nano-banana-pro

Generate and edit images from prompts or existing inputs using Gemini 3 Pro.

Updated Mar 30, 2026

Search Tags:#image generation #visual design #image editing #gemini #prompting #png export

Ready to run

npx skills add https://github.com/miethe/signal_to_system --skill nano-banana-pro-miethe

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/miethe/signal_to_system/tree/main/.agents/skills/nano-banana-pro
Command: npx skills add https://github.com/miethe/signal_to_system --skill nano-banana-pro-miethe

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of generating polished images and making precise visual edits by turning a short prompt, or an existing image plus instructions, into a ready-to-use PNG.

Core Features & Use Cases

Text-to-Image Generation: Create new images from scratch for concepts, scenes, posters, and product mockups.
Image-to-Image Editing: Modify an existing image by changing style, content, lighting, background, or other visual details while preserving the source image as needed.
Resolution Control and Iteration: Start with fast draft outputs and move to higher-resolution final renders for production use.
Use Case: A marketer can generate a campaign hero image, iterate on the composition and tone, then export a final high-resolution version for publishing.

Quick Start

Use the nano-banana-pro skill to create or edit an image from your prompt and save the result as a PNG in your current working directory.

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 high-resolution PNG images from text prompts?▼

You can generate PNG images from text prompts by providing a short description to the skill. It uses the Gemini 3 Pro Image preview model to create concepts, scenes, or product mockups and saves the result in your working directory.

Can I edit an existing image and change its background or lighting?▼

Yes, image-to-image editing allows you to modify an existing image by changing style, content, lighting, or background. You provide the source image and instructions, and the skill outputs the refined visual as a PNG file.

Do I need an API key to export images with Gemini?▼

Yes, API-key authentication is required to export your generated or edited images as PNG files. The skill relies on the google-genai dependency to process your prompts and handle the final image export.

What resolutions are supported for image generation and editing?▼

The skill supports selectable 1K, 2K, and 4K output sizes for image generation and editing. This allows you to start with fast draft outputs and move to higher-resolution final renders for production use.

What is the best way to iterate on marketing visuals before exporting?▼

The best way to iterate on marketing visuals is to use the image-to-image editing feature to adjust composition and tone. You can start with fast draft outputs, refine the visual details iteratively, and then export a final high-resolution PNG.