nano-banana-pro

Generate or edit images via the Gemini 3 Pro Image API.

Updated Jan 8, 2026
One-click install
npx skills add https://github.com/drshailesh88/Krypto --skill nano-banana-pro-drshailesh88
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/drshailesh88/Krypto/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/drshailesh88/Krypto --skill nano-banana-pro-drshailesh88

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai>=1.0.0, pillow>=10.0.0, and includes scripts (resource) components.

What problem does it solve?

This Skill enables rapid generation or editing of images using Google Gemini 3 Pro Image API, enabling designers and creators to iterate visuals quickly without complex tooling.

Core Features & Use Cases

  • Generate new images from natural language prompts using Gemini 3 Pro Image.
  • Edit existing images by applying prompts to alter visuals or features.
  • Output high-resolution PNG/JPG images at 1K, 2K, or 4K depending on input and prompt.

Quick Start

Use the bundled script to generate an image: uv run {baseDir}/scripts/generate_image.py --prompt "a futuristic city at sunset" --filename "output.png" [--resolution 1K|2K|4K]

Frequently Asked Questions about nano-banana-pro

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using the Gemini 3 Pro API?▼

To generate images from text prompts using the Gemini 3 Pro API, run the bundled script with your natural language prompt and desired filename. It outputs high-resolution PNG or JPG files at 1K, 2K, or 4K resolution.

Can I edit existing images by applying text modifications with Gemini 3 Pro?▼

Yes, you can edit existing images by applying text modification instructions with Gemini 3 Pro. The Skill processes your prompts to alter visual features and outputs the updated high-resolution image files.

Do I need a specific Python environment to use the Gemini 3 Pro Image API for image generation?▼

Yes, image generation requires the google-genai and Pillow Python libraries. You must also provide your GEMINI_API_KEY via an environment variable or pass it directly using the --api-key argument.

What resolutions are supported when generating AI images via natural language prompts?▼

Generating AI images via natural language prompts supports 1K, 2K, and 4K resolutions. You can specify your desired output size using the --resolution argument when running the generation script.

Why does my image generation script fail when using the Gemini API client?▼

Your image generation script fails if the google-genai and Pillow dependencies are missing or the GEMINI_API_KEY is not configured. Ensure your environment has the required libraries installed and your API key is set correctly.

Is nano-banana-pro suitable for rapid visual prototyping in design workflows?▼

nano-banana-pro is suitable for rapid visual prototyping in design workflows. It enables designers and creators to quickly iterate visuals from text prompts or modification instructions without complex tooling.