Fuser

Florence-2 Image Captioner

Provided by Fal — Learn More

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.

Preview

Inputs

Image
image
The image to generate a caption for.
Detail Level
dropdown
The level of detail in the generated caption.
default: detailedAccepts: Basic (simple description), Detailed (comprehensive description), More Detailed (extensive information)

Outputs

Caption
text
The generated caption for the image.