generateImageFromReference
Create a new image by providing a text prompt and a reference image URL. Use an existing image as input to generate variations or transformations based on your description.
Instructions
Generate a new image using an existing image as reference. User-configured settings in MCP config will be used as defaults unless specifically overridden.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The text description of what to generate based on the reference image (e.g., "create a cartoon version", "make it look like a painting") | |
| imageUrl | Yes | Public HTTP(S) URL(s) of reference images. Accepts a string or an array for multi-reference. Local file paths, file uploads, or base64/data URLs are not supported. | |
| model | No | Model name to use for generation (default: user config or "kontext"). Available: "kontext", "nanobanana", "seedream" | |
| seed | No | Seed for reproducible results (default: random) | |
| width | No | Width of the generated image (default: 1024) | |
| height | No | Height of the generated image (default: 1024) | |
| enhance | No | Whether to enhance the prompt using an LLM before generating (default: true) | |
| safe | No | Whether to apply content filtering (default: false) | |
| outputPath | No | Directory path where to save the image (default: user config or "./mcpollinations-output") | |
| fileName | No | Name of the file to save (without extension, default: generated from prompt) | |
| format | No | Image format to save as (png, jpeg, jpg, webp - default: png) |