> ## Documentation Index
> Fetch the complete documentation index at: https://docs.markifact.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Edit Image

> Edit or enhance an existing image, ad, infographic, slide or creative using AI

Edit or enhance an existing image, ad, infographic, slide or creative using AI. Provide an image URL and describe the changes you want to make to generate a new version. Supports multiple AI image models, including the leading Gemini Nano Banana model.

| | |
| - | - |
| **App** | AI |
| **Operation ID** | `ai_edit_image` |
| **Type** | Action |
| **Connection** | None |
| **Credits per run** | 25 |
| **Agent / MCP tool** | Yes |
| **MCP** | Not exposed via MCP |

## Inputs

| Field | Type | Required | Default | Description |
| - | - | - | - | - |
| `prompt` | string | Yes | - | Instructions for editing the image. This is a multi-line text area where you can: - Describe the changes you want to make - Specify styles, objects to add/remove, or modifications - Reference dynamic data for personalized edits - Use line breaks to structure complex edit instructions  Example: "Remove the background and add a professional office setting Make the lighting more vibrant Ensure the person looks professional" |
| `images` | array of string | Yes | - | List of image URLs to edit (first image will be used for editing). You can reference images from upstream nodes using \{\{nodeId\_\_data}} syntax.  Supported formats: JPEG, PNG, GIF, WebP Images can be from URLs, file uploads, or outputs from other workflow nodes.  Example: \["`https://example.com/image.jpg`"] or \["\{\{imageNodeId\_\_data.url}}"] |
| `model` | string or SelectableOption | Yes | - | The AI model to use for image generation and editing. Available options: 'gemini-3.1-flash-image-preview' - This is the RECOMMENDED model. AKA 'Nano Banana 2'. 'gemini-3-pro-image-preview' - AKA 'Nano Banana Pro'. 'gpt-image-2.5-flare' - Fast image generation and precise editing. 'gpt-image-2.5-sunburst' - Highest quality image generation and precise editing. |
| `numImages` | integer | No | `1` | Number of edited image variations to generate (1-10). More variations give you more options to choose from. |
| `output_format` | string or SelectableOption | No | - | Format of the edited images (GPT-Image only). Available options: 'png' - High quality, supports transparency 'jpeg' - Smaller file size, good for photos ('jpg' is also accepted) 'webp' - Modern format, good compression |
| `quality` | string or SelectableOption | No | - | Quality of the edited images (GPT-Image only): auto, low, medium, high. GPT Image 2.5 Flare and Sunburst also support xhigh and max. |
| `size` | string or SelectableOption | No | - | Size of the edited images (GPT-Image only): auto, 1024x1024, 1536x1024, or 1024x1536. GPT Image 2 and 2.5 also support 2048x2048, 2048x1152, 3840x2160, 2160x3840, or custom WIDTHxHEIGHT sizes. Custom edges must be multiples of 16, at most 3840 pixels, with an aspect ratio no greater than 3:1 and 655360 to 8294400 total pixels. Outputs above 3686400 pixels are experimental. |
| `background` | string or SelectableOption | No | - | Background type for the edited images (GPT-Image only): 'transparent' - No background (PNG or WebP only) 'opaque' - Solid background 'auto' - Let the model decide |
| `aspect_ratio` | string or SelectableOption | No | - | Aspect ratio for the edited images (Gemini model only). Available options: '1:1' - Square '1:4' - Ultra Tall '1:8' - Ultra Tall '2:3' - Portrait '3:2' - Portrait '3:4' - Portrait '4:1' - Ultra Wide '4:3' - Portrait '4:5' - Portrait '5:4' - Portrait '8:1' - Panorama '9:16' - Portrait '16:9' - Landscape '21:9' - Wide Landscape |
| `resolution` | string or SelectableOption | No | - | Resolution for edited images (Gemini only). Available options: '512px' '1K' '2K' '4K' |

### SelectableOption

| Field | Type | Required | Default | Description |
| - | - | - | - | - |
| `value` | string | Yes | - | |
| `label` | string | Yes | - | |

## Output

**Type**: `str | List[str]`

Returns URL(s) of edited image(s). Single URL if one image, list if multiple.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.