Visual Object Detection and Annotation Using n8n & Gemini 2.0

This workflow demonstrates how to perform prompt-based object detection on an image using Google Gemini 2.0 API within n8n. It starts with a manual trigger for testing and involves several steps: fetching an image, retrieving its dimensions, requesting object detection from Gemini, normalizing and scaling bounding box coordinates, and finally drawing these bounding boxes on the original image. Additionally, the workflow includes sticky notes explaining each step and the practical applications of this process, such as automated image analysis or content moderation. This automation is ideal for users wanting to add AI-powered visual insights to their WordPress sites or digital workflows, making image annotation fast, accurate, and visually interpretable.