Uses Google's Gemini model to expand rough user ideas into detailed image prompts before image generation.
Generates images from text prompts using the Hugging Face Inference API, sending enhanced prompts to text-to-image models.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Imaginate generate an image of a steampunk octopus"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Turn a rough idea into a generated image — a LangChain prompt-enhancement chain expands your casual description into a detailed image prompt, which is then sent to a text-to-image model. Also exposed as an MCP tool, so any MCP-compatible AI agent (e.g. Claude Desktop) can call it directly.
User idea ("a cat astronaut")
│
▼
LangChain LCEL chain (Gemini) → expands into a detailed, styled prompt
│
▼
Hugging Face Inference API → generates the actual image
│
▼
Streamlit UI / MCP tool call → shown to the user or returned to the agentRelated MCP server: fluxlora-mcp
imaginate/
├── src/
│ ├── prompt_chain.py # LangChain LCEL: rough idea -> detailed prompt
│ ├── image_gen.py # Hugging Face Inference API call
│ └── mcp_server.py # Exposes generate_image_tool as an MCP tool
├── app/
│ └── streamlit_app.py # UI
├── outputs/ # generated images land here
├── .env.example
├── .gitignore
├── requirements.txt
└── README.mdInstall dependencies:
pip install -r requirements.txtCopy .env.example to .env and fill in your keys:
GOOGLE_API_KEY=your_gemini_api_key
HF_API_KEY=your_huggingface_tokenGemini key: https://aistudio.google.com/app/apikey
Hugging Face token: https://huggingface.co/settings/tokens
streamlit run app/streamlit_app.pypython src/mcp_server.pyTo connect this to Claude Desktop, add this to your Claude Desktop MCP config
(claude_desktop_config.json):
{
"mcpServers": {
"imaginate": {
"command": "python",
"args": ["/absolute/path/to/imaginate/src/mcp_server.py"]
}
}
}Restart Claude Desktop, and you'll be able to ask it to generate an image using
the imaginate tool directly.
This server cannot be deployed
MCP server for Flux AI image generation
MCP server for NanoBanana AI image generation and editing
MCP server for Qwen Image 3 AI image generation
MCP server for ByteDance Seedream AI image generation