What image formats are supported?

The script supports common web formats including PNG, JPEG, GIF, and WebP. All generated or edited results are saved as PNG files by default.

Which AI models are supported by this skill?

The skill supports high-quality models via OpenRouter, including Google's Gemini 3 Pro, Black Forest Labs' FLUX.2 Pro, and FLUX.2 Dev for generation only.

Can I edit existing images with this skill?

Yes, you can use the --input parameter to provide an existing image and describe the specific changes you want, such as adding sunglasses or changing the background.

Do I need a separate API key for image generation?

Yes, an OpenRouter API key is required. You can set it in a .env file as OPENROUTER_API_KEY or export it as an environment variable.

Is there a cost to use this image generation skill?

While the skill script itself is open-source, OpenRouter charges for model usage. Prices vary depending on whether you choose Gemini 3 Pro or FLUX models.

AI Image Generation & Editing

Name: AI Image Generation & Editing
Author: Microck

byMicrock

•

デザインツール

Generates and edits high-quality images and technical diagrams using state-of-the-art AI models like FLUX and Gemini via OpenRouter.

概要

This skill empowers Claude to create and refine visual assets directly within the development workflow by interfacing with OpenRouter's powerful image models. It supports both text-to-image generation and sophisticated image-to-image editing, allowing users to create technical diagrams, scientific illustrations, UI placeholders, and artistic visualizations without leaving the terminal. Whether you need to generate a new schematic or modify an existing marketing asset, this skill provides a streamlined Python-based interface for professional-grade visual content creation.

主な機能

Multi-model support including FLUX.2 Pro, FLUX.2 Dev, and Gemini 3 Pro
81 GitHub stars
Automated .env file detection for secure OpenRouter API key management
Support for multiple input formats including PNG, JPEG, GIF, and WebP
Advanced image editing capabilities for modifying existing visuals and style transfers
Customizable output parameters for filenames and specific model selection

ユースケース

Modifying existing design assets such as changing background colors or adding elements
Creating scientific diagrams and technical illustrations for project documentation
Rapid prototyping of UI icons and visual placeholders for web and mobile development

概要

主な機能

Multi-model support including FLUX.2 Pro, FLUX.2 Dev, and Gemini 3 Pro
81 GitHub stars
Automated .env file detection for secure OpenRouter API key management
Support for multiple input formats including PNG, JPEG, GIF, and WebP
Advanced image editing capabilities for modifying existing visuals and style transfers
Customizable output parameters for filenames and specific model selection

ユースケース

Modifying existing design assets such as changing background colors or adding elements
Creating scientific diagrams and technical illustrations for project documentation
Rapid prototyping of UI icons and visual placeholders for web and mobile development