SAM (Segment Anything v1)
Original Segment Anything Model by Meta for zero-shot image segmentation.
About
Segment Anything Model by Meta AI is a foundation model for promptable image segmentation that masks objects given point, box, or rough region prompts, trained on 11 million images with over a billion masks for strong zero-shot generalization. It produces high-quality masks without task-specific training and has been widely adopted as a building block for downstream vision tools. The successor SAM 2 extends it to video. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Apache-2.0
- Minimum VRAM
- 6 GB
- Added
- Apr 3, 2026
Related Tools
Contrastive language-image pre-training model by OpenAI for zero-shot visual classification.
Lightweight face recognition and analysis framework wrapping multiple models.
Foundation model for monocular depth estimation by TikTok.
Monocular depth estimation model producing detailed depth maps from single images.
Meta AI research platform for object detection, segmentation, and pose estimation.
Simple and effective multi-object tracking using every detection box.