mirror of
https://github.com/hanzoui/workflow-templates-broken-zap-2026-06-08.git
synced 2026-10-30 20:44:35 +00:00
739 B
739 B
HanzoStudio-Florence2
Author: Kijai URL: https://github.com/kijai/HanzoStudio-Florence2 Registry: https://registry.hanzo.ai/nodes/hanzo-studio-florence2 Downloads: 1,103,756 Stars: 1,592 Templates using this: 1
Description
Nodes to use Florence2 VLM (Vision-Language Model) for image vision tasks including object detection, captioning, segmentation, and OCR. Florence2 is a versatile model that can perform multiple vision tasks through natural language prompts.
Key Nodes
Florence2: Runs the Florence2 vision-language model on an input image with a text prompt to perform tasks such as image captioning, object detection, region-based captioning, segmentation, and optical character recognition.