Generates images from text prompts using Stable Diffusion via Cloudflare Workers AI.
Generates images and text using Google Gemini models through Cloudflare AI Gateway.
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., "@cf-image-gen MCP Server Create an image of a futuristic city skyline at night."
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.
Generate images and video from text prompts using Cloudflare Workers AI (Stable Diffusion) or Google Gemini models via Cloudflare AI Gateway.
Text Prompt → cf-image-gen MCP Server → Cloudflare AI Gateway
├── Workers AI (Stable Diffusion XL)
├── Gemini Image Models (generateContent)
└── Gemini Text Models (Interactions API)Related MCP server: pixel-surgeon-mcp
Model | ID | Output |
Stable Diffusion XL |
| 1024×1024 PNG |
Use google-ai-studio/{modelName} format.
Model | Format | Notes |
| image/jpeg | No text, 1120 image tokens |
| image/jpeg | +157 reasoning tokens |
| image/png | Returns text + image |
Model | Notes |
| Latest text model |
Node.js 18+
Cloudflare account with:
Account ID
API Token (Workers AI)
AI Gateway ID
AI Gateway Auth Token (for Gemini models)
Google AI Studio API key (for Gemini models)
Variable | Required | Description |
| ✅ | Cloudflare Account ID |
| ✅ | Cloudflare API Token |
| For Gemini | AI Gateway ID |
| For Gemini | Google AI Studio API Key |
| For Gemini | AI Gateway Auth Token |
| ❌ | Output directory (default: |
{
"prompt": "a samurai warrior standing on a mountain at sunset, pixel art style, 8-bit game aesthetic",
"model": "google-ai-studio/gemini-3.1-flash-image"
}Or with Stable Diffusion (default):
{
"prompt": "a red apple on white background"
}Gemini 3.1 Flash Image — google-ai-studio/gemini-3.1-flash-image
Prompt: "a samurai warrior standing on a mountain at sunset, pixel art style, 8-bit game aesthetic"
Workers AI path: Direct call to POST /accounts/{id}/ai/run/{model} with Cloudflare API Token
AI Gateway path: Routes through gateway.ai.cloudflare.com/v1/{account}/{gateway}/
Image-capable models → v1beta/models/{model}:generateContent with generationConfig.responseModalities: ["IMAGE"]
Text-only models (gemini-3-flash*) → v1beta/interactions with plain string input
# Install dependencies
cd .opencode/mcp/cf-image-gen
npm install
# Run standalone (stdio)
# Configure in opencode.jsonc as MCP serverMIT
This server cannot be deployed
Generate images, videos, voiceovers, and captions from a chat prompt.
Create images and videos from prompts, with options for image mixing, reference images, and start/…
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
