The SAM 2.1 Hiera Large model extends the Segment Anything Model to support both images and videos. It enables precise object segmentation using various input prompts and works with the Transformers library. Designed for research and practical applications in video understanding and image editing.
In the Other AI space, Sam2.1 Hiera Large takes a focused approach. It focuses on segmenting objects in images and videos using point, box, or mask prompts. Sam2.1 Hiera Large is an open-source project aimed at computer vision developers and researchers. The project is open source (Apache-2.0). Sam2.1 Hiera Large is available on the web and API.
Behind Sam2.1 Hiera Large is Meta AI, based in the United States, and it first shipped in 2024. The project is developed in the open on GitHub with 19.6k stars. Key capabilities include Mask Generation, Video Segmentation, and point and Box Prompts. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do