nano-banana-2

Generate and edit images via Google Gemini 3.1 Flash using the inference.sh CLI.

1|Updated Mar 9, 2026

Search Tags:#image generation #image editing #gemini #text-to-image #ai art #inference.sh

Ready to run

npx skills add https://github.com/docaohieu2808/claude-skills --skill nano-banana-2-docaohieu2808

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-2
Source: https://github.com/docaohieu2808/claude-skills/tree/main/nano-banana-2
Command: npx skills add https://github.com/docaohieu2808/claude-skills --skill nano-banana-2-docaohieu2808

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to generate new images from text prompts and edit existing images using natural language, overcoming the limitations of manual image creation tools.

Core Features & Use Cases

Text-to-Image Generation: Create unique images based on descriptive text prompts.
Image Editing: Modify existing images by describing the desired changes (e.g., "add a hat").
High-Resolution Output: Generate images up to 4K resolution.
Search Grounding: Incorporate real-time information from Google Search for contextually relevant images.
Use Case: Generate a photorealistic image of a "cat astronaut on the moon" or edit a photo of a park by adding "a hot air balloon in the sky."

Quick Start

Generate an image of a banana in space using the nano-banana-2 skill.

Frequently Asked Questions about nano-banana-2

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

FAQPage Schema

How do I generate images from text prompts using Gemini?▼

Text-to-image generation with Gemini is achieved by providing descriptive text prompts to the inference.sh CLI, which then creates unique images based on your natural language input.

Can I edit existing images with natural language commands?▼

Yes, image editing with natural language is supported by submitting an existing image and describing the desired modifications, allowing the Gemini model to apply changes like adding objects to a scene.

Does this text-to-image tool support high-resolution 4K output?▼

Yes, the skill supports high-resolution image generation up to 4K, and also allows you to specify variable aspect ratios to fit different formatting requirements.

How does Google Search grounding work for AI art generation?▼

Google Search grounding incorporates real-time information into the AI art generation process, providing contextually relevant and up-to-date details to ensure accurate image creation.

What is the best way to automate image generation deterministically?▼

Deterministic image generation is handled by utilizing bash scripts that execute tasks via the inference.sh CLI, ensuring consistent and automated text-to-image or image editing workflows.