Use Cases
- Automating object detection in images for analysis
- Enhancing image processing workflows with AI capabilities
- Visualizing detected objects in images for better insights
How It Works
Fetch an image from a specified URL using an HTTP request Extract image dimensions for processing Send the image to Gemini 2.0 for object detection Receive bounding box coordinates for detected objects Normalize coordinates to match the original image size Draw bounding boxes on the original image for visualization
Setup Steps
- 1Import the workflow template into n8n
- 2Click on 'Test workflow' to trigger the process
- 3Configure the HTTP request node with the desired image URL
- 4Run the workflow to see the object detection results
Apps Used
Image Editing
Google Gemini
Categories
Target Roles
Tags
#ai content generation
#process automation
#workflow management