skills.rest
landfill
landfillCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

nano-banana-pro

Generate images from text prompts using Google's Nano Banana Pro model.

Updated Dec 26, 2025
One-click install
npx skills add https://github.com/landfill/devtool-and-rule --skill nano-banana-pro-landfill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/landfill/devtool-and-rule/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/landfill/devtool-and-rule --skill nano-banana-pro-landfill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai.

What problem does it solve?

Generates data-accurate infographics and visuals using Google's Nano Banana Pro model, suitable for charts, maps, and text-rendered visuals.

Core Features & Use Cases

  • Grounded generation: Uses Google Search grounding for data-backed visuals
  • Text rendering: High-quality text within images
  • Infographics & Visualizations: Charts, maps, and complex visuals
  • Usage: Create data-driven infographics with labeled axes

Quick Start

uv run generate_image.py "Population growth from 2010 to 2025" -o growth.png --aspect-ratio 16:9

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 Google's image generation model?▼

Generate images from text prompts using Google's Nano Banana Pro model by running `uv run generate_image.py "your prompt" -o output.png` with a GEMINI_API_KEY set in your environment. The model renders text-accurate visuals suitable for infographics, charts, and diagrams.

Can I create data-accurate infographics and visualizations with text labels?▼

Yes. Nano Banana Pro uses Google Search grounding to generate data-backed visuals with high-quality text rendering, making it ideal for charts, maps, and infographics where labeled axes and accurate information matter.

What are the requirements to use this image generation tool?▼

You need a GEMINI_API_KEY environment variable, Python with uv, and the google-genai dependency. Invocation requires a text prompt and output path; optional parameters include aspect-ratio and size for customization.

How do I control the dimensions and aspect ratio of generated images?▼

Specify `--aspect-ratio` (e.g., 16:9) and `--size` parameters when running the command. Example: `uv run generate_image.py "your prompt" -o image.png --aspect-ratio 16:9` adjusts output dimensions.

What types of visuals work best with this image generation approach?▼

Complex visuals requiring accurate data and text rendering work best: population charts, geographic maps, labeled infographics, and diagrams. Grounded generation ensures information accuracy in rendered output.

Does this tool require specific knowledge of the underlying model API?▼

No. The Skill abstracts the gemini-3-pro-image-preview model; you provide a prompt, output path, and optional sizing parameters via command-line arguments without direct API interaction.

Related Skills

aryaxtaryaxt

generate-image

Generate single or batch images using Google Gemini's image generation API.

Community
Intermediate
pkoka888pkoka888
1

image-enhancer

Upscale image resolution, sharpen details, and reduce compression artifacts.

Community
Intermediate
zhouboyu-xrealzhouboyu-xreal

baoyu-comic

Generate knowledge comics from text descriptions using image generation services.

Community
Advanced
ElwinLiuElwinLiu

umple-diagram-generator

Convert natural language requirements into Umple diagrams and SVG visuals.

Community
Advanced