What model does the Gemini Image Generation skill use?

It uses the gemini-3-pro-image-preview model by default, which is optimized for high-quality image generation and complex editing tasks.

Is Google Search grounding supported for images?

Yes, you can enable Google Search grounding to generate images or infographics based on real-time information and current events.

Can I use this skill to edit existing images?

Absolutely. You can provide an existing image along with a text prompt to perform semantic edits, such as adding objects or changing the background.

How should I save the generated images to avoid errors?

Because the Gemini API returns images in JPEG format by default, you should always use the .jpg extension when saving files to prevent media type mismatch errors.

Does it support different aspect ratios?

Yes, it supports multiple aspect ratios including 1:1, 16:9, 9:16, 21:9, 3:2, 4:3, and more to fit various design requirements.

Gemini Image Generation

Name: Gemini Image Generation
Author: 8b-is

by8b-is

デザインツール

Generates and edits high-resolution images using the Google Gemini API directly within your Claude Code environment.

概要

The Gemini Image Generation skill empowers developers to integrate advanced visual creation capabilities into their development workflows using the Gemini 3 Pro model. It supports a wide range of tasks from basic text-to-image generation to complex multi-turn refinements, style transfers, and compositions using up to 14 reference images. With built-in support for custom resolutions up to 4K, various aspect ratios, and Google Search grounding for real-time data visualization, this skill provides a robust toolkit for creating logos, stickers, product mockups, and photorealistic assets without leaving the terminal.

主な機能

High-resolution generation from 1K to 4K with custom aspect ratios
Real-time visual data generation through Google Search grounding
Multi-image composition using up to 14 reference images simultaneously
Semantic image editing including object addition and style transfers
0 GitHub stars
Multi-turn iterative editing and refinement via conversational chat

ユースケース

Generating high-quality photorealistic imagery for marketing and documentation
Automating visual content creation based on real-time data and multi-reference sources
Rapidly prototyping UI assets, logos, and product mockups during development

概要

主な機能

High-resolution generation from 1K to 4K with custom aspect ratios
Real-time visual data generation through Google Search grounding
Multi-image composition using up to 14 reference images simultaneously
Semantic image editing including object addition and style transfers
0 GitHub stars
Multi-turn iterative editing and refinement via conversational chat

ユースケース

Generating high-quality photorealistic imagery for marketing and documentation
Automating visual content creation based on real-time data and multi-reference sources
Rapidly prototyping UI assets, logos, and product mockups during development