nano-banana-pro

Generate or edit images with Gemini 3 Pro Image and output PNG files.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/Kastalien-Research/kastalien-factory --skill nano-banana-pro-kastalien-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/Kastalien-Research/kastalien-factory/tree/main/lettabot/.skills/nano-banana-pro
Command: npx skills add https://github.com/Kastalien-Research/kastalien-factory --skill nano-banana-pro-kastalien-research

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generating or editing visuals currently requires manual effort, several tools, and repeated steps; this Skill automates that workflow with Gemini 3 Pro Image.

Core Features & Use Cases

  • Generate images from prompts at 1K, 2K, or 4K resolutions.
  • Edit existing images by providing prompts and optional input images (up to 14).
  • Create composite scenes by merging multiple inputs into a single output.
  • Manage API access via GEMINI_API_KEY or clawdbot.json configuration.

Quick Start

Run the bundled script with a prompt and optional input images to generate or edit a final image.

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?▼

Generate images from text prompts using Gemini by providing a prompt to the script, which outputs a PNG file. Resolution options include 1K, 2K, or 4K.

Can I edit existing images with Gemini 3 Pro Image?▼

Edit existing images with Gemini 3 Pro Image by providing an edit prompt and up to 14 optional input images. The script processes the request and outputs a modified PNG file.

Do I need a Gemini API key to generate AI art?▼

A Gemini API key is required to generate AI art. Configure it using the GEMINI_API_KEY environment variable or define it within the clawdbot.json configuration file.

What is the best way to merge multiple images into a single composition?▼

Merge multiple images into a single composition by supplying up to 14 input images and a prompt to the script. Gemini 3 Pro Image generates a unified composite PNG output.

Does Gemini image generation support 4K resolution output?▼

Gemini image generation supports 4K resolution output. The script allows you to specify 1K, 2K, or 4K resolutions for both prompt-based generation and multi-image compositions.

Why does my Gemini image generation script signal completion via a MEDIA line?▼

Gemini image generation signals completion via a MEDIA line to indicate the output PNG file is ready. This line confirms the image processing workflow has successfully finished.