nano-banana-pro

Generates and edits images using Gemini 3 Pro Image API with multi-image composition support.

Updated Feb 8, 2026

Search Tags:#image generation #image editing #AI art #Gemini 3 Pro Image API #prompt-based image creation

Ready to run

npx skills add https://github.com/dioerden/OpenClaw-Flash-Vault --skill nano-banana-pro-dioerden

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/dioerden/OpenClaw-Flash-Vault/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/dioerden/OpenClaw-Flash-Vault --skill nano-banana-pro-dioerden

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires uvicorn, uvicorn-gemini, and includes scripts (resource) components.

What problem does it solve?

This Skill allows users to generate or edit images using the Gemini 3 Pro Image API, offering a simple and efficient way to create visual content.

Core Features & Use Cases

Image Generation: Generate images based on descriptive prompts.
Image Editing: Edit existing images with new prompts.
Multi-image Composition: Combine multiple images into a single scene.
Use Case: A designer can quickly create concept art or edit product images for a marketing campaign.

Quick Start

Generate an image by running the following command:

uv run generate_image.py --prompt "a futuristic cityscape" --filename "futuristic_city.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 using the Gemini 3 Pro Image API?▼

To generate images using the Gemini 3 Pro Image API, you run a Python script with uvicorn dependencies, providing a descriptive prompt, filename, and resolution to create the visual content.

Can I edit existing images and combine multiple images into one scene?▼

Yes, you can edit existing images with new prompts and perform multi-image composition to combine multiple separate images into a single unified scene using the API.

Do I need a specific Python environment to use prompt-based image creation?▼

Yes, prompt-based image creation requires a Python environment configured with uvicorn and uvicorn-gemini dependencies to execute the generation and editing scripts successfully.

What is the best way to create 2K resolution concept art from text prompts?▼

The best way to create 2K resolution concept art from text prompts is by running the generation script with the desired prompt and specifying the 2K resolution parameter in your command.

How does multi-image composition work when editing images with prompts?▼

Multi-image composition works by taking multiple existing images and applying prompt-based editing to merge them together, allowing you to combine separate visual elements into a single cohesive output.