Automate Prompt-Based Object Detection with Gemini 2.0 in n8n - n8n Workflow | Neura Market
Automate Prompt-Based Object Detection with Gemini 2.0 in n8n
Leverage Gemini 2.0's bounding box detection in n8n to identify and mark objects in images using prompts, enabling powerful contextual searches.
This workflow demonstrates the integration of Gemini 2.0's advanced bounding box detection into n8n. By using prompt-based queries, users can specify objects of interest within images, such as 'bunnies' or 'cars parked out of bounds'. The workflow downloads an image, retrieves its dimensions, and sends it to the Gemini 2.0 API for object detection. The detected coordinates are then rescaled to match the original image dimensions, and bounding boxes are drawn to visualize the results. This setup
Platform
n8n
Category
AI
Price
Free
Creator
Nina Petrova
set
code
editImage
stickyNote
httpRequest
manualTrigger
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.