claude-image-gen plugin
The media-pipeline plugin generates images through Gemini or OpenAI gpt-image-2: a skill, CLI and MCP server install in one step.
- 83 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Prompts and reference images go to Gemini or OpenAI with your API key, and requests are billed.
- The CLI and server save files to a configured folder on disk.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/claude-image-genDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Prompts and reference images go to Gemini or OpenAI with your API key, and requests are billed.
- The CLI and server save files to a configured folder on disk.
This is third-party code. Review the repository files before installing.
What it does
claude-image-gen is a Claude Code plugin named `media-pipeline`. It generates images from a text prompt through Google Gemini or OpenAI (`gpt-image-2`): the model name picks the provider, `gpt-image*` goes to OpenAI and everything else to Gemini. The plugin bundles a core skill that proactively suggests images for websites and presentations, a CLI script and an MCP server for direct tool calls. It supports aspect ratios, up to five reference images in PNG, JPEG and WebP, and on OpenAI models inpainting with a PNG mask, transparent background and GIF and SVG output. Files are saved to a configured folder and the agent gets the paths. A ready `.mcpb` extension exists for Claude Desktop.
Who it is for. Developers and designers who need illustrations for landing pages, slides and mocks straight from a Claude Code session.
Good fit when
- A landing page needs a 16:9 hero image and the agent writes the prompt itself.
- Slides need illustrations in one style based on reference images.
- An area of a finished picture has to be replaced through a PNG mask.
- An agent calls generation over MCP, or the script is used without the server.
Not a fit when
- You have no Gemini or OpenAI key: at least one is required.
- Prompts must not leave for external services: prompts and reference images go to the provider.
- You need a `dall-e` model: the README says it was shut down on 12 May 2026.
Example request
Generate a 16:9 hero image for a fintech startup landing page in calm blue tones and save the file in the project folder.Limitations
A Google Gemini or OpenAI API key is required, at least one; requests are billed by the provider. Manual installation needs Node.js 20 or newer. Mask inpainting, transparent background and GIF and SVG output are available only on OpenAI models. Files are saved inside the configured folder (`IMAGE_OUTPUT_DIR`), and the CLI accepts no other paths. Specialized workflows live outside `skills/` and are installed by hand; the default set leaves them out.
How to disable. Remove the plugin with `/plugin uninstall media-pipeline@media-pipeline-marketplace`. Clean keys in environment variables and saved images in `~/generated-images` separately.
FAQ
How do I install the plugin in Claude Code?
Run `/plugin marketplace add guinacio/claude-image-gen`, then `/plugin install media-pipeline@media-pipeline-marketplace`. A direct form also works: `/plugin install guinacio/claude-image-gen`.
How is the provider chosen?
By model name: `gpt-image*` goes to OpenAI and other models to Gemini. `IMAGE_PROVIDER` sets the default provider.
Can I disable the MCP server?
Yes. The skill runs the CLI directly, so it keeps working without MCP and Claude Code starts faster.
Is there a version for Claude Desktop?
Yes. Download `media-pipeline.mcpb` from the releases, install it in Settings, Extensions, Advanced settings, then enter a key.
Which reference images are accepted?
Up to five PNG, JPEG or WebP files on both providers.
Discussion
No questions or reviews yet.
Related
PluginsA plugin that draws and edits images in Claude Code through the built-in image_gen of local Codex on a ChatGPT login, no API key.
A Claude Code skill for generating, editing and reviewing images with Google Gemini models, with a plan and approval before every paid request
Skills give Claude Code three ways to make images: code-drawn graphics, Three.js 3D scenes and Flux diffusion on Cloudflare.
Claude Image (GPT Image 2)
claude-image
A skill teaching agents to work with GPT Image 2. OpenAI API access is needed and it is unavailable from Russia without workarounds
MCP server for image generation and editing: Gemini, OpenAI and Seedream with automatic prompt enhancement
A skill that adds image generation to Claude Code and Cursor through the Codex CLI on a ChatGPT subscription, no API key.
README in short
The description lists features and prerequisites, three install paths (plugin, Claude Desktop extension, manual build), MCP setup through `claude mcp add` and manual skill installation.