nano-banana

Generate images from text prompts via Google Nano Banana with adjustable models and resolutions.

15|5|Updated Dec 5, 2025
One-click install
npx skills add https://github.com/rebyteai-template/rebyte-skills --skill nano-banana-rebyteai-template
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/rebyteai-template/rebyte-skills/tree/main/nano-banana
Command: npx skills add https://github.com/rebyteai-template/rebyte-skills --skill nano-banana-rebyteai-template

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill allows users to generate unique images from textual descriptions, transforming creative ideas into visual realities without needing advanced design skills.

Core Features & Use Cases

  • Text-to-Image Generation: Create diverse images based on detailed prompts.
  • Model Selection: Choose between 'flash' for speed and 'pro' for higher quality and resolution (up to 4K).
  • Aspect Ratio Control: Specify desired image dimensions for various platforms.
  • Use Case: A marketer needs a unique banner image for a social media campaign. They provide a prompt like "A vibrant, abstract representation of digital connection with glowing lines on a dark background" and receive a custom image.

Quick Start

Use the nano-banana skill to generate an image of a futuristic cityscape at sunset with flying cars.

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?

To generate images from text, you provide descriptive prompts to the nano-banana skill, which uses Google Gemini image generation via the eng0 API to create custom visuals and illustrations.

Can I generate 4K resolution AI art with adjustable aspect ratios?

Yes, you can generate 4K resolution AI art by selecting the 'pro' model option, and you can specify adjustable aspect ratios to fit various platform dimensions for your visual creation.

What is the difference between flash and pro models for AI image generation?

For AI image generation, the 'flash' model offers faster processing speeds, while the 'pro' model provides higher quality output and supports resolutions up to 4K for detailed artwork.

Do I need advanced design skills to create custom visuals from text?

No, you do not need advanced design skills to create custom visuals; this text-to-image generation transforms your descriptive text prompts into unique visual realities automatically.

What are the limitations when using text-to-image generation for custom visuals?

Limitations for text-to-image generation include dependency on the eng0 data API connectivity and the inherent quality constraints of the 'flash' model compared to the 'pro' model for complex artwork.