Does this skill support different aspect ratios?

Yes, it supports a wide range of aspect ratios including 1:1, 16:9, 9:16, 21:9, 4:3, and more to suit various design requirements.

What is Google Search grounding in image generation?

Google Search grounding allows the model to use real-time web data to inform the visual content of an image, such as visualizing current weather or specific news events.

What file format are the generated images saved in?

The Gemini API returns images in JPEG format by default. You should always use the .jpg extension when saving files to avoid media type mismatch errors.

What model does the Gemini Image Generation skill use?

By default, this skill uses the gemini-3-pro-image-preview model, also known as Nano Banana Pro, which is optimized for high-quality image generation and editing.

Can I edit an existing image with this skill?

Yes, you can pass an existing image along with a text prompt to perform tasks like adding objects, changing styles, or applying semantic modifications.

Gemini Image Generation

Name: Gemini Image Generation
Author: SiTaggart

bySiTaggart

0•

디자인 도구

Generates and edits high-resolution images using the Google Gemini API with support for multi-turn refinement and search grounding.

The Gemini Image Generation skill empowers Claude to interact with Google's Gemini API (Nano Banana Pro) for advanced visual tasks. It enables high-fidelity text-to-image generation up to 4K resolution, sophisticated image editing, and multi-turn conversational refinements. Unique features include the ability to compose scenes from up to 14 reference images and the integration of real-time data through Google Search grounding. Whether you're creating brand logos, product mockups, or stylized artwork, this skill provides the precision and flexibility needed for professional-grade visual assets.

주요 기능

01High-resolution support for 1K, 2K, and 4K image output

02Flexible aspect ratio controls ranging from 21:9 panoramic to 9:16 portrait

03Composition capabilities using up to 14 distinct reference images

04Multi-turn refinement for iterative conversational image editing

050 GitHub stars

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

사용 사례

01Generating professional logos and brand assets with specific font requirements

02Iteratively modifying existing images through natural language instructions

03Creating photorealistic product mockups and studio-lit marketing materials

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sitaggart/claude-devbench gemini-imagegen

For use in Claude.ai and ChatGPT

Download Skill