Grounded SAM 2

Combines Grounding DINO with SAM 2 for text-prompted segmentation and tracking.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

Grounded SAM 2 by IDEA Research is a pipeline that pairs text-prompted detection from Grounding DINO with the segmentation and tracking of SAM 2, so any object described in natural language can be detected, segmented, and tracked across images and video. It assembles open-world models rather than introducing new training, and supports related detectors like Florence-2 and DINO-X. 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
Intermediate (3/5)
License
Apache-2.0
Minimum VRAM
8 GB
Added
Apr 3, 2026

Related Tools

Foundation model for monocular depth estimation by TikTok.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Improved vision-language model by Google using sigmoid loss for contrastive learning.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)

Open-vocabulary object detection model by Google using vision transformers.

Open SourceSelf HostedOfflineGPU 6GB+
Intermediate
0.0 (0)

OpenMMLab detection toolbox with 300+ pre-trained models and 80+ algorithms.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)
Featured

State-of-the-art real-time object detection supporting YOLOv5 through v11.

Open SourceSelf HostedOffline
Easy
0.0 (0)

Additive angular margin loss for deep face recognition.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)
Browse all Computer Vision & Object Detection tools