What aspect ratios are available for image generation?

The skill supports a wide range of ratios including 1:1, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and cinematic 21:9 formats.

Can I edit existing images with the Gemini API skill?

Yes, you can use the --edit flag to modify existing images or the --ref flag to use an image as a style reference for new generations.

How does the skill handle rate limits and network errors?

It features built-in automatic retries with exponential backoff (starting at 1s and doubling) for rate limits (429) and server errors (502, 503).

Which Gemini models are supported by this skill?

This skill supports gemini-3-pro-image-preview for high-quality 4K results and gemini-2.5-flash-image for faster iterations.

Gemini Image API Integration

Name: Gemini Image API Integration
Author: MadAppGang

byMadAppGang

•

211

数据科学与机器学习

Integrates Google Gemini's advanced image generation and editing capabilities directly into your Claude Code workflow.

关于

The gemini-api skill empowers developers to leverage Google's cutting-edge Gemini 3 Pro and 2.5 Flash models for high-quality image generation, editing, and style referencing. It provides a comprehensive set of tools for controlling aspect ratios, applying custom style templates, and handling complex image-to-image tasks. Built with robust error handling and automatic retry logic, this skill ensures a seamless experience for generating production-ready assets, UI mockups, or cinematic visuals directly from the command line while providing full reference documentation for the API.

主要功能

Comprehensive image editing and reference-based styling support via CLI flags.
Extensible style template system for consistent visual outputs across projects.
Native support for 8+ specific aspect ratios including cinematic and mobile formats.
211 GitHub stars
High-quality text-to-image generation using Gemini 3 Pro with up to 4K resolution.
Built-in exponential backoff and automatic retry logic for transient API errors.

使用场景

Automating batch image generation for content creation and social media workflows.
Prototyping visual design systems using reference images and markdown-based style templates.
Generating custom UI icons and high-resolution background assets for web applications.

关于

主要功能

Comprehensive image editing and reference-based styling support via CLI flags.
Extensible style template system for consistent visual outputs across projects.
Native support for 8+ specific aspect ratios including cinematic and mobile formats.
211 GitHub stars
High-quality text-to-image generation using Gemini 3 Pro with up to 4K resolution.
Built-in exponential backoff and automatic retry logic for transient API errors.

使用场景

Automating batch image generation for content creation and social media workflows.
Prototyping visual design systems using reference images and markdown-based style templates.
Generating custom UI icons and high-resolution background assets for web applications.