The Image Generation MCP Server enables text-to-image generation and image upscaling via Stable Diffusion WebUI API.
Generate Images: Create images from text prompts with customizable parameters (sampling steps, dimensions, CFG scale, seed, sampler, batch size, etc.)
Upscale Images: Enhance image resolution using various upscaling models and modes (multiplier or dimensions)
Manage Models: List and switch between available Stable Diffusion models
Access Upscalers: Get available upscaler models for image enhancement
Advanced Controls: Adjust face restoration, tiling, negative prompts, and other image generation features
Provides text-to-image generation capabilities by connecting to a Stable Diffusion WebUI instance, allowing image generation, model selection, and image upscaling through the API.
image-gen MCP Server
A MCP server that provides text-to-image generation capabilities using Stable Diffusion WebUI API (ForgeUI/AUTOMATIC-1111).
Installation
Prerequisites
Node.js
Access to a Stable Diffusion WebUI instance with API enabled
The WebUI must have
--api
flag enabled when starting
Setup
Clone the repository:
Install dependencies:
Build the server:
Add the server configuration to your environment:
Replace the environment variables with your values:
SD_WEBUI_URL
: URL of your Stable Diffusion WebUI instanceSD_AUTH_USER
: Username for basic auth (if enabled)SD_AUTH_PASS
: Password for basic auth (if enabled)SD_OUTPUT_DIR
: Directory where generated images will be savedSD_RESIZE_MODE
: Default upscaling mode (0 for multiplier, 1 for dimensions)SD_UPSCALE_MULTIPLIER
: Default upscale multiplier when resize_mode is 0SD_UPSCALE_WIDTH
: Default target width when resize_mode is 1SD_UPSCALE_HEIGHT
: Default target height when resize_mode is 1SD_UPSCALER_1
: Default primary upscaler modelSD_UPSCALER_2
: Default secondary upscaler model
Features
Tools
generate_image
- Generate images using Stable DiffusionParameters:
prompt
(required): Text description of the desired imagenegative_prompt
: Things to exclude from the imagesteps
: Number of sampling steps (default: 4, range: 1-150)width
: Image width (default: 1024, range: 512-2048)height
: Image height (default: 1024, range: 512-2048)cfg_scale
: CFG scale (default: 1, range: 1-30)sampler_name
: Sampling algorithm (default: "Euler")scheduler_name
: Scheduler algorithm (default: "Simple")seed
: Random seed (-1 for random)batch_size
: Number of images to generate (default: 1, max: 4)restore_faces
: Enable face restorationtiling
: Generate tileable imagesoutput_path
: Custom output path for the generated image
get_sd_models
- Get list of available Stable Diffusion modelsNo parameters required
Returns an array of model names
set_sd_model
- Set the active Stable Diffusion modelParameters:
model_name
(required): Name of the model to set as active
get_sd_upscalers
- Get list of available upscaler modelsNo parameters required
Returns an array of upscaler names
upscale_images
- Upscale one or more images using Stable DiffusionParameters:
images
(required): Array of image file paths to upscaleresize_mode
: 0 for multiplier mode, 1 for dimension mode (default: from env)upscaling_resize
: Upscale multiplier when resize_mode=0 (default: from env)upscaling_resize_w
: Target width in pixels when resize_mode=1 (default: from env)upscaling_resize_h
: Target height in pixels when resize_mode=1 (default: from env)upscaler_1
: Primary upscaler model (default: from env)upscaler_2
: Secondary upscaler model (default: from env)output_path
: Custom output directory for upscaled images
Development
For development with auto-rebuild:
Error Handling
Common issues and solutions:
Make sure your Stable Diffusion WebUI is running with the
--api
flagCheck if the WebUI URL is accessible from where you're running the MCP server
If using authentication, ensure credentials are correct
Verify the output directory exists and has write permissions
When upscaling, ensure the input image files exist and are readable
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
A MCP server that integrates with Stable Diffusion WebUI to provide text-to-image generation and image upscaling capabilities through simple API calls.
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityAn intelligent MCP server with a fully automated batch pipeline for web-ready images. Features include noise reduction, auto levels/curves, JPEG artifact removal, 4K resizing, smart sharpening with shadow/highlight enhancement, and advanced WebP conversion.
- AsecurityAlicenseAqualityAn MCP Server that integrates with Stability AI's API to provide high-quality image generation, editing, and manipulation capabilities including background removal, outpainting, search-and-replace, and upscaling.Last updated -4278MIT License
- AsecurityAlicenseAqualityAn MCP server that allows users to generate images using Replicate's Stable Diffusion model and save them to the local filesystem.Last updated -MIT License
- AsecurityAlicenseAqualityA server that integrates ComfyUI with MCP, allowing users to generate images and download them through natural language interactions.Last updated -49Apache 2.0