What image formats are supported for input and output?

The skill supports PNG, JPEG, GIF, and WebP for input during editing and defaults to saving high-quality PNG files for all generated outputs.

Can I use this skill to edit my existing images?

Yes, by specifying an input file path, you can use text prompts to modify existing images, such as changing the lighting, adding objects, or altering the background style.

Is this the right skill for creating technical flowcharts or circuit diagrams?

No, this skill is for creative and general-purpose imagery. For technical schematics, flowcharts, or system architectures, you should use the scientific-schematics skill.

Which AI models does the Generate Image skill support?

The skill primarily utilizes Google Gemini 3 Pro and Black Forest Labs FLUX.2 Pro for high-quality generation and editing, while FLUX.2 Flex is available as a cost-effective alternative for generation-only tasks.

What is required to start using the Generate Image skill?

You will need an OpenRouter API key configured in a .env file or as an environment variable (OPENROUTER_API_KEY) to authenticate and access the image models.

AI Image Generator & Editor

Name: AI Image Generator & Editor
Author: x-cmd

byx-cmd

•

设计工具

Generates and edits high-quality photorealistic images, illustrations, and visual assets using state-of-the-art AI models.

The Generate Image skill enables Claude to produce and modify high-fidelity visual content using industry-leading models like FLUX.2 Pro and Gemini 3 Pro via OpenRouter. It is designed for creative and general-purpose tasks such as creating artwork, concept visuals, marketing assets, and photorealistic imagery. Beyond simple generation, the skill supports sophisticated image editing, allowing users to modify existing files by changing backgrounds, adding elements, or adjusting styles through natural language instructions. While optimized for aesthetic and conceptual visuals, it is meant to be used alongside technical diagramming tools to provide a comprehensive visual toolkit for developers and researchers.

主要功能

01Automated .env configuration for secure and easy API key management

02Advanced image editing capabilities for modifying existing JPG, PNG, and WebP files

03Customizable output parameters for file paths, model selection, and prompt refinement

04Seamless OpenRouter API integration for high-performance generation

059 GitHub stars

06Multi-model support including Black Forest Labs FLUX.2 and Google Gemini 3 Pro

使用场景

01Performing rapid image transformations such as object insertion or color modifications

02Creating conceptual scientific illustrations and artistic visuals for research presentations

03Generating photorealistic hero images and backgrounds for frontend web development

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add x-cmd/skill generate-image

For use in Claude.ai and ChatGPT

Download Skill