Florence-2 Large | Vision | AI Playground

fal-ai/florence-2-large/region-to-category

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

Inference

Commercial use

Image Url*

Hint: you can drag and drop file(s) here, or provide a base64 encoded data URL Accepted file types: jpg, jpeg, png, webp

Region*

X1*

Y1*

X2*

Y2*

Idle

{
  "results": ""
}

Loading pricing info...

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

Use any vision language model from our selected catalogue (powered by OpenRouter)

Multimodal vision-language model for video understanding

Florence-2 Large Vision