image-to-image
Edits an existing image based on a text prompt and optional mask.
How to use it
image-to-image is exposed by the Imagegen MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the image-to-image tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Imagegen MCP
npx imagegen-mcp [options]Other tools in Imagegen MCP (14)
(enum, optional): Background (transparent, opaque, auto). Defaults to auto. transparent requires outputformat to be png or webp.
An array containing:
(string, required): An array of file paths to local images.
(string, optional): A file path of mask image (PNG). Transparent areas indicate where the image should be edited.
(enum, optional): The model to use (e.g., gpt-image-1, dall-e-2, dall-e-3). Defaults to the first allowed model.
(enum, optional): Moderation level (low, auto). Defaults to low.
(number, optional): Compression level (0-100). Defaults to 100.
(enum, optional): Format (png, jpeg, webp). Defaults to png.
(string, required): A text description of the desired edits.
(enum, optional): Quality (standard, hd, auto, ...). Defaults to auto. hd only applicable to dall-e-3.
(enum, optional): Size of the generated image (e.g., 1024x1024, 1792x1024). Defaults to 1024x1024. Check OpenAI documentation for model-specific size support.
(enum, optional): Style of the image (vivid or natural). Only applicable to dall-e-3. Defaults to vivid.
(string, required): The prompt to generate an image from.
Generates an image based on a text prompt.