MODEL TASKAI IMAGE · EDITING

Image Editing AI Models

Edit, restyle and combine images with a text instruction using Nano Banana, GPT Image, Seedream, FLUX, Qwen Image Edit and other image-to-image models.

Browse 51 models Get API key

Image Editing AI Models collection artwork

All Image Editing AI Models

Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.

image

Ideogram

Ideogram 4.5 Edit

Ideogram 4.5 edits an image from a text instruction, with an optional mask and style references, with reliable text rendering and polished graphic design output.

image-to-image

Flux 3 Edit

FLUX 3 by Black Forest Labs edits up to 10 reference images from a text instruction, with strong prompt adherence and typography at 512px to 4K resolution tiers.

image-to-image

Grok Imagine Image Quality Edit

Grok Imagine Image Quality Edit is xAI's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversio...

image-to-image
mcp_exposable

try-on

CatVTON is a virtual try-on model. It dresses the person in a photo with a garment from a second image, with controls for the covered body area, guidance, steps, and aspect ratio.

image-to-image

GPT Image 1 Mini Edit

Gpt Image 1 Mini Edit is OpenAI's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Ideogram 3.0 Edit

Ideogram V3 Edit by ideogram-ai - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images ef...

image-to-image

Flux 2 Klein 4B Edit

Flux 2 Klein 4b by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessl...

image-to-image

Hunyuan Image 3.0 Edit

Hunyuan Image 3.0 Edit by Tencent - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images ...

image-to-image

Flux 2 Flex Edit

Flux 2 Flex Edit by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortless...

image-to-image

Flux 2 Turbo Edit

Flux 2 Turbo Edit is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Flux 2 Klein 9B Edit

Flux 2 Klein 9b by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessl...

image-to-image

FLUX.1 Kontext [dev]

Flux 2 Kontext Dev by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortle...

image-to-image

Flux 2 Flash Edit

Flux 2 Flash Edit is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Flux 2 Max Edit

Flux 2 Max Edit is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Flux 2 Dev Edit

Flux 2 Dev Edit is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

MAI Image 2.5 Edit

Mai Image 2.5 Edit by Microsoft - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images ef...

image-to-image

SAM 3 Image

SAM 3 Image is Meta's segmentation model. It finds objects in an image from a text, point, or box prompt and returns masks and the masked image, with optional confidence scores.

image-to-image

Clarity Upscaler

Clarity Upscaler by ClarityAI - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effo...

image-to-image

Topaz Upscale

Upscale Image is Topaz Labs's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Kling Image O3 Edit

Kling Image O3 Edit by Kuaishou edits or recomposes images from a text instruction using up to 10 reference images, with 1K, 2K, or 4K output.

image-to-image

SeedVR2 Image Upscale

Seedvr Upscale Image by Bytedance - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images ...

image-to-image

Grok Imagine Image Edit

Grok Imagine Image Edit is xAI's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Flux 2 Pro Edit

Flux 2 Pro Edit is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

MAI Image 2.5 Pro Edit

Mai Image 2.5 Pro Edit by Microsoft - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance image...

image-to-image

Qwen Image Edit 2511

Qwen Image Edit 2511 by Alibaba - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images ef...

image-to-image

Qwen Image Edit 2511 Multiple Angles

Qwen Image Edit 2511 Multiple Angles by Alibaba - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and e...

image-to-image

Qwen Image Edit

Qwen Image Edit is Alibaba's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

GPT Image 1.5 Edit

Gpt Image 1.5 Edit by OpenAI - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effor...

image-to-image

Wan 2.5 Image to Image

Alibaba Wan 2.5 image-to-image model that edits one or more input images from a natural-language instruction, with selectable output aspect ratio.

image-to-image

Seedream 4.5 Edit

A new-generation image creation model from ByteDance, Seedream 4.5 integrates text-to-image generation and image editing into a single unified architecture, delivering high-fidelity visuals, precise p...

image-to-image
commercial

Z-Image Turbo Edit

Z Image Turbo Edit by Alibaba - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effo...

image-to-image

Wan 2.6 Image to Image

Alibaba Wan 2.6 image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.

image-to-image

Seedream 5.0 Lite Edit

Seedream 5.0 Lite — Fast Text-to-Image API The lightweight version of Seedream 5.0, delivering high-quality, low-latency AI image generation from text prompts. Ideal for real-time creative tools, e-co...

image-to-image
commercial

Wan 2.7 Image to Image

Alibaba Wan 2.7 image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.

image-to-image

Wan 2.7 Pro Image to Image

Alibaba Wan 2.7 Pro image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.

image-to-image

Nano Banana Pro Edit

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

image-to-image
commercial

Nano Banana 2 Edit

Nano Banana 2 is Google's new state-of-the-art image generation and editing model

image-to-image
commercial

Nano Banana 2 Lite Edit

Nano Banana 2 Lite Edit is Google's low-latency, cost-efficient image editing model (Gemini 3.1 Flash Lite Image). Edit and combine supplied images with a text prompt; output is a 1K image.

image-to-image

Qwen Image 3 Edit

Alibaba Qwen Image 3 image editing model with support for up to three reference images.

image-to-image

Seedream 5.0 Pro Edit

Seedream 5.0 Pro is Bytedance's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Grok Imagine Image 2.0 Edit

Grok Imagine Image 2.0 Edit is xAI's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

image-to-image

Seedream 5.0 Flash Edit

Seedream 5.0 Flash Editing edits and fuses up to 10 reference images from a text instruction at one flat price per image, with fast 15–20 second turnaround.

image-to-image
commercial

GPT Image 2 Edit

GPT Image 2 Editing supports image editing and multi-image synthesis with high-quality results.

image-to-image
commercial

Nano Banana 2.1 Edit

Nano Banana 2.1 Edit is Google's latest fast image editing model, fusing up to 14 reference images with stronger subject consistency and 1K to 4K output.

image-to-image
commercial

GPT Image 2.5 Sunburst Edit

GPT Image 2.5 Sunburst Edit prioritizes precision and visual fidelity for complex image editing workflows.

image-to-image
commercial

GPT Image 2.5 Flare Edit

GPT Image 2.5 Flare Edit is optimized for fast, high-quality image editing and multi-image composition.

image-to-image
commercial

Seedream 5.5 Edit

Seedream 5.5 Edit by ByteDance edits images with text instructions and up to 10 reference images. It keeps unedited regions stable across many rounds of editing and can return transparent-background (...

image-to-image

MiniMax H3 Image Highspeed Edit

MiniMax H3 Image Highspeed Edit is the faster version of MiniMax H3 Image Edit, editing and composing images from 1 to 16 reference images with the same parameters and 1K, 2K or 4K output.

image-to-image
commercial

MiniMax H3 Image Edit

MiniMax H3 Image Edit edits and composes images from 1 to 16 reference images with MiniMax's H3 image model, following the instruction while keeping subjects consistent, with 1K, 2K or 4K output.

image-to-image
commercial

GPT Image 2.6 Flare Edit

GPT Image 2.6 Flare Edit is optimized for fast, high-quality image editing and multi-image composition.

image-to-image
commercial

GPT Image 2.6 Sunburst Edit

GPT Image 2.6 Sunburst Edit prioritizes precision and consistency across successive edits for complex image editing workflows.

image-to-image
commercial

PRICEFrom $0.105

MODEimage

View model

Edit images with an instruction

Image editing models take one or more input images and a text instruction, then return a modified image. Typical jobs include replacing clothing or backgrounds, changing style, fixing details and composing several references into one scene.

Multi-reference editing

Several models accept many reference images at once: Nano Banana 2.1 Edit fuses up to 14, MiniMax H3 Image Edit up to 16, and Kling Image O3 Edit up to 10. Use this to keep a product or person consistent while changing everything around it.

Related tasks

Increase resolution or restore detail: image and video upscalers.
Create from scratch: text-to-image models.

Start using Image Editing AI Models on SandBase

One API key and one request shape for every model on this page.

01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINAL
```
export SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY"
```

Submit a run

Send a request to the Unified Run API with model bytedance/seedream/4.5/edit. Only the model field changes between models on this page.

TERMINAL

curl https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bytedance/seedream/4.5/edit", "prompt": "Replace the clothing in image 1 with the outfit from image 2", "images": ["https://p9-arcosite.byteimg.com/tos-cn-i-goo7wpa0wc/4b4464161cf3463db6f9463b10939178~tplv-goo7wpa0wc-image.image"]}'

03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINAL
```
curl https://api.sandbase.ai/v1/run/$RUN_ID \
  -H "Authorization: Bearer $SANDBASE_API_KEY"
```

Questions, answered

How do I pass the images to edit?

Send an images array of public HTTPS URLs together with a prompt. The order matters when your instruction refers to "image 1" and "image 2".

Which model is the most used for editing on SandBase?

Seedream 4.5 Edit, GPT Image 2 Edit and Nano Banana Pro Edit have the highest run counts on SandBase. The cards on this page are ordered by usage.

Can I edit only part of an image?

Some models, such as GPT Image 2.5 Flare, accept an optional mask. Others edit from the instruction alone; describe what should stay unchanged.

Is editing priced differently from generation?

Edit endpoints have their own price, shown on each model card. Price usually depends on output size and quality tier.

READY / SET / RUN

Build with Image Editing AI Models.

One key, consistent APIs, and usage-based pricing across every model on this page.

Get your API key Read the docs

Image Editing AI Models

Ideogram 4.5 Edit

Flux 3 Edit

Grok Imagine Image Quality Edit

try-on

GPT Image 1 Mini Edit

Ideogram 3.0 Edit

Flux 2 Klein 4B Edit

Hunyuan Image 3.0 Edit

Flux 2 Flex Edit

Flux 2 Turbo Edit

Flux 2 Klein 9B Edit

FLUX.1 Kontext [dev]

Flux 2 Flash Edit

Flux 2 Max Edit

Flux 2 Dev Edit

MAI Image 2.5 Edit

SAM 3 Image

Clarity Upscaler

Topaz Upscale

Kling Image O3 Edit

SeedVR2 Image Upscale

Grok Imagine Image Edit

Flux 2 Pro Edit

MAI Image 2.5 Pro Edit

Qwen Image Edit 2511

Qwen Image Edit 2511 Multiple Angles

Qwen Image Edit

GPT Image 1.5 Edit

Wan 2.5 Image to Image

Seedream 4.5 Edit

Z-Image Turbo Edit

Wan 2.6 Image to Image

Seedream 5.0 Lite Edit

Wan 2.7 Image to Image

Wan 2.7 Pro Image to Image

Nano Banana Pro Edit

Nano Banana 2 Edit

Nano Banana 2 Lite Edit

Qwen Image 3 Edit

Seedream 5.0 Pro Edit

Grok Imagine Image 2.0 Edit

Seedream 5.0 Flash Edit

GPT Image 2 Edit

Nano Banana 2.1 Edit

GPT Image 2.5 Sunburst Edit

GPT Image 2.5 Flare Edit

Seedream 5.5 Edit

MiniMax H3 Image Highspeed Edit

MiniMax H3 Image Edit

GPT Image 2.6 Flare Edit

GPT Image 2.6 Sunburst Edit

Edit images with an instruction

Multi-reference editing

Related tasks

Create an API key

Submit a run

Fetch the result

Build with Image Editing AI Models.