skills.rest
qsimeon
qsimeonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

nano-banana-pro

Generates and edits images using the Gemini 3 Pro Image API.

1|1|Updated Feb 17, 2026
Search Tags:#image generation#multimodal#image editing#gemini#ai art#creative ai
One-click install
npx skills add https://github.com/qsimeon/openclaw-engaging --skill nano-banana-pro-qsimeon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/qsimeon/openclaw-engaging/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/qsimeon/openclaw-engaging --skill nano-banana-pro-qsimeon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pillow, and 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 graphic design software or manual editing for many tasks.

Core Features & Use Cases

  • Image Generation: Create new images from detailed text prompts.
  • Image Editing: Modify existing images based on instructions, such as changing styles or adding elements.
  • Multi-Image Composition: Combine multiple input images into a single scene or collage.
  • Use Case: Generate a realistic image of a "cyberpunk cat wearing sunglasses" or edit a photo to "make the sky look more dramatic."

Quick Start

Use the nano-banana-pro skill to generate an image of a futuristic city at sunset 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 prompts using Gemini?▼

To generate images from text prompts using Gemini, you use the Gemini 3 Pro Image model to process detailed descriptions and produce new visual assets. This approach automates image creation without requiring complex graphic design software.

Can I edit existing images by providing text instructions to AI?▼

You can edit existing images by providing text instructions to AI models like Gemini. The model modifies your original photo based on commands, enabling tasks like changing styles or adding elements without manual graphic editing effort.

Do I need a specific API key to use the Gemini image generation model?▼

You need a GEMINI_API_KEY to use the Gemini image generation model. The Python scripts utilize the google-genai library for API interaction, requiring this specific environment configuration to authenticate and process your image requests.

What's the best way to combine multiple images into a single scene with AI?▼

The best way to combine multiple images into a single scene with AI is using multi-image composition features. The Gemini model processes several input images simultaneously to merge them into a cohesive collage or unified visual output.

Does the Gemini image editing API work with Python and Pillow?▼

The Gemini image editing API works with Python using the google-genai and Pillow libraries. These dependencies handle API interaction and image manipulation, allowing you to save your generated or modified images directly as PNG files.

Related Skills

Explore More Design & Creative Skills→
dfpalhanodfpalhano

google-web-search

Execute Google Search within Gemini models for grounded, cited answers.

Community
Intermediate
SJTU-IPADSSJTU-IPADS
7

image-utils

Automate deterministic image editing tasks on image collections with Pillow.

Official
Intermediate
zrt-ai-labzrt-ai-lab
266

image-service

Generate, edit, and analyze multimodal images via prompts and references.

Community
Advanced
antoniolgantoniolg
97

nano-banana-pro

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

Community
Advanced