skills.rest
horuz-ai
horuz-aiOFFICIAL
Explore all skills by this author →
GitHub

nano-banana

Generate and edit images from text prompts and input images via Nano Banana APIs.

5|2|Updated Dec 1, 2025
One-click install
npx skills add https://github.com/horuz-ai/claude-plugins --skill nano-banana
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/horuz-ai/claude-plugins/tree/main/plugins/google/skills/nano-banana
Command: npx skills add https://github.com/horuz-ai/claude-plugins --skill nano-banana

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables rapid AI-powered image generation and editing using Google's Nano Banana family (Gemini 2.5 Flash Image and Gemini 3 Pro Image) with prompts, edits, and multi-image compositions.

Core Features & Use Cases

  • Text-to-image generation
  • Image editing (add/remove elements)
  • Multi-image composition (Pro)
  • Text rendering in images and style transfer
  • Iterative refinement and real-time collaboration

Quick Start

Set GEMINI_API_KEY in your environment and use the provided Python scripts to generate or edit images, e.g., python scripts/generate_image.py "A cozy cafe interior" --output coffee.png

Frequently Asked Questions about nano-banana

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 uses the Nano Banana APIs to create images from natural language descriptions. Set your GEMINI_API_KEY environment variable and run the provided Python script with your prompt—for example, `python scripts/generate_image.py "A cozy cafe interior" --output coffee.png`—to produce images in seconds.

Can I edit existing images with AI, and what formats does it support?▼

Image editing with Nano Banana lets you add, remove, or modify elements in existing images through text instructions. The Skill accepts input images up to 5MB encoded as base64 data in the API payload, enabling iterative refinement of your edits.

What's the difference between Gemini Flash and Pro image models?▼

Gemini 2.5 Flash Image prioritizes speed for rapid prototyping, while Gemini 3 Pro Image includes multi-image composition—combining multiple images into a single output—along with enhanced text rendering, style transfer, and character consistency across generations.

Do I need to configure image size and aspect ratio, and how?▼

Yes. The Skill supports imageConfig parameters for aspectRatio and imageSize to control output dimensions. Specify these in your API request alongside responseModalities (TEXT and IMAGE) to tailor generation to your needs.

Can I use Google Search grounding with image generation for real-world context?▼

Optional Google Search grounding via tools is available, allowing the model to incorporate current information into generated or edited images for use cases requiring real-world accuracy or up-to-date visual references.

What authentication and environment setup do I need to get started?▼

Set the GEMINI_API_KEY environment variable with your API credentials before running any scripts. This is the required authentication for all Nano Banana API calls—no additional setup is needed to begin generating or editing images.

Related Skills

bahayonghangbahayonghang
16

gemini-image

Generate images from text prompts or reference images via the Gemini API.

Community
Basic
cdrgurucdrguru
1

imagegen

Generate and edit images via the OpenAI Image API with a bundled CLI.

Community
Advanced
OpenMinisOpenMinis
361

nano-banana

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

Official
Advanced
eyadsibaieyadsibai
7

multimodal-models

Access pre-trained CLIP, Whisper, and Stable Diffusion models for vision, audio, and cross-modal tasks.

Community
Advanced