Florence-2

Unified vision foundation model by Microsoft for captioning, detection, and segmentation.

Open SourceSelf HostedOffline CapableGPU Required (6GB+ VRAM)
0.0 (0)

About

Florence-2 by Microsoft handles multiple vision tasks through a unified sequence-to-sequence architecture. Supports captioning, object detection, grounding, OCR, and segmentation using text prompts. Lightweight yet powerful. MIT 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
MIT
Minimum VRAM
6 GB
Added
Apr 3, 2026

Similar Tools

Featured

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

Open SourceSelf HostedOffline
Easy
0.0 (0)

Open-vocabulary real-time object detection using YOLO with text prompts.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)
Featured

Open-set object detection combining DINO with grounded pre-training.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)