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.
- clone this repository to 'ComfyUI/custom_nodes` -folder. Only real dependency is new enough transformers version.
Supports the following models, they are automatically downloaded to ComfyUI/LLM:
https://huggingface.co/microsoft/Florence-2-base
https://huggingface.co/microsoft/Florence-2-base-ft