nano-banana-pro

Generate or edit images via Nano Banana Pro text prompts.

Updated Apr 6, 2026
One-click install
npx skills add https://github.com/Muchunpeng/openclaw-config --skill nano-banana-pro-muchunpeng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/Muchunpeng/openclaw-config/tree/main/workspace/skills/nano-banana-pro
Command: npx skills add https://github.com/Muchunpeng/openclaw-config --skill nano-banana-pro-muchunpeng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill enables fast creation and modification of images using Nano Banana Pro, reducing manual design time and accelerating visual iteration.

Core Features & Use Cases

  • Text-to-image and image-to-image generation
  • Iterative editing with prompts and optional input images
  • Supports 1K/2K/4K resolutions for quick drafts and high-fidelity outputs

Quick Start

Run the generate_image.py script with a prompt and optional input image to produce a new or edited image.

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 with text prompts using Gemini Pro?

You can generate images from text prompts by providing a text input to the Gemini 3 Pro API. This skill uses a local Python script to process your prompt and produce new visual assets.

Can I edit existing images with text prompts using AI?

Yes, you can edit existing images by providing an input image alongside a text prompt. This image-to-image capability supports iterative editing of existing visual assets across 1K, 2K, and 4K resolutions.

Do I need an API key to run the image generation script?

Yes, an API key for Gemini 3 Pro is required to run the image generation script. The local script interfaces with the API using this key to authenticate your text-to-image and image-to-image generation requests.

What resolutions are supported for AI image generation?

AI image generation supports 1K, 2K, and 4K resolutions. You can select the appropriate output size for quick concept art drafts or high-fidelity product visuals depending on your specific creative workflow requirements.

What is the best way to create high-fidelity product visuals from text?

Using text-to-image generation at 4K resolution is the best way to create high-fidelity product visuals. You provide a detailed text prompt to the API to swiftly produce high-quality visual assets without manual design work.