{"product_id":"n8n-workflow-object-based-image-search-with-cloudflare-ai","title":"n8n Workflow: Object-Based Image Search with Cloudflare AI","description":"\u003ch3\u003eTurn one image into searchable object crops using Cloudflare AI + Elasticsearch\u003c\/h3\u003e\n\u003cp\u003eThis n8n workflow downloads an image, uses \u003cstrong\u003eCloudflare Workers AI (DETR ResNet-50)\u003c\/strong\u003e to detect objects, crops only high-confidence detections, uploads those crops to \u003cstrong\u003eCloudinary\u003c\/strong\u003e, and indexes the results in \u003cstrong\u003eElasticsearch\u003c\/strong\u003e to enable \u003cstrong\u003eobject-based image search\u003c\/strong\u003e.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003eRuns when you manually start the workflow in n8n.\u003c\/li\u003e\n  \u003cli\u003eDownloads the source image from the URL you configure.\u003c\/li\u003e\n  \u003cli\u003eCalls Cloudflare Workers AI (@cf\/facebook\/detr-resnet-50) to extract object \u003cstrong\u003elabels\u003c\/strong\u003e, \u003cstrong\u003ebounding boxes\u003c\/strong\u003e, and \u003cstrong\u003econfidence scores\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003eSplits detection output into one item per detected object and filters to keep only detections with a \u003cstrong\u003escore ≥ 0.9\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003eRe-downloads the original image for each retained detection and crops the object region using the bounding box.\u003c\/li\u003e\n  \u003cli\u003eUploads each cropped object image to \u003cstrong\u003eCloudinary\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003eInserts a document into \u003cstrong\u003eElasticsearch\u003c\/strong\u003e containing the \u003cstrong\u003eCloudinary URL\u003c\/strong\u003e, the \u003cstrong\u003eoriginal source URL\u003c\/strong\u003e, the \u003cstrong\u003eobject label\u003c\/strong\u003e, and detection metadata.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eObject-based search\u003c\/strong\u003e for product catalogs (e.g., find images by detected items).\u003c\/li\u003e\n  \u003cli\u003eBuilding visual indexes for \u003cstrong\u003eSaaS content libraries\u003c\/strong\u003e where users search by what’s inside an image.\u003c\/li\u003e\n  \u003cli\u003eCurating labeled image datasets with \u003cstrong\u003ehigh-confidence object crops\u003c\/strong\u003e for downstream review or indexing.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eCloudflare Workers AI\u003c\/strong\u003e: DETR ResNet-50 endpoint for object detection (labels, bounding boxes, scores).\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eCloudinary\u003c\/strong\u003e: uploads cropped object images using configured cloud name, an unsigned upload preset, and query-auth credentials.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eElasticsearch\u003c\/strong\u003e: indexes image documents into your configured index name.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003en8n nodes\u003c\/strong\u003e include: set, filter, split out, edit image, sticky note, and http request.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eBefore running, configure Cloudflare Workers AI credentials, Cloudflare Account ID, Cloudinary settings, Elasticsearch credentials\/index, and the source image URL (and adjust the object score threshold if needed).\u003c\/p\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":46160851632307,"sku":"N8N-20405","price":73.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/3xQn0EVkJDnJk-ddP2kVF_VDfQtfQE.png?v=1791191483","url":"https:\/\/buyflowscripts.com\/products\/n8n-workflow-object-based-image-search-with-cloudflare-ai","provider":"N8N Commerce","version":"1.0","type":"link"}