microsoft/Florence-2-base
image-text-to-text model by microsoft
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft. Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks. Florence-2 can interpret simple text prompts to perform tasks like captioning, object detection, and segmentation. It leverages our FLD-5B dataset, containing 5.4 billion annotations across 126 million images, to master multi-task learning. The model's sequence-to-sequence architecture enables it to excel in both zero-shot and fine-tuned settings, proving to be a competitive vision foundation model. Resources and Technical Documentation: Use the code below to get started with the model. All models are trained with float16. This model is capable of performing different tasks through changing the prompts. First, let's define a function to run a prompt. Click to expand Here are the tasks Florence-2 could perform: Click to expand caption to phrase grounding task requires additional…
Read the full model card ↗ · Preview checked 2026-10-29T06:17:45.593Z
Inside the original model card — Document outline
- Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
- Model Summary
- How to Get Started with the Model
- Tasks
- Caption
- Detailed Caption
- More Detailed Caption
- Caption to Phrase Grounding
- Object Detection
- Dense Region Caption
- Region proposal
- OCR
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
microsoft/Florence-2-base is a image-text-to-text model repository published by microsoft on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 4,436,701
- Cumulative likes
- 433
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 231,567,705
- Architecture
- Florence2ForConditionalGeneration
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2024-06-15T00:57:24.000Z
- Last modified
- 2025-08-04T17:36:57.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:30.840Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.