AI-Powered Object Detection and Visualization with Google Gemini
detail.loadingPreview
Automate advanced image analysis by leveraging Google Gemini 2.0 for object detection. This workflow identifies specified objects in an image, retrieves their bounding box coordinates, and visually marks them directly on the image, providing clear visual insights.
About This Workflow
Unlock the power of Vision AI with this n8n workflow that seamlessly integrates with Google Gemini 2.0. Start by fetching any image, then send it to Gemini with a natural language prompt to detect specific objects (e.g., "rabbits"). Gemini returns precise, normalized bounding box coordinates for the detected objects. The workflow then intelligently scales these coordinates to the image's original dimensions and uses n8n's built-in image editing tools to draw clear bounding boxes around each identified object. This provides an immediate, visual representation of the AI's detection, making complex object recognition simple and actionable.
Key Features
- AI-Powered Object Detection: Utilizes Google Gemini 2.0's advanced multi-modal capabilities for accurate object identification based on natural language prompts.
- Automated Image Analysis: Automatically fetches images, extracts dimensions, and processes AI responses without manual intervention.
- Dynamic Bounding Box Visualization: Scales normalized AI coordinates to original image dimensions and draws precise bounding boxes directly on the image for clear visual feedback.
- Customizable Object Search: Easily modify the prompt to detect different objects or attributes within an image.
- No-Code/Low-Code Integration: Connects powerful AI services with n8n's intuitive visual workflow builder.
How To Use
- Set up Google Gemini (PaLM) Credential: Ensure you have a Google Gemini (PaLM) API credential configured in your n8n instance.
- Configure 'Get Test Image': Modify the
URLparameter to point to the image you wish to analyze. Ensure it's publicly accessible. - Adjust 'Gemini 2.0 Object Detection' Prompt: In the
JSON Bodyof the 'Gemini 2.0 Object Detection' node, locate thetextfield:"I want to see all bounding boxes of rabbits in this image."Change "rabbits" to the object you want Gemini to detect. - Review 'Draw Bounding Boxes': The 'Draw Bounding Boxes' node currently has a fixed number of operations (6). If Gemini detects more objects, you might need to add more "draw" operations, iterating through
$json.coordsor modify the node's logic for dynamic drawing of all detected objects. - Execute the Workflow: Run the workflow by clicking 'Test workflow' or activate it to run on a schedule or webhook trigger.
Apps Used
Workflow JSON
{
"id": "00f2f8dd-8322-4feb-8628-f65c5d5c3b16",
"name": "AI-Powered Object Detection and Visualization with Google Gemini",
"nodes": 7,
"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: 00f2f8dd-8322...
About the Author
N8N_Community_Pick
Curator
Hand-picked high quality workflows from the global community.
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.