S

Sam2 Hiera Small

Developed by facebook
A foundational model developed by FAIR for solving promptable visual segmentation tasks in images and videos
Downloads 12.98k
Release Time : 8/2/2024

Model Overview

SAM 2 is a foundational model for image and video segmentation, supporting interactive segmentation through prompts such as points or boxes.

Model Features

Multimodal Prompt Support
Supports interactive segmentation through various prompt methods such as points and boxes
Image and Video Versatility
The same model can handle both image and video segmentation tasks
Efficient Inference
Supports bfloat16 precision and CUDA acceleration to improve inference efficiency

Model Capabilities

Image Segmentation
Video Segmentation
Interactive Segmentation
Mask Generation

Use Cases

Computer Vision
Image Object Segmentation
Segment specific objects in images using point or box prompts
Generate precise object masks
Video Object Tracking
Track and segment moving objects in video sequences
Generate consistent object masks across consecutive frames
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase