What file formats are supported for image editing?

The script supports common image formats including PNG, JPEG, GIF, and WebP. All generated or edited images are saved as PNG files.

Can I edit existing images with this skill?

Yes, by using the --input parameter, you can provide an existing image and a prompt to perform edits like adding objects, changing styles, or modifying colors.

What models does this skill support?

This skill supports several models via OpenRouter, including google/gemini-3-pro-image-preview, black-forest-labs/flux.2-pro, and black-forest-labs/flux.2-dev.

Do I need an API key to use this skill?

Yes, you must have an OpenRouter API key. You can configure it in a .env file or as an environment variable named OPENROUTER_API_KEY.

Is there a cost associated with generating images?

The skill script itself is free, but the underlying models accessed via OpenRouter are subject to their specific pricing per generation or edit.

AI Image Generation & Editing

Name: AI Image Generation & Editing
Author: Activer007

byActiver007

デザインツール

Generates and modifies high-quality images, diagrams, and illustrations using FLUX and Gemini models via the OpenRouter API.

概要

This skill empowers Claude to create and transform visual assets directly within your development environment. By utilizing powerful AI models like FLUX.2 Pro and Gemini 3 Pro, it allows for the seamless generation of scientific illustrations, UI mockups, and artistic concepts. Beyond simple generation, it supports advanced image editing, enabling users to modify existing files by changing colors, adding or removing elements, or applying style transfers through natural language instructions, making it an essential tool for creating technical documentation and visual project resources.

主な機能

Supports premium models including FLUX.2 Pro and Gemini 3 Pro
0 GitHub stars
Text-to-image generation for diagrams, schematics, and illustrations
Automatic handling of base64 encoding and local file storage
Configurable model selection based on quality and cost requirements
Advanced image-to-image editing for modifying existing assets

ユースケース

Generating technical diagrams and scientific figures for documentation
Performing rapid AI-driven edits on project images using text prompts
Creating UI/UX mockups and placeholder assets during frontend development

概要

主な機能

Supports premium models including FLUX.2 Pro and Gemini 3 Pro
0 GitHub stars
Text-to-image generation for diagrams, schematics, and illustrations
Automatic handling of base64 encoding and local file storage
Configurable model selection based on quality and cost requirements
Advanced image-to-image editing for modifying existing assets

ユースケース

Generating technical diagrams and scientific figures for documentation
Performing rapid AI-driven edits on project images using text prompts
Creating UI/UX mockups and placeholder assets during frontend development