Labelbox has introduced an upgraded image Auto-Segment tool that integrates Segment Anything 2.0 (SAM 2), Meta's latest model for image and video segmentation, into its image editor. SAM 2 enhances the capabilities of its predecessor by improving speed and accuracy, particularly in real-time, zero-shot segmentation tasks across both images and videos. It utilizes a new dataset, SA-V, which includes a vast array of real-world videos and masklets, enabling seamless segmentation without custom adaptation. SAM 2's innovations include a memory mechanism that allows for consistent video segmentation with fewer user interactions and faster processing. The tool's integration into Labelbox promises to benefit industries that depend on precise and efficient segmentation, such as autonomous driving and robotics, while promoting broader adoption of computer vision technologies due to its open-source nature and extensive dataset.