Stable Diffusion WebUI

🚀 Image Generation MCP Server

An MCP server that provides text-to-image generation functionality based on the Stable Diffusion WebUI API (ForgeUI/AUTOMATIC-1111).

🚀 Quick Start

📦 Installation

Prerequisites

• Node.js
• Access to a Stable Diffusion WebUI instance with the API enabled
• The --api flag must be enabled when starting the WebUI

Setup

1. Clone the repository:

git clone https://github.com/Ichigo3766/image-gen-mcp.git
cd image-gen-mcp

2. Install dependencies:

npm install

3. Build the server:

npm run build

4. Add the server configuration to your environment:

{
  "mcpServers": {
    "image-gen": {
      "command": "node",
      "args": [
        "/path/to/image-gen-mcp/build/index.js"
      ],
      "env": {
        "NODE_ENV": "production",
        "PORT": "3000",
        "SD_WEBUI_URL": "http://localhost:7860",
        "AUTH_ENABLED": "false",
        "OUTPUT_DIR": "/path/to/output",
        "UPSCALER_1": "RealESRGAN_x2plus",
        "UPSCALER_2": "RealSR_x4plus"
      }
    }
  }
}

✨ Features

Tools

Generate Images

Generate high-quality images using a text-to-image model.

Get SD Models

Get a list of currently available Stable Diffusion models.

Set SD Model

Set the default Stable Diffusion model.

Upscale Resolution

Upscale the resolution of an image using Stable Diffusion.

Parameters

Generate Images

• prompt (required): A text prompt describing the image.
• negative_prompt: A prompt for content you don't want to appear.
• width (optional, default 512): The width of the output image.
• height (optional, default 512): The height of the output image.
• samples (optional, default 1): The number of images to generate.
• num_inference_steps (optional, default 20): The number of inference steps.

Get SD Models

No parameters. Returns a list of all available models.

Set SD Model

• model_id (required): The ID of the model to set.

Upscale Resolution

• images (required): An array of file paths for the images to be upscaled.
• resize_mode (optional, default from environment variable): 0 for multiplier mode, 1 for dimension mode.
• upscaling_resize (optional, default from environment variable): The scaling factor in multiplier mode.
• upscaling_resize_w (optional, default from environment variable): The target width in pixels in dimension mode.
• upscaling_resize_h (optional, default from environment variable): The target height in pixels in dimension mode.
• upscaler_1 (optional, default from environment variable): The primary upscaler model.
• upscaler_2 (optional, default from environment variable): The secondary upscaler model.
• output_path (optional, default current directory): The output path for the upscaled images.

💻 Usage Examples

Development

Use automatic reconstruction for development:

npm run watch

🛠️ Error Handling

Common issues and solutions:

1. Ensure that your Stable Diffusion WebUI is running and the --api flag is enabled.
2. Check if the WebUI URL is accessible from the MCP server.
3. If authentication is used, ensure that the credentials are correct.
4. Verify that the output directory exists and has write permissions.
5. When upscaling the resolution, ensure that the input image files exist and are readable.

📄 License

This MCP server is distributed under the MIT License. This means that you are free to use, modify, and distribute the software, but you must comply with the terms and conditions of the MIT License. For more information, please refer to the LICENSE file in the project repository.