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
Foundation model for monocular depth estimation by TikTok.
Improved vision-language model by Google using sigmoid loss for contrastive learning.
Open-vocabulary object detection model by Google using vision transformers.
OpenMMLab detection toolbox with 300+ pre-trained models and 80+ algorithms.
State-of-the-art real-time object detection supporting YOLOv5 through v11.
Additive angular margin loss for deep face recognition.