Segment Anything 2 (SAM 2)
Foundation model by Meta for promptable image and video segmentation.
About
SAM 2 by Meta is a foundation model for promptable segmentation in images and videos. Supports point, box, and mask prompts. Handles arbitrary objects without training. Extends to video with streaming memory. Requires GPU with 8+ GB VRAM. Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
Simple and effective multi-object tracking using every detection box.
Monocular depth estimation model producing detailed depth maps from single images.
End-to-end object detection with transformers by Meta, eliminating hand-designed components.
Self-supervised vision transformer by Meta producing universal visual features.
Unified vision foundation model by Microsoft for captioning, detection, and segmentation.
Robust multi-object tracking combining motion and appearance cues.