Buckets:
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| assets | 1 items | ||
| .gitattributes | 1.58 kB xet | e4f9e2a8 | |
| LICENSE | 7.35 kB xet | 1774e7d0 | |
| README.md | 2 kB xet | b98e32d2 | |
| config.json | 25.8 kB xet | 34d5fa15 | |
| merges.txt | 525 kB xet | f3310159 | |
| processor_config.json | 1.71 kB xet | 7e43b798 | |
| sam3.1_multiplex.pt | 3.5 GB xet | 850acf27 | |
| special_tokens_map.json | 588 Bytes xet | c0f91064 | |
| tokenizer.json | 3.64 MB xet | 76750d65 | |
| tokenizer_config.json | 799 Bytes xet | 1d7a3d49 | |
| vocab.json | 862 kB xet | 8a587ca0 |
SAM 3.1
SAM 3 (Segment Anything with Concepts) is a unified foundation model from Meta for promptable segmentation in images and videos. It detects, segments, and tracks objects using text or visual prompts such as points, boxes, and masks. SAM 3 introduces the ability to exhaustively segment all instances of an open-vocabulary concept specified by a short text phrase, handling over 50x more unique concepts than existing benchmarks. SAM 3.1 builds on this with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers ~7x faster inference at 128 objects on a single H100 GPU without sacrificing accuracy, along with improved VOS performance on 6 out of 7 benchmarks.
This repository hosts only the SAM 3.1 model checkpoints — there is no Hugging Face Transformers integration. For installation, code, usage examples, and full documentation, please visit the SAM 3 GitHub repository.
- Total size
- 3.51 GB
- Files
- 12
- Last updated
- Jun 16
- Pre-warmed CDN
- US EU US EU