Models
Florence-2 vs. Kosmos-2

Florence-2 vs. Kosmos-2

Both Florence 2 and Kosmos-2 are commonly used in computer vision projects. Below, we compare and contrast Florence 2 and Kosmos-2.

Models

icon-model

Florence 2

Florence-2 is a lightweight vision-language model open-sourced by Microsoft under the MIT license.
icon-model

Kosmos-2

Kosmos-2 is a multimodal language model capable of object detection and grounding text in images.
Model Type
Object Detection
--
Object Detection
--
Model Features
Item 1 Info
Item 2 Info
Architecture
--
--
Frameworks
--
--
Annotation Format
Instance Segmentation
Instance Segmentation
GitHub Stars
--
--
License
MIT
--
--
Training Notebook

Compare Florence 2 and Kosmos-2 with Autodistill

Compare Florence-2 vs. Kosmos-2

Provide your own image below to test YOLOv8 and YOLOv9 model checkpoints trained on the Microsoft COCO dataset.

COCO can detect 80 common objects, including cats, cell phones, and cars.