Does this skill require an API key?

Yes, you must have an OpenRouter API key configured in your environment variables or a .env file to access the generation models.

What is the difference between generate-image and scientific-schematics?

Use generate-image for artistic content, photos, and illustrations. Use the scientific-schematics skill for technical diagrams, flowcharts, and circuit maps.

Which models are supported for image generation?

The skill supports Gemini 3 Pro and FLUX.2 Pro for high-quality generation and editing, plus FLUX.2 Flex for cost-effective image generation.

Can I edit existing images with this skill?

Yes, by using the --input parameter, you can provide an existing image and use a text prompt to specify modifications such as changing colors or adding objects.

AI Image Generation

Name: AI Image Generation
Author: Sologa

bySologa

0•

设计工具

Generates and edits high-quality visual assets, photorealistic images, and artistic illustrations using advanced AI models like FLUX and Gemini.

The generate-image skill empowers developers to create and modify professional visual content directly through Claude Code. By leveraging OpenRouter's integration with top-tier models like FLUX.2 Pro and Gemini 3 Pro, it facilitates the rapid production of photos, concept art, and UI assets. This skill is ideal for enhancing documentation, presentations, and marketing materials, offering a clear distinction between general-purpose artistic imagery and technical scientific schematics.

主要功能

01Multi-model support including cost-effective options like FLUX.2 Flex

02Text-based image editing and modification of existing files

03Seamless OpenRouter API integration with environment variable support

040 GitHub stars

05High-quality image generation via FLUX.2 Pro and Gemini 3 Pro

06Automated output handling for base64-encoded visual data

使用场景

01Generating conceptual illustrations and artwork for scientific documentation

02Modifying existing visual assets to update styles or add specific elements

03Creating photorealistic hero images for websites and presentation slides

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sologa/codex-pipeline generate-image

For use in Claude.ai and ChatGPT

主要功能

01Multi-model support including cost-effective options like FLUX.2 Flex

02Text-based image editing and modification of existing files

03Seamless OpenRouter API integration with environment variable support

040 GitHub stars

05High-quality image generation via FLUX.2 Pro and Gemini 3 Pro

06Automated output handling for base64-encoded visual data

使用场景

01Generating conceptual illustrations and artwork for scientific documentation

02Modifying existing visual assets to update styles or add specific elements

03Creating photorealistic hero images for websites and presentation slides

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sologa/codex-pipeline generate-image

For use in Claude.ai and ChatGPT