generateImageFromReference
Create new images by using an existing image as a reference. Customize settings like dimensions, model, and enhancements to generate tailored visuals based on user prompts.
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
| Name | Required | Description | Default |
|---|---|---|---|
| enhance | No | Whether to enhance the prompt using an LLM before generating (default: true) | |
| 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) | |
| height | No | Height of the generated image (default: 1024) | |
| imageUrl | Yes | URL of the reference image to base the generation on | |
| model | No | Model name to use for generation (default: user config or "gptimage"). Available: "gptimage", "kontext" | |
| outputPath | No | Directory path where to save the image (default: user config or "./mcpollinations-output") | |
| 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") | |
| safe | No | Whether to apply content filtering (default: false) | |
| seed | No | Seed for reproducible results (default: random) | |
| transparent | No | Generate image with transparent background (gptimage model only, default: false) | |
| width | No | Width of the generated image (default: 1024) |