Does this skill support 4K resolution?

Yes, it supports native 4K generation and upscaling to provide ultra-high-definition visual outputs for professional use.

What is grounded image generation?

Grounded generation utilizes Google Search to verify facts, ensuring that images of real-world objects, historical scenes, or landmarks are factually accurate and up-to-date.

Can I edit images after they are generated?

Yes, the skill supports conversational editing, allowing you to refine images through multi-turn dialogue while preserving visual context across prompts.

Can this model render readable text?

Yes, Gemini 3 Pro Image is specifically optimized for high-quality, readable text rendering, making it suitable for generating business cards, posters, and UI elements.

Gemini 3 Pro Image Generation

Name: Gemini 3 Pro Image Generation
Author: adaptationio

byadaptationio

数据科学与机器学习

Generates high-resolution 4K images, renders precise text, and performs conversational image editing using the Gemini 3 Pro Image model.

关于

This skill integrates the Gemini 3 Pro Image model (Nano Banana Pro) into Claude Code, enabling developers to generate 4K high-definition images, render accurate text within visuals, and refine outputs through multi-turn conversational editing. It leverages Google Search grounding for factual accuracy in generated scenes and provides full control over aspect ratios and quality parameters, making it ideal for visual prototyping, marketing content creation, and automated design workflows that require high-fidelity results.

主要功能

Grounded generation using Google Search for factual accuracy
Conversational multi-turn image editing and iterative refinement
Native 4K image generation with built-in upscaling support
High-quality, readable text rendering within generated images
0 GitHub stars
Flexible aspect ratio control including 16:9, 1:1, 4:3, and 9:16

使用场景

Iteratively refining graphic designs through natural language instructions
Creating factually accurate historical or scientific visualizations
Generating photorealistic assets and UI prototypes from text prompts

关于

主要功能

Grounded generation using Google Search for factual accuracy
Conversational multi-turn image editing and iterative refinement
Native 4K image generation with built-in upscaling support
High-quality, readable text rendering within generated images
0 GitHub stars
Flexible aspect ratio control including 16:9, 1:1, 4:3, and 9:16

使用场景

Iteratively refining graphic designs through natural language instructions
Creating factually accurate historical or scientific visualizations
Generating photorealistic assets and UI prototypes from text prompts