# Detect objects in images by text prompt with bounding box visualization via Google Gemini
This automation template detects objects in an image using a text prompt via Google Gemini API and visualizes the results by drawing colored bounding boxes. Perfect for rapid analysis, annotation, or filtering of visual content without requiring trained computer vision models.
## Who it´s for
- Developers integrating AI-powered object detection into their workflows
- Analysts needing to quickly annotate images
- Teams evaluating prompt-based computer vision capabilities
## What the automation does
- Triggered manually
- Downloads an image from a public URL
- Sends the image and a text prompt to Google Gemini API for object detection
- Receives normalized bounding box coordinates
- Rescales coordinates to match original image dimensions
- Draws colored bounding boxes on the image using image editing node
- Returns the annotated image for visual validation
## What´s included
- Ready-to-use n8n workflow
- Logic for manual triggering and image handling
- Integrations with Google Gemini API and HTTP image sources
- Basic textual instructions for setup and adaptation
## Requirements for setup
- n8n instance with access to JavaScript code node and image processing features
- Google Gemini API key
- Publicly accessible image URL (HTTP/HTTPS)
## Benefits and outcomes
- Saves time on manual image annotation
- Enables fast evaluation of AI’s ability to detect objects by description
- Scales visual content analysis without ML expertise
- Flexible targeting — change the object just by updating the text prompt
## Important: template only
Important: you are purchasing a ready-made automation workflow template only. Rollout into your infrastructure, connecting specific accounts and services, 1:1 setup help, custom adjustments for non-standard stacks and any consulting support are provided as a separate paid service at an individual rate. To discuss custom work or 1:1 help, contact via chat
No feedback yet