nano-banana-pro

Name: nano-banana-pro
Availability: InStock
Author: iliagerman

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

1|Updated Jan 30, 2026

Search Tags:#image generation #visual content #Gemini #image editing #AI art #text-to-image

Ready to run

npx skills add https://github.com/iliagerman/mordecai --skill nano-banana-pro-iliagerman

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the creation and modification of images using AI, allowing users to generate new visuals from text prompts or edit existing images with specific instructions.

Core Features & Use Cases

Text-to-Image Generation: Create unique images based on detailed text descriptions.
Image Editing: Modify existing images by providing instructions on desired changes.
Resolution Control: Supports 1K, 2K, and 4K resolutions, with a default to 1K for efficiency.
Use Case: Generate a marketing banner for a new product, or edit a photograph to remove an unwanted object.

Quick Start

Generate a new image by describing it in natural language.

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?▼

Yes, you can edit existing images by providing specific modification instructions to the Gemini API. This image-to-image transformation capability allows you to alter visuals, such as removing unwanted objects from photographs.

What resolutions are supported for AI image generation?▼

AI image generation supports configurable resolutions of 1K, 2K, and 4K. The system defaults to 1K resolution to ensure processing efficiency, but you can specify higher resolutions like 4K for detailed visual content.

Do I need a GEMINI_API_KEY to use this image generation tool?▼

Yes, a GEMINI_API_KEY is required for authentication to use this image generation tool. You must configure this key within the Python environment that utilizes the google-genai and Pillow libraries for image manipulation.

Does the Gemini image API work with Python for automated image editing?▼

Yes, the Gemini image API works with Python through the google-genai library for automated image editing. Combined with the Pillow library, the Python scripts can programmatically apply text-to-image and image-to-image transformations.

What are the limitations of using AI for image-to-image transformations?▼

Limitations for image-to-image transformations include dependency on the Gemini 3 Pro Image API's capabilities and the need for precise text instructions. Complex modifications may require iterative prompting to achieve the desired visual result.