skills.rest
JiayueMeng128
JiayueMeng128COMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

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

Updated Mar 10, 2026
Search Tags:#image generation#content creation#multimedia#image editing#gemini#AI art
One-click install
npx skills add https://github.com/JiayueMeng128/OpenClaw2Androidtrying --skill nano-banana-pro-jiayuemeng128
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/JiayueMeng128/OpenClaw2Androidtrying/tree/main/openclaw/skills/nano-banana-pro
Command: npx skills add https://github.com/JiayueMeng128/OpenClaw2Androidtrying --skill nano-banana-pro-jiayuemeng128

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the creation and modification of images using advanced AI models, eliminating the need for complex design software or manual editing for many tasks.

Core Features & Use Cases

  • Image Generation: Create unique images from text descriptions.
  • Image Editing: Modify existing images based on instructions.
  • Multi-Image Composition: Combine multiple images into a single scene.
  • Use Case: Generate a realistic image of a "cyberpunk cat riding a skateboard" or edit a photo to "add a sunset in the background."

Quick Start

Generate an image of a futuristic city skyline at dusk and save it as 'cityscape.png'.

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 descriptions using the Gemini API?▼

Image generation from text descriptions is achieved by sending prompts to the Gemini 3 Pro Image API, which creates unique visuals without requiring manual design software. You provide the text prompt, and the API returns the generated image.

Can I edit an existing image to add or modify elements?▼

Yes, you can edit an existing image by providing the source file alongside modification instructions to the Gemini API. The API processes the original image and applies the requested changes, such as adding a sunset background.

How does multi-image composition work for combining multiple scenes?▼

Multi-image composition combines multiple source images into a single scene by processing them together through the Gemini API. This allows you to merge various visual elements and subjects into one cohesive generated output.

Do I need a specific environment setup to run AI image generation scripts?▼

Yes, running these AI image generation scripts requires the 'uv' binary to be installed and the 'GEMINI_API_KEY' environment variable to be configured. These prerequisites allow the scripts to authenticate and communicate with the API.

Can I specify different resolutions and aspect ratios for generated images?▼

Yes, the image generation process supports various resolutions and aspect ratios. You can specify these parameters within your API request to ensure the output image matches your specific dimensional requirements.

What is the best way to automate AI art creation without complex design software?▼

Automating AI art creation without complex design software is done by using script-based API calls to generate and edit images from text prompts. This approach eliminates manual editing by directly processing instructions through the Gemini model.

Related Skills

Explore More Design & Creative Skills→
codatacodata
8

translator

Detect source languages and translate text or video scripts into English.

Official
Intermediate
rezosndrezosnd

remove-image-background

Remove backgrounds from image files and output transparent PNGs.

Community
Basic
marioluciofjrmarioluciofjr
12

prompt-personagem

Generate detailed character prompts for AI image generation from predefined attribute lists.

Community
Intermediate
ToqsickToqsick

creative-suite

Generate ASCII art, diagrams, infographics, comics, and pixel art.

Community
Advanced