skills.rest
openaeon
openaeonCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate or edit PNG images from text prompts using Gemini 3 Pro Image API.

87|20|Updated Mar 9, 2026
Search Tags:#png#image generation#image editing#gemini#prompt to image#media attachment
One-click install
npx skills add https://github.com/openaeon/OpenAEON --skill nano-banana-pro-openaeon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/openaeon/OpenAEON/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/openaeon/OpenAEON --skill nano-banana-pro-openaeon

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of creating or revising images by turning text prompts (and optional input images) into finished PNGs using Gemini 3 Pro Image.

Core Features & Use Cases

  • Image generation from prompts: Create a brand-new image from a detailed description for concepts, thumbnails, and visual drafts.
  • Image editing and composition: Edit a single image with instructions or combine multiple images (up to 14) into one coherent scene.
  • OpenAEON-ready output handling: Prints a MEDIA: path so OpenAEON can automatically attach the generated image in supported chat providers.

Quick Start

Use the nano-banana-pro skill to generate an image from the prompt "a futuristic city at sunset, cinematic lighting" and save it as output.png.

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 a PNG image from a text prompt using Gemini?▼

To generate a PNG image from a text prompt using Gemini, you provide a descriptive text string to the API. The script processes this prompt using Google's Gemini 3 Pro Image API and saves the returned inline image data as a PNG file.

Can I edit an existing image with text instructions using the Gemini API?▼

Yes, you can edit an existing image by providing the input image alongside text instructions. The Skill supports single-image editing to apply specific revisions based on your descriptive text prompt.

How many images can I combine into a single scene during image composition?▼

You can combine up to 14 input images into one coherent scene during image composition. The Skill processes these multiple input images together to generate a single combined PNG output.

Do I need an API key to generate images with Gemini 3 Pro?▼

Yes, you need a GEMINI_API_KEY to authenticate your requests when generating images with Gemini 3 Pro. This key is required for the script to access the Google API and process your image generation or editing prompts.

How does the script handle generated image outputs for chat providers?▼

The script handles generated image outputs by converting the returned inline image data into a saved PNG file. It then prints a MEDIA attachment line with the file path, allowing supported chat providers to automatically attach the image.

Related Skills

Explore More Design & Creative Skills→
tamireslaeao-progtamireslaeao-prog

nano-banana-pro

Generate or edit Gemini 3 Pro images from prompts and input images, saving PNG outputs.

Community
Advanced
mjunaidcamjunaidca
27

datetime-timezone

Convert browser local datetimes to UTC for API submission and back for display.

Community
Intermediate
CristoVenturesCristoVentures
2

gemini-imagegen

Generate and edit images via the Gemini API from text prompts.

Official
Advanced
MicrockMicrock
322

generate-image

Generate or edit scientific visuals from text prompts and optional input images.

Community
Advanced