Does it support high-resolution 4K images?

Yes, the skill supports 1K, 2K, and 4K resolution settings, primarily when utilizing Gemini-based models.

How do I handle authentication for image generation?

You need an OpenRouter API key, which can be configured via the OPENROUTER_API_KEY environment variable or a local .openrouter-config file.

Which AI models are supported by this skill?

The skill supports any image generation model available through OpenRouter, including Google's Gemini series and Black Forest Labs' FLUX models.

Can I modify an image after it has been generated?

Yes, by using the --session flag, you can start a persistent session where the model remembers the previous image, allowing for iterative refinement.

Can I use existing images as a style reference?

Absolutely. Use the --reference flag followed by the image path to provide one or more images as style or content guidance for the AI.

OpenRouter Image Generator

Name: OpenRouter Image Generator
Author: typedrat

bytypedrat

Design Tools

Generates and refines high-quality AI images directly within Claude Code using the OpenRouter API.

About

The OpenRouter Image Generator skill enables Claude to create, iterate upon, and manage visual assets without leaving the terminal. It leverages OpenRouter's extensive model library—including FLUX and Gemini—to produce images tailored to specific aspect ratios, resolutions, and styles. With advanced features like session-based iterative refinement and reference image support, developers can seamlessly integrate visual content creation into their coding workflow, making it ideal for UI placeholders, marketing assets, and design prototyping.

Key Features

Access multiple AI models including Gemini 2.0 and FLUX.1 via OpenRouter
Iterative refinement sessions to evolve images through conversational feedback
Reference image integration for consistent style and content guidance
Built-in model discovery and pricing transparency via CLI commands
Support for multiple aspect ratios and high-resolution output up to 4K
0 GitHub stars

Use Cases

Generating UI/UX placeholders and mockups during frontend development
Creating marketing and social media assets with iterative style refinement
Producing consistent character or environment concept art for game development

About

Key Features

Access multiple AI models including Gemini 2.0 and FLUX.1 via OpenRouter
Iterative refinement sessions to evolve images through conversational feedback
Reference image integration for consistent style and content guidance
Built-in model discovery and pricing transparency via CLI commands
Support for multiple aspect ratios and high-resolution output up to 4K
0 GitHub stars

Use Cases

Generating UI/UX placeholders and mockups during frontend development
Creating marketing and social media assets with iterative style refinement
Producing consistent character or environment concept art for game development