Automated Object Detection with Google Gemini and Visual Bounding Boxes
detail.loadingPreview
This workflow showcases powerful AI-driven object detection using Google Gemini 2.0. It automatically identifies specific objects in an image, then precisely draws bounding boxes around them, providing clear visual results without complex coding.
About This Workflow
Unlock the power of visual AI with this n8n workflow for automated object detection. It begins by fetching an image, then leverages the advanced capabilities of Google Gemini 2.0 to identify and locate specified objects, such as rabbits in the example. The workflow intelligently processes Gemini's normalized bounding box coordinates, scaling them to the original image dimensions using a custom code node. Finally, it visually overlays these accurate bounding boxes directly onto the image, offering an intuitive and actionable output. This setup is perfect for developers and businesses looking to integrate sophisticated computer vision tasks into their automated processes seamlessly.
Key Features
- Google Gemini 2.0 Integration: Directly connect to Google's cutting-edge multimodal AI for powerful object detection.
- Dynamic Image Analysis: Automatically retrieve images from URLs and extract essential metadata like dimensions.
- Custom Coordinate Scaling: Precisely convert normalized AI output into pixel-accurate bounding box coordinates using a versatile Code node.
- Visual Bounding Box Overlay: Generate clear, visually annotated images with detected objects highlighted for easy interpretation.
- No-Code/Low-Code AI Automation: Automate complex computer vision tasks without extensive programming, streamlining your operations.
How To Use
- Start the Workflow: Trigger the workflow manually via the "When clicking ‘Test workflow’" node.
- Configure Image Source: In the "Get Test Image" HTTP Request node, update the
URLparameter to point to your desired image. Ensure it's publicly accessible. - Set Up Gemini Credentials: Add your Google Gemini (PaLM) API credentials to the "Gemini 2.0 Object Detection" node. Follow the n8n documentation for setting up this credential type.
- Define Object for Detection: In the "Gemini 2.0 Object Detection" node's JSON Body, modify the
textpart (e.g.,"I want to see all bounding boxes of cats in this image.") to specify the object you wish to detect. - Run and Review: Execute the workflow. The "Draw Bounding Boxes" node will output an image with the detected objects highlighted. You can save or further process this image.
Apps Used
Workflow JSON
{
"id": "c2ef0560-7c3a-4f50-9fee-f0051f8324e5",
"name": "Automated Object Detection with Google Gemini and Visual Bounding Boxes",
"nodes": 23,
"category": "Operations",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: c2ef0560-7c3a...
About the Author
AI_Workflow_Bot
LLM Specialist
Building complex chains with OpenAI, Claude, and LangChain.
Statistics
Related Workflows
Discover more workflows you might like
Google Sheets to Icypeas: Automated Bulk Domain Scanning
This workflow streamlines the process of performing bulk domain scans by integrating your Google Sheets data directly with the Icypeas platform. Automate the submission of company names from your spreadsheet to Icypeas for comprehensive domain information, saving valuable time and effort.
Instant WooCommerce Order Notifications via Telegram
When a new order is placed on your WooCommerce store, instantly receive detailed notifications directly to your Telegram chat. Stay on top of your e-commerce operations with real-time alerts, including order specifics and a direct link to view the order.
On-Demand Microsoft SQL Query Execution
This workflow allows you to manually trigger and execute any SQL query against your Microsoft SQL Server database. Perfect for ad-hoc data lookups, administrative tasks, or quick tests, giving you direct control over your database operations.