Florence-2: Advancing Multiple Vision Tasks with a Single VLM Model | Towards Data Science

A Guided Exploration of Florence-2’s Zero-Shot Capabilities: Captioning, Object Detection, Segmentation and OCR.

By · · 1 min read
Florence-2: Advancing Multiple Vision Tasks with a Single VLM Model | Towards Data Science

Source: Towards Data Science

A Guided Exploration of Florence-2’s Zero-Shot Capabilities: Captioning, Object Detection, Segmentation and OCR.