Automated Image Object Detection with Bounding Boxes in n8n

This n8n workflow automates the process of detecting objects in an image using Google’s Gemini 2.0 API, then visualizes the results by drawing bounding boxes directly onto the image. The workflow begins with a manual trigger, allowing users to test the process with any image URL. It fetches the image and retrieves its dimensions, then sends the image to the Gemini API to detect specific objects based on prompts, such as identifying all rabbits. The detected bounding box coordinates are scaled to match the original image size, ensuring accurate placement. Finally, the workflow overlays bounding boxes onto the original image, making the detection results visually understandable. This automation is useful for developers or content creators who need to quickly analyze images and display marked objects, such as in visual data analysis, content moderation, or digital asset management.