Does it support different aspect ratios?

Yes, it supports a wide range of ratios including 1:1, 16:9, 9:16, 3:2, 4:3, and ultra-wide 21:9 for various platform requirements.

Which Gemini model does this skill use?

It uses the gemini-3-pro-image-preview model (Nano Banana Pro) by default, supporting high-quality outputs from 1K up to 4K resolution.

How do I authenticate the API?

You must have a valid Google Gemini API key set in your environment as the GEMINI_API_KEY variable for the skill to function.

Can I edit existing images with this skill?

Yes, you can upload existing images and provide text prompts to perform semantic edits, style transfers, or add specific elements to the scene.

What file formats does the Gemini API return?

Gemini returns images in JPEG format by default. This skill includes specific guidance to save files with the .jpg extension to prevent media type mismatch errors.

Gemini Image Generation

Name: Gemini Image Generation
Author: gvkhosla

bygvkhosla

•

Herramientas de Diseño

Generates and edits high-quality visual assets using the Gemini API with support for custom resolutions, aspect ratios, and multi-turn refinement.

This skill integrates Google's advanced Gemini image generation capabilities directly into the Claude Code workflow, enabling developers to create and manipulate visual assets using the gemini-3-pro-image-preview model. It provides specialized implementation patterns for text-to-image generation, conversational image editing, and multi-image composition. By offering precise control over resolutions up to 4K and various aspect ratios, the skill ensures production-grade visual outputs while handling specific technical requirements like JPEG formatting and Google Search grounding for real-time data visualization.

Características Principales

01Composition support for up to 14 reference images in a single request

02Multi-turn refinement for iterative editing through conversational chat

0335 GitHub stars

04High-resolution generation from 1K to 4K with 10+ aspect ratio options

05Standardized Python patterns for robust Gemini API integration and file handling

06Google Search grounding for generating images based on real-time data

Casos de Uso

01Creating complex visual compositions using multiple reference images for product mockups

02Generating UI mockups, logos, and branding assets directly within development workflows

03Iteratively editing existing images using semantic masking and natural language instructions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add gvkhosla/compound-engineering-pi gemini-imagegen

For use in Claude.ai and ChatGPT

Download Skill