skills.rest
javierd009
javierd009COMMUNITY
Explore all skills by this author →
GitHub

nano-banana-image-combine

Merge 2-8 base64 or URL images into one composite via OpenRouter.

Updated Aug 23, 2026
Search Tags:#photo editing#gemini#openrouter#image combination#face swap#background replacement#ai art
One-click install
npx skills add https://github.com/javierd009/sitnova --skill nano-banana-image-combine-javierd009
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-image-combine
Source: https://github.com/javierd009/sitnova/tree/main/.claude/skills/nano-banana-image-combine
Command: npx skills add https://github.com/javierd009/sitnova --skill nano-banana-image-combine-javierd009

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill leverages Google's Gemini 2.5 Flash (Nano Banana) via OpenRouter to intelligently combine multiple images, solving complex photo manipulation tasks like face swapping, background replacement, and AI-guided collages that would otherwise require manual graphic design.

Core Features & Use Cases

  • Multi-Image Composition: Merge 2-8 images into a single, cohesive composition with AI guidance.
  • Face Swapping & Background Replacement: Perform advanced photo editing tasks with natural blending.
  • AI-Guided Collages & Thumbnails: Create artistic collages or engaging YouTube thumbnails from multiple sources.
  • Use Case: A content creator needs to quickly generate a YouTube thumbnail by combining a portrait of themselves with a dynamic background and overlaying text. This skill automates the complex composition, ensuring professional results.

Quick Start

To combine images with Nano Banana, first install: pip install httpx python-dotenv pydantic pillow base64 Then, set your OPENROUTER_API_KEY and FRONTEND_URL in your .env file. Encode your image URLs to base64 and send them with a prompt to the OpenRouter API.

Frequently Asked Questions about nano-banana-image-combine

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

FAQPage Schema
How do I combine multiple images into a single composite with AI guidance?▼

Image combination merges 2-8 photos into one cohesive composite using AI. This skill uses Gemini 2.5 Flash via OpenRouter to intelligently blend images for face swapping, background replacement, collages, and thumbnails. Provide base64-encoded or URL-sourced images with a descriptive prompt to generate your result.

Can I use AI to automatically swap faces or replace backgrounds in photos?▼

Yes, face swapping and background replacement are core capabilities. The skill accepts multiple images and processes them through Gemini 2.5 Flash with natural blending. Results output as a URL or base64 payload along with the prompt used for reproducibility.

What image formats and sources does this support for composition?▼

The skill accepts base64-encoded images or URL-sourced images as input. You supply 2-8 images with a text prompt describing the desired composition, and it outputs a composite image URL or base64 payload from the Gemini model.

Do I need an API key or special setup to combine images with this skill?▼

Yes, you need an OpenRouter API key and a frontend URL configured in your .env file. Install dependencies via pip (httpx, python-dotenv, pydantic, pillow, base64). Once configured, encode images and send them with your composition prompt to the API.

What's the best way to create YouTube thumbnails by combining multiple image sources?▼

This skill automates thumbnail creation by merging portrait, background, and overlay elements into a single composite. Provide images and describe your desired layout in text; the AI handles blending and composition to produce professional results without manual graphic design.

What are the limits on image count and composition complexity?▼

The skill supports merging 2-8 images per request. Complexity depends on your prompt clarity and the Gemini model's interpretation. Results include the generated prompt for verification, helping you refine inputs if adjustments are needed.

Related Skills

Explore More Design & Creative Skills→
NikGorNikGor

openrouter-research

Research OpenRouter API details for Grok model IDs and vision support.

Community
Intermediate
Marky-TeamMarky-Team
3

schedule-posts

Schedule and publish social media posts with captions and media via the Marky API.

Official
Advanced
jasrajtulsijasrajtulsi

generate-image

Generate or edit images from text prompts via OpenRouter models.

Community
Intermediate
ViewWayViewWay

Image Editing

Automate image editing tasks including inpainting, outpainting, background removal, upscaling, restoration, and style transfer.

Community
Intermediate