Roboflow Blog

Claude Fable 5, Anthropic's most capable model, is now available in Roboflow Workflows and the Roboflow Playground.

Train a Roboflow localization model, isolate printed label fields, and verify batch numbers and expiry dates with Google Gemini.

We are excited to announce support for YOLO26 semantic segmentation in Roboflow.

Use RF-DETR and Gemini 2.5 Pro to inspect medical device packaging, verify UDI labels, and identify packaging issues.

Claude Fable 5 is a strong reasoning model for visual understand but not a state-of-the-art vision model.

Combine RF-DETR and LMMs to build an AI pipeline that perceives, reasons, and acts.

Learn the difference between missing versus null annotations, including how they are represented in VOC XML and COCO JSON formats, and how their misidentification can be addressed using Roboflow tools to improve dataset quality.

Learn how to detect defects with Roboflow and trigger real-time downstream alerts in manufacturing facilities.

NVIDIA Cosmos 3 offers zero-shot performance on fixed-camera footage across airports, warehouses, and production lines.

A practical guide to understanding how AI cameras and IP cameras differ, and when each makes sense for your operation.

Learn how to build a sports analytics AI pipeline. Use RF-DETR and Gemini to automate sports formation analysis and player tracking.

Discover how image tiling improves small object detection. Learn to apply it during training and inference using Roboflow Workflows.

In this guide, we walk through how to deploy computer vision models offline using Roboflow Inference.

Roboflow enables manufacturers to generate synthetic data with NVIDIA Defect Image Generation skill for defect image generation

YOLO-StereoDepth brings stereo depth for robotics to the YOLO family in September 2026. See what we know and how to read metric depth today.

Ingest RTSP streams, handle frame buffering, and run wildfire smoke detection on the Roboflow Inference Docker container.

Learn how to build a multi-stage computer vision pipeline. Chain RF-DETR object detection, OpenAI OCR and LLMs in Roboflow to process documents.

Google's Gemini models bring computer vision capabilities and enables understanding images and video without fine-tuning. In this guide you will learn how to use latest Gemini models in Roboflow Playground and Workflows for computer vision tasks.

OpenAI models can classify images, extract text, detect objects, and answer visual questions without any training data. This guide covers the latest OpenAI models with vision capabilities, how to test them in Roboflow Playground, and how to build vision pipelines using Roboflow.