfect for professional print media

Try on Zubnet →

8B parameter MMDiT model. Superior quality, typography, and prompt adherence. Most powerful in SD family.

Try on Zubnet →

SD3.5 Large Turbo

SD3.5 Large Turbo

Distilled SD3.5 Large optimized for faster inference with fewer steps.

Try on Zubnet →

Balanced SD3.5 model. Great quality with lower resource requirements than Large.

Try on Zubnet →

SDXL 1.0 for high-resolution 1024x1024 image generation

Try on Zubnet →

Seedream 5.0 FlashNew

Seedream 5.0 Flash

ByteDance Seedream 5.0 Flash, the fast tier of Seedream 5.0: text-to-image up to 2K at the lowest price of the line. Native via BytePlus (Ark).

Try on Zubnet →

Seedream 5.0 Lite

Seedream 5.0 Lite

ByteDance Seedream 5.0 Lite, text-to-image (2K+), native via BytePlus (Ark).

Try on Zubnet →

Seedream 5.0 Pro

Seedream 5.0 Pro

ByteDance Seedream 5.0 Pro, flagship text-to-image (2K+), highest quality + consistency. Native via BytePlus (Ark).

Try on Zubnet →

The most creative, intelligent and personalizable image generation models built on a new groundbreaking architecture that delivers ultra high quality and 10x higher cost efficiency.

Try on Zubnet →

The most creative, intelligent and personalizable image generation models built on a new groundbreaking architecture that delivers ultra high quality and 10x higher cost efficiency.

Try on Zubnet →

Double image resolution

Try on Zubnet →

Quadruple image resolution

Try on Zubnet →

Q1 Image (Reference)

Vidu Q1 Image (Reference)

Generate images from 1-7 reference images. Upload reference images to get started.

Try on Zubnet →

Generate images from text or reference images. Supports 1080p, 2K, and 4K resolution.

Try on Zubnet →

Alibaba Wan 2.6 image editing. Edits 1-4 input images from a natural-language instruction (native DashScope, US-Virginia).

Try on Zubnet →

Alibaba Wan 2.6 text-to-image. Photorealistic generation with accurate text rendering and flexible artistic styles (native DashScope, US-Virginia).

Try on Zubnet →

Alibaba Wan 2.7 text-to-image and editing. Served from Singapore — the US tenant returns AccessDenied.

Try on Zubnet →

Wan 2.7 Image Pro

Wan 2.7 Image Pro

Alibaba Wan 2.7 pro tier, up to 4K output for print and large-format work. Served from Singapore.

Try on Zubnet →