nano-banana

Name: nano-banana
Availability: InStock
Author: OpenMinis

Generate and edit images via Google's Gemini Nano Banana API.

361|58|Updated Mar 1, 2026

Search Tags:#image-generation #nanobanana #batch-processing #image-editing #ai-art #gemini-api #prompt-tuning

Ready to run

npx skills add https://github.com/OpenMinis/MinisSkills --skill nano-banana-openminis

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate or edit AI-generated images using Google's Gemini Nano Banana API, enabling instant visual creation and image transformations without manual, repetitive editing.

Core Features & Use Cases

Text-to-image generation, image editing, and batch generation using the bundled scripts gen.py, edit.py, and batch.py.
Local environment validation and model selection with a default Gemini model for fast, high-quality output.
Output handling to /var/minis/attachments and inline display of results in conversations.
Use Case: designers, marketers, and content creators can rapidly generate visuals for campaigns, social media, and product mockups.

Quick Start

Tell Nano Banana to generate or edit an image with a prompt and optional input image, and the tool will save the result to the attachments directory.

Frequently Asked Questions about nano-banana

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate AI images using the Gemini API?▼

You can generate AI images by providing a text prompt to the tool, which uses the Gemini API to create the visual and saves the output to the local attachments directory.

Can I edit existing images with AI without manual photo editing?▼

Yes, you can edit existing images with AI by providing an input image and a prompt to the editing script, allowing the Gemini API to transform the visual automatically without manual adjustments.

What is batch image generation and how does it work for marketing assets?▼

Batch image generation processes multiple prompts sequentially to produce a volume of AI-generated visuals, enabling marketers and designers to rapidly create campaign or social media assets at scale.

Do I need a Gemini API key to run AI image generation scripts?▼

Yes, you need a Gemini API key configured as an environment variable to authenticate requests, alongside a local Python environment to execute the bundled generation and editing scripts.

Where are the generated AI images saved after processing?▼

Generated AI images are saved directly to the local attachments directory, ensuring outputs are stored locally and can be displayed inline within your active conversation interface.

Are there limitations when using the Gemini API for image editing?▼

Limitations include relying on an active Gemini API key and Python environment, as the tool processes text-to-image and editing tasks strictly through bundled scripts without a graphical interface.