skills.rest
emdashcodes
emdashcodesCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

nano-banana-image-editor

Edit and create images using natural language prompts via Gemini 3 Pro Image.

13|1|Updated Oct 18, 2025
Search Tags:#image-generation#image-editing#style-transfer#reference-images#natural-language-prompts#google-grounding
One-click install
npx skills add https://github.com/emdashcodes/claude-code-plugins --skill nano-banana-image-editor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-image-editor
Source: https://github.com/emdashcodes/claude-code-plugins/tree/main/plugins/nano-banana-image-editor/skills/nano-banana-image-editor
Command: npx skills add https://github.com/emdashcodes/claude-code-plugins --skill nano-banana-image-editor

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Edit and create images using natural language prompts, eliminating tedious manual editing and iteration overhead.

Core Features & Use Cases

  • Edit existing images with text prompts for background changes, object removal/addition, text overlays, and color adjustments.
  • Generate new images from prompts, with support for reference images for style transfer and character consistency.
  • Ground real-time information via Google Search grounding for facts in infographics or data-driven visuals.

Quick Start

Use the nano-banana-image-editor to edit images by providing an input image, an output path, and a natural language instruction, e.g., input.png, output.png, 'Change the background to a gradient blue'.

Frequently Asked Questions about nano-banana-image-editor

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

FAQPage Schema
How do I edit images using natural language prompts?▼

Image editing with natural language prompts is done by providing an input image, an output path, and a text instruction to modify backgrounds, remove objects, or add text overlays. This eliminates manual editing by processing changes directly.

Can I use reference images for style transfer and multi-image blending?▼

Yes, reference images can be used for style transfer and character consistency. The process supports multi-image blending by accepting up to 14 images per request to generate new visuals based on provided references.

Do I need a Google API key to generate images with Gemini?▼

A configured Google API key is required to generate images with Gemini. You must also install the necessary dependencies, specifically the google-genai and Pillow packages, using the included setup scripts before executing edits.

How does Google Search grounding work for data-driven infographics?▼

Google Search grounding for data-driven infographics works by optionally integrating real-time information retrieval into the image generation process. This ensures that facts and data visualized in infographics are accurate and up-to-date.

What are the limitations of using text prompts for image editing?▼

Limitations of using text prompts for image editing include reliance on natural language accuracy for desired outputs and the specific constraints of the Gemini 3 Pro Image model. Complex edits might require precise wording to achieve accurate visual results.

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
tiankong0101-bytetiankong0101-byte

nano-banana-pro

Generate and edit images with Google's Nano Banana Pro model, exporting PNGs.

Community
Advanced
rmjamesrmjames
1

image-processor

Resize and crop raster and SVG images with ImageMagick and SVGO.

Community
Advanced
SpaceZephyrSpaceZephyr
127

space-gemini-image

Convert text descriptions and image references into generated images.

Community
Intermediate