LibraryOther★ 7.0
Prompt-Based Object Detection with Google Gemini 2.0
An n8n workflow leveraging Google Gemini 2.0 API for prompt-based object detection in images. It downloads an image, extracts dimensions, queries Gemini for bounding boxes of specified objects, rescales coordinates, and draws boxes on the image using n8n's Edit Image node.
▮▯▯Beginner5 min6 nodes
$9.00
SSL secureInstant access24h refund
Card payment via Dodo
Wise · Bank transfer
Wise emailvirginaiagency@gmail.com
Amount$9.00 USD
Referencevai-lib-prompt
VISA
AMEX
PayPal
Pay
GPay
✦ Built with
Google Geminin8n
✦ Workflow at a glance
✦ What you get
In thebox.
- workflow.jsonReady-to-import n8n workflow file
- Setup guideStep-by-step deployment instructions
- Node documentationWhat each node does + how to tune it
- Sample dataTest inputs to verify it works end-to-end
- Community supportBest-effort via Telegram / GitHub
- Lifetime updatesNew versions delivered free, forever
✦ Setup
Live inthree steps.
01
Import
Open n8n → Workflows → New from JSON. Drop in the workflow.json you received.
02
Connect
Add credentials for each tool used (OpenAI key, Slack token, etc.). All shown in the setup guide.
03
Test & activate
Run on sample data to verify the flow. Toggle the workflow to active and you're shipping.
✦ Stack · 2 tools
The fullintegration map.
AI
1
Google Gemini
Automation
1
n8n
✦ Related
More inOther.
✦ Ready when you are
Deploy Prompt-Based Object Detection with
Free to license through our library tier. Custom builds in 1–3 days.