skills.rest
mycelium-hq
mycelium-hqOFFICIAL
Explore all skills by this author →
GitHub

nano-banana

Generate, edit, and compose images with Gemini 3 Pro.

31|20|Updated Apr 9, 2026
Search Tags:#composition#image-generation#infographic#image-editing#logo#multi-image#ai-art
One-click install
npx skills add https://github.com/mycelium-hq/ai-brain-starter --skill nano-banana-mycelium-hq
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/mycelium-hq/ai-brain-starter/tree/main/skills/nano-banana
Command: npx skills add https://github.com/mycelium-hq/ai-brain-starter --skill nano-banana-mycelium-hq

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Create, edit, and compose high-quality visuals efficiently using Gemini 3 Pro, reducing manual design toil and iterations.

Core Features & Use Cases

  • Text-to-image generation, image editing, and multi-image composition (up to 14 reference images).
  • Iterative refinement with interactive prompts, enabling quick design exploration for logos, thumbnails, infographics, and product shots.
  • Real-time data-grounded image generation via Google Search integration for up-to-date visuals.

Quick Start

Generate a photorealistic product shot of a blue ceramic mug on a white background.

Frequently Asked Questions about nano-banana

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

FAQPage Schema
How do I generate and iterate on AI images using Gemini?▼

To generate and iterate on AI images, you provide text prompts to the interactive chat script, which uses Gemini to produce and refine visuals like logos or infographics. You can iteratively adjust designs through quick text-based refinements.

Can I compose multiple images into a single graphic with Gemini Pro?▼

Yes, you can compose multiple images by supplying up to 14 reference images to the composition script. Gemini Pro merges these inputs to create unified graphics, suitable for product shots and complex infographics.

What do I need to set up before using this image generation workflow?▼

You need a valid GEMINI_API_KEY and Python dependencies installed, specifically the google-genai and Pillow libraries. These prerequisites enable the scripts to execute image generation, editing, and composition tasks.

Does this approach support real-time data-grounded image generation?▼

Yes, the workflow supports real-time data-grounded image generation via Google Search integration. This allows you to create up-to-date visuals and infographics based on current information.

What is the best way to edit an existing image using Gemini?▼

The best way to edit an existing image is to use the dedicated edit_image script. This automates the image editing process through Gemini, allowing you to apply modifications and refine visuals efficiently.

Are there limitations when compositing multiple reference images?▼

The main limitation for multi-image composition is that you can supply a maximum of 14 reference images for a single generation task. Exceeding this constraint may require batch processing or manual merging.

Related Skills

Explore More Design & Creative Skills→
tense-itense-i
1

nanobanana-skill

Generate or edit images from prompts using the Google Gemini API.

Community
Intermediate
zhangdszqzhangdszq
1

baoyu-infographic

Convert content into publication-ready infographics with 20 layouts and 17 visual styles.

Community
Intermediate
tdiminotdimino
41

nano-banana-pro

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

Community
Advanced
snake-dev-teamsnake-dev-team

ckm:design

Generate logos, corporate identity programs, and SVG icons with Gemini AI.

Official
Advanced