Does it support high-resolution output for professional use?

Absolutely. The skill supports 1K, 2K, and 4K resolutions with various aspect ratios including 16:9, 21:9, and mobile-friendly formats.

What is Google Search grounding in this context?

Grounding allows the AI to use real-time Google Search data to ensure that generated images, such as infographics or specific locations, are factually accurate.

Can I edit existing images with this Claude Code skill?

Yes, it includes specialized scripts for semantic image editing, allowing you to pass an existing image and a text prompt to modify specific elements.

How do I authenticate the Gemini API?

You must set the GEMINI_API_KEY environment variable in your system to allow the scripts to communicate with Google's generative AI services.

What model does this skill use for image generation?

It utilizes the gemini-3-pro-image-preview model, also known as Nano Banana Pro, which offers advanced reasoning and 4K resolution support.

Gemini Image Generation

Name: Gemini Image Generation
Author: agneym

byagneym

•

디자인 도구

Generates and edits professional-quality images, technical diagrams, and illustrations using the Gemini 3 Pro Image model.

소개

This skill integrates Google's Gemini 3 Pro Image model (Nano Banana Pro) into the Claude Code environment, enabling developers to generate high-resolution assets up to 4K directly via terminal scripts. It provides a comprehensive suite for text-to-image generation, semantic image editing, and iterative refinement through multi-turn chat interfaces. With advanced capabilities like Google Search grounding for factual accuracy and the ability to compose scenes from up to 14 reference images, this skill is ideal for creating technical documentation, UI mockups, and professional brand assets within a developer workflow.

주요 기능

High-resolution generation up to 4K with multiple aspect ratio support
Iterative multi-turn chat for conversational image refinement
Google Search grounding for factually accurate visual representations
Multi-reference composition using up to 14 source images simultaneously
Semantic image editing to modify existing assets via natural language
1 GitHub stars

사용 사례

Creating high-fidelity UI/UX mockups and product visualizations
Developing custom brand assets and logos through iterative AI refinement
Generating complex technical architecture diagrams for documentation

소개

주요 기능

High-resolution generation up to 4K with multiple aspect ratio support
Iterative multi-turn chat for conversational image refinement
Google Search grounding for factually accurate visual representations
Multi-reference composition using up to 14 source images simultaneously
Semantic image editing to modify existing assets via natural language
1 GitHub stars

사용 사례

Creating high-fidelity UI/UX mockups and product visualizations
Developing custom brand assets and logos through iterative AI refinement
Generating complex technical architecture diagrams for documentation