Microsoft Florence-2
Family overview — summarizes releases; licenses and availability belong to each release.
Maintained by Microsoft (Azure AI)13
Florence-2 is a family of vision foundation models from Microsoft's Azure AI group that handle captioning, object detection, visual grounding, segmentation, and OCR through text prompts, using a sequence-to-sequence design with a DaViT vision encoder. The models were trained on FLD-5B, a set of 5.4 billion visual annotations on 126 million images that the team built with an iterative automated annotation process. Microsoft published four checkpoints on Hugging Face in June 2024: Florence-2-base (0.23B parameters) and Florence-2-large (0.77B), plus versions of each fine-tuned on a collection of downstream tasks (base-ft and large-ft).1325
- Paper: Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks (arXiv 2311.06242) (external site: arxiv.org)
- Model hub: Florence-2-large (Hugging Face) (external site: huggingface.co)
- Model hub: Florence-2-base (Hugging Face) (external site: huggingface.co)
- Paper: Microsoft Research publication page (external site: microsoft.com)
Releases assessed
| Release | Weights | Tier (USASI rubric v0.2) | License | Released |
|---|---|---|---|---|
| Florence-2-large | Weights: Public | Model-disclosure tier (USASI rubric v0.2): Open-weight | MIT | Jun 2024 |
What it is useful for
The model card shows prompt-selected tasks including captioning at several levels of detail, object detection, dense region captioning, region proposals, caption-to-phrase grounding, OCR, and OCR with regions.3
Organization context
U.S. eligibility
Eligible · basis: U.S. headquarters
The technical report lists its authors under Azure AI, Microsoft, and the checkpoints are published in Microsoft's Hugging Face organization with an MIT license naming Microsoft Corporation. Microsoft Corporation lists One Microsoft Way, Redmond, Washington as its principal executive offices on the cover page of its Form 10-K for fiscal year 2026.1349
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.