generateImage

generateImage

Create images using AI by providing a text prompt, adjusting dimensions, format, and saving location. Enhance prompts with LLM, choose models, and ensure reproducibility with seed values.

Instructions

Generate an image, return the base64-encoded data, and save to a file by default

Input Schema

Name	Required	Description
`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)
`model`	No	Model name to use for generation (default: "flux"). Available options: "flux, "turbo" (sdxl),
`outputPath`	No	Directory path where to save the image (default: "./mcpollinations-output")
`prompt`	Yes	The text description of the image to generate
`safe`	No	Whether to apply content filtering (default: false)
`seed`	No	Seed for reproducible results (default: random)
`width`	No	Width of the generated image (default: 1024)

Input Schema (JSON Schema)

{
  "properties": {
    "enhance": {
      "description": "Whether to enhance the prompt using an LLM before generating (default: true)",
      "type": "boolean"
    },
    "fileName": {
      "description": "Name of the file to save (without extension, default: generated from prompt)",
      "type": "string"
    },
    "format": {
      "description": "Image format to save as (png, jpeg, jpg, webp - default: png)",
      "type": "string"
    },
    "height": {
      "description": "Height of the generated image (default: 1024)",
      "type": "number"
    },
    "model": {
      "description": "Model name to use for generation (default: \"flux\"). Available options: \"flux, \"turbo\" (sdxl),",
      "type": "string"
    },
    "outputPath": {
      "description": "Directory path where to save the image (default: \"./mcpollinations-output\")",
      "type": "string"
    },
    "prompt": {
      "description": "The text description of the image to generate",
      "type": "string"
    },
    "safe": {
      "description": "Whether to apply content filtering (default: false)",
      "type": "boolean"
    },
    "seed": {
      "description": "Seed for reproducible results (default: random)",
      "type": "number"
    },
    "width": {
      "description": "Width of the generated image (default: 1024)",
      "type": "number"
    }
  },
  "required": [
    "prompt"
  ],
  "type": "object"
}

MCPollinations Multimodal MCP Server

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from MCPollinations Multimodal MCP Server

Related Tools