nano-banana-pro

Generate and edit images with Gemini 3 Pro Image API.

5|Updated Jan 31, 2026

Search Tags:#api #image generation #prompt design #image editing #gemini #multi-image #png output

Ready to run

npx skills add https://github.com/kcns008/clusterclaw --skill nano-banana-pro-kcns008

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/kcns008/clusterclaw/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/kcns008/clusterclaw --skill nano-banana-pro-kcns008

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

It removes the friction of creating or revising images by turning a natural-language prompt and optional reference images into a finished visual output.

Core Features & Use Cases

Image Generation: Create a brand-new image from a text prompt using Gemini 3 Pro Image.
Image Editing: Modify one image or combine multiple images into a single composed result.
Practical Workflow: Use it for concept art, marketing visuals, social graphics, and rapid visual iteration with automatic output saving and resolution handling.

Quick Start

Use the nano-banana-pro skill to create a 2K image of a futuristic neon city at sunset and save it as output.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 and edit images using the Gemini API?▼

You can generate and edit images using the Gemini API by providing a natural-language text prompt and optional reference images. The skill handles text-to-image creation, single-image editing, and multi-image composition, outputting a finished PNG file.

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

Yes, you can combine multiple images into one composed result with Gemini 3 Pro Image. The skill supports multi-image composition workflows, allowing you to merge several input images into a single visual output.

What do I need to set up before generating images with this API tool?▼

Before generating images, you need a valid Gemini API key and Python image-processing dependencies installed. The environment requires the google-genai and pillow libraries to manage resolution selection and PNG output.

What is the best way to create marketing visuals from text prompts?▼

The best way to create marketing visuals from text prompts is using an AI image generation tool that supports natural-language input. This skill turns your descriptive text directly into high-resolution PNG assets for rapid visual iteration.

Does this image generation method automatically save the output file?▼

Yes, this image generation method automatically saves the output file. It manages resolution selection and error-checked API execution to ensure your generated or edited image is securely saved as a PNG file.