Florence-2-base-ft
A fine-tuned version of the Florence-2 vision foundation model with approximately 230 million parameters. It supports vision tasks such as image captioning and can be used to automatically generate alt text for images.
Timeline (last 90 days)
The Florence-2-base-ft vision model has about 230 million parameters, a download size of 350-450MB, and is used to automatically generate image description text.
Alt text generated by Florence-2-base-ft can only serve as an accessibility aid and cannot replace human writing; the model cannot understand the context and purpose of an image's use, and occasionally omits or fabricates details.
All Facts (2)
The Florence-2-base-ft vision model has about 230 million parameters, a download size of 350-450MB, and is used to automatically generate image description text.
50%UnverifiedAlt text generated by Florence-2-base-ft can only serve as an accessibility aid and cannot replace human writing; the model cannot understand the context and purpose of an image's use, and occasionally omits or fabricates details.
50%