• 9 min read
Retail Object Detection with RF-DETR
Detect visible beverage products with RF-DETR, compare their counts with fixed camera-frame thresholds, and use Gemini 2.5 Pro to generate a shelf inspection summary.
• 17 min read
Teaching a Porch to Recognize Delivery Drivers and Accept Packages
An end-to-end build of a self-unlocking porch lockbox: on-device detection on an old iPhone gates a cloud Roboflow Workflow, which validates courier-with-package events inside a drawn porch zone and triggers a solenoid lock through an ESP32. Includes delivery verification and a live dashboard.
• 11 min read
Cosmetic Defect Detection with Computer Vision
Learn how computer vision can automate cosmetic defect inspection by detecting paint scratches and identifying the affected car part. This guide shows how to train an RF-DETR model in Roboflow, build a part-level inspection Workflow, and return visual results and repair-ready outputs for QA review.
• 6 min read
Multi-Model Auto Labeling for Segmentation with Roboflow Workflows
Stack SAM 3, Gemini, and GPT into a single Workflow, require a 2-of-3 vote on every mask, and auto-label entire segmentation datasets without drawing a single polygon.
• 6 min read
GPT 5.6 Sol is the best "vision" model OpenAI ever released
GPT-5.6 Sol is OpenAI’s strongest vision model yet. We tested Sol, Terra, and Luna across detection, counting, OCR, and extraction, then compared their results, speed, and cost with leading VLMs.
• 4 min read
How to Scale a Computer Vision Pilot to Production in Manufacturing
See how to scale a computer vision pilot to production: why 77% stall on integration, not the model, and how to get past it in manufacturing.
• 13 min read
Open Vocabulary Segmentation
Learn how to build a zero-shot segmentation pipeline with SAM 3 and Roboflow Workflows.
• 10 min read
Segment Anything with Text
Use Segment Anything with Text in Roboflow Workflows to segment workers, helmets, and safety vests without training a custom model.
• 11 min read
Analyze Video Feeds for Process Monitoring with RF-DETR
Analyze video feeds for process monitoring with Roboflow: RF-DETR detects, ByteTrack tracks, and a line counter logs counts and speed.
• 13 min read
Automate Surface Defects Detection with Vision AI
Learn how computer vision can detect surface defects. This guide explains common use cases and shows how to build a Roboflow surface inspection workflow that detects defects, visualizes results, and supports quality decisions.
• 16 min read
Product Recognition AI
Product Recognition AI helps businesses identify, count, and verify products from images or video. This blog explains key use cases and shows how to build a Roboflow Product-to-Bill Verification System that detects products, reads receipts, and checks billing accuracy.
• 11 min read
How to Detect Paint Defects with Computer Vision
Automate paint defect inspection in manufacturing. Learn how to train an RF-DETR model and build a visual QA pipeline using Roboflow Workflows.
• 6 min read
Multi-Model Auto Labeling with Roboflow Workflows
Roboflow has brought the full power of Workflows into Auto Label, letting you run custom pipelines serverlessly on your unannotated images. This post walks through building a sample multi-VLM workflow from scratch, then shows how to launch it on an image batch in a few clicks.
• 3 min read
OpenAI GPT-5.6 (Sol, Terra, and Luna) for Vision: Now in Roboflow Playground
OpenAI's GPT-5.6 family (Sol, Terra, and Luna) is now in the Roboflow Playground, so you can test all three tiers against your own visual data and compare them side by side with other frontier models.
• 8 min read
Dimensional Defect Inspection with Vision AI
Catch dimensional defects automatically: a Roboflow Workflow where Gemini detects features and a Python block measures spacing for pass/fail.
• 4 min read
Making Visual AI Standard Practice in Complex Manufacturing
Learn how to implement visual AI in manufacturing from Florida Crystals' quality lead: trust tests, feedback loops, and pilots that scale.
• 12 min read
Detect Anything Model
A detect anything model finds any object from a text prompt, no training or labels. Build one with SAM3 in Roboflow Workflows to search a scene.
• 10 min read
Predictive Maintenance with Vision AI
Use RF-DETR to detect early bearing defects and Gemini 2.5 Pro to analyze defect severity, explain potential failure causes, and generate maintenance recommendations.
• 2 min read
Claude Sonnet 5 for Vision: Evaluation and Benchmarks
We ran Claude Sonnet 5 through the Roboflow Vision Evals across 67 real vision prompts. It ties Sonnet 4.6, trails Fable 5, and sits well behind Gemini 3.5 Flash, which still leads the board.
• 4 min read
Build a 3D Soccer Offside (VAR) System
Learn how to build a 3D soccer offside (VAR) system from any video clip.
• 12 min read
Fastest Object Detection Models in 2026
Compare the fastest object detection models. Learn how to test models in Roboflow Workflows and use local Inference profiling to choose the best model for your data.
• 15 min read
Defect Inspection
Automate manufacturing defect inspection with computer vision. Learn how to train an RF-DETR model and build a pass/fail QA workflow using Roboflow and Gemini.
• 11 min read
What Is A Two-Stage Detector?
Learn what a two-stage detector is, how it works, and how it compares with one-stage models like YOLO. This guide explains the architecture, common examples such as Faster R-CNN and Mask R-CNN, and shows how to train Faster R-CNN using a Roboflow dataset in Colab.
• 9 min read
Text Prompt Object Detection with Roboflow
Text prompt object detection with SAM3: type your classes in a Roboflow Workflow and get boxes, masks, and confidence, no dataset or training.
Stay Connected