Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By thorrak
Generate and edit images using OpenAI's image models via the imagegen-mcp server
npx claudepluginhub thorrak/imagegen-plugin --plugin imagegenGenerate and edit images directly from Claude Code using OpenAI's image models (GPT-Image-1, DALL-E 2, DALL-E 3). Powered by imagegen-mcp.
npx)This repository serves as its own plugin marketplace. Add it to Claude Code, then install the plugin:
Step 1: Add the marketplace
Run Claude Code and use the /plugins command, then select Manage marketplaces and add this repository:
thorrak/imagegen-plugin
Step 2: Install the plugin
Once the marketplace is added, install the plugin:
/plugins install imagegen@imagegen-marketplace
Or browse interactively via /plugins > Discover.
Clone the repository and point Claude Code to it directly:
git clone https://github.com/thorrak/imagegen-plugin.git
claude --plugin-dir /path/to/imagegen-plugin
Set your OpenAI API key as an environment variable:
export OPENAI_API_KEY="your-api-key-here"
Add this to your shell profile (~/.bashrc, ~/.zshrc, etc.) to persist across sessions. The plugin's MCP server reads this variable automatically on startup.
Generate an image from a text prompt:
/generate-image a minimalist weather app icon, flat design, blue gradient
/generate-image --model dall-e-3 --size 1792x1024 a panoramic mountain landscape
/generate-image --transparent a coffee shop logo, simple vector style
Edit an existing image:
/edit-image ./assets/logo.png change the background color to navy blue
/edit-image ./photo.png --mask ./mask.png replace the sky with a starry night
You can also ask Claude conversationally — the plugin's skill activates automatically:
Both commands support optional flags:
| Flag | Values | Default | Notes |
|---|---|---|---|
--model | gpt-image-1, dall-e-2, dall-e-3 | gpt-image-1 | |
--size | e.g. 1024x1024, 1792x1024 | 1024x1024 | Valid sizes vary by model |
--format | png, jpeg, webp | png | |
--quality | auto, standard, hd | auto | hd is DALL-E 3 only |
--transparent | (flag, no value) | off | GPT-Image-1 + PNG/WebP only |
--n | number | 1 | DALL-E 3 limited to 1 |
| Model | Best For | Editing | Transparent BG | Sizes |
|---|---|---|---|---|
| gpt-image-1 | General use, highest quality | Yes | Yes | 1024x1024, 1536x1024, 1024x1536 |
| dall-e-3 | Artistic/creative images | No | No | 1024x1024, 1792x1024, 1024x1792 |
| dall-e-2 | Quick drafts, low cost | Yes | No | 256x256, 512x512, 1024x1024 |
Generated images are saved to ./generated-images/ in your project directory with descriptive filenames (e.g., weather-app-icon.png, hero-banner.png).
| Component | Description |
|---|---|
| MCP Server | Auto-starts imagegen-mcp via npx — connects to OpenAI's image APIs |
| Skill | Activates automatically when you discuss image generation — guides model selection, parameters, and prompting |
| Commands | /generate-image and /edit-image for quick, flag-based access |
MCP server fails to start:
OPENAI_API_KEY is set: echo $OPENAI_API_KEYnode --version (v18+ required)npx works: npx --versionImage generation fails:
Plugin not loading:
/plugins in Claude Code and verify imagegen is listed and enabledBuilt on imagegen-mcp by spartanz51.
Requires secrets
Needs API keys or credentials to function
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
GPT Image 2 CLI as a Claude Code skill: OpenAI gpt-image-2 + Codex image_generation under one command surface, with masks, transparent backgrounds, custom sizes up to 4K, and structured JSON / JSONL progress output.
AI image generation Creative Director powered by Google Gemini Nano Banana models. Claude interprets intent, selects domain expertise, constructs optimized prompts, and orchestrates Gemini for best results.
Generate and edit images using Gemini's Nano Banana Pro (gemini-3-pro-image-preview) model
AI-powered creative tools for image generation, editing, and visual content creation. Includes 0 agents, 1 command, and 1 skill for Gemini image generation.
Media asset processing plugin with skills for visual content creation.
OpenAI GPT Image 2 prompt gallery, image prompt library, agentic skill + CLI. Gallery-first prompt patterns, reference-image editing workflows, and a packaged CLI for skill-capable agent runtimes.
Integrates the PubMed MCP server for biomedical literature search, article retrieval, citation formatting, and research planning
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim