nano-banana-pro

Automate image generation and editing via the Gemini 3 Pro Image API.

Updated Apr 6, 2026

Search Tags:#graphics #composition #image-generation #prompt-engineering #ai-art #gemini-pro #photo-editing

Ready to run

npx skills add https://github.com/dakshrawat298-gif/SOL-ALPHA-GUARDIAN --skill nano-banana-pro-dakshrawat298-gif

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/dakshrawat298-gif/SOL-ALPHA-GUARDIAN/tree/main/packages/skills/skills/nano-banana-pro
Command: npx skills add https://github.com/dakshrawat298-gif/SOL-ALPHA-GUARDIAN --skill nano-banana-pro-dakshrawat298-gif

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai>=1.0.0, pillow>=10.0.0, and includes scripts (resource) components.

What problem does it solve?

Gemini 3 Pro Image enables rapid creation and editing of visuals from text prompts or input images, streamlining the design workflow and enabling quick iteration for creative tasks.

Core Features & Use Cases

Text-to-Image Generation: Create visuals from descriptive prompts.
Single-Image Editing: Refine or modify existing images with prompts.
Multi-Image Composition: Combine several inputs into a single scene for concept art or marketing visuals.
Use Case: A designer can quickly prototype campaign visuals by generating variants from prompts and applying edits to meet brand standards.

Quick Start

Provide a prompt to generate an image or upload an image with edit instructions to create the desired visual.

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 the Gemini API?▼

Text-to-image generation with the Gemini API requires a descriptive prompt to create visuals. This Skill automates that process by sending your prompt to the Gemini 3 Pro Image API and retrieving the generated visual output.

Can I combine multiple images into one scene with Gemini 3 Pro?▼

Yes, multi-image composition combines several input images into a single scene. This is useful for creating concept art or marketing visuals by leveraging the Gemini integration within your design workflow.

How do I edit an existing image using an AI prompt?▼

Single-image editing modifies existing images by applying text instructions. You provide an input image along with edit prompts, and the Gemini 3 Pro Image API refines or alters the visual accordingly.

Do I need an API key to use Gemini for image generation?▼

Yes, Gemini integration requires an active API key to access the Gemini 3 Pro Image API. You must configure this key in your environment to automate text-to-image generation and image editing tasks.

What are the limitations of using AI art for design workflows?▼

AI art generation accelerates rapid visual prototyping but may require further refinement. It relies on prompt engineering accuracy and API availability, making it best suited for quick iteration rather than final brand assets.

Is Pillow required for AI image composition and editing?▼

Yes, the Pillow library is a required dependency for handling image files. It works alongside the Google GenAI package to process, save, and manage the images generated or edited through the API.