nano-banana

Generate and edit images with Google Gemini Nano Banana Pro from prompts and reference images.

11|1|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/jimezsa/opencolab --skill nano-banana-jimezsa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/jimezsa/opencolab/tree/main/projects/SKILLS/nano-banana
Command: npx skills add https://github.com/jimezsa/opencolab --skill nano-banana-jimezsa

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate and edit high-fidelity images from prompts and optional reference images using Google Gemini Nano Banana Pro, with convenient local key handling via .env.local when available.

Core Features & Use Cases

  • Generate new images from prompts.
  • Edit existing images by providing input references and guidance.
  • Save outputs locally, with optional model text and summaries.

Quick Start

Run the nano_banana.py script with a prompt and optional input images to generate or edit images using Gemini.

Frequently Asked Questions about nano-banana

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

FAQPage Schema
How do I generate deterministic images from prompts using a CLI workflow?

Generate deterministic images by running the nano_banana.py script with a text prompt, using model selection and aspect ratio options to produce repeatable visual assets saved locally.

Can I edit existing images by providing reference inputs to Gemini Nano Banana Pro?

Edit existing images by supplying optional reference images alongside guidance prompts to Gemini Nano Banana Pro, enabling targeted modifications while saving the updated outputs locally.

What's the best way to produce repeatable architectural diagrams and posters locally?

Produce repeatable architectural diagrams and posters by executing CLI commands with specific image size options and optional Google Search grounding to ensure deterministic, structured outputs.

Do I need to configure environment variables to handle API keys for image generation?

Configure API keys for image generation by utilizing convenient local key handling via a .env.local file, ensuring secure access to Google Gemini Nano Banana Pro services.

Does this image generation workflow support structured outputs with text and summaries?

This workflow supports structured outputs by generating images with optional model text and summaries, providing comprehensive results for asset production and architectural figures.