nano-banana-pro

Generate and edit images via Google's Gemini 3 Pro Image API.

4|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/resultanyildizi/skills --skill nano-banana-pro-resultanyildizi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/resultanyildizi/skills/tree/main/nano-banana-pro
Command: npx skills add https://github.com/resultanyildizi/skills --skill nano-banana-pro-resultanyildizi

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 creation and modification of visuals by leveraging Gemini 3 Pro's image generation and editing capabilities, reducing design turnaround time and enabling quick concept exploration.

Core Features & Use Cases

  • Text-to-image generation: Create new visuals from natural language prompts for logos, concept art, and marketing assets.
  • Image-to-image editing: Apply edits to existing images using editing prompts to refine composition, style, or color.
  • Resolution presets: Generate outputs at 1K, 2K, or 4K to fit different media channels.
  • Workflow integration: Use via the provided Python script with uv, enabling automation from the command line.

Quick Start

Generate a 2K image from a prompt: uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "minimalist coffee shop logo" --filename "2026-02-06-12-00-00-coffee-logo.png" --resolution 2K

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?

You can generate images from text prompts using the Gemini 3 Pro API by running the provided Python script via uv, passing your prompt, filename, and desired resolution as command-line arguments to create new visuals.

Can I edit existing images with AI using a command-line interface?

Yes, you can edit existing images with AI using a command-line interface by applying editing prompts to refine composition, style, or color through the provided Python script powered by the Gemini 3 Pro Image API.

What Python dependencies are required for AI image generation with Gemini 3 Pro?

AI image generation with Gemini 3 Pro requires the google-genai library for API access and the Pillow library for image processing, both executed through a Python script using the uv package manager.

Does this image generation workflow support 4K resolution outputs?

Yes, the image generation workflow supports 4K resolution outputs alongside 1K and 2K presets, allowing you to generate visuals tailored to different media channels by specifying the resolution parameter in the command line.

How do I automate logo creation and concept art generation from the command line?

You can automate logo creation and concept art generation from the command line by executing the Python script with uv, passing a natural language text prompt to generate the desired design asset automatically.

What is the best way to integrate AI image editing into a design workflow?

The best way to integrate AI image editing into a design workflow is using the command-line Python script with uv, enabling rapid creation and modification of visuals like logos and concept assets for quick concept exploration.