GET

/v1/schemas/fal/image/fal-ai/florence-2-large/caption-to-phrase-grounding?kind=output

Accept:

kind outputactivity imagehash 8c3a7793…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `b7f4045a12703f09aee634dc065313952deb16d818e9790dc7f87610a13469ae` { "fetchedAt": 1783329487, "extractorVersion": "1", "verifiedAt": null }

Response body

2 properties · 1 required · 3 $defs

property	type	description	constraints
results*	BoundingBoxes	Results from the model
image	Image	Processed image

Types

3 $defs

BoundingBoxobject

label*	string	Label of the bounding box
h*	number	Height of the bounding box
w*	number	Width of the bounding box
y*	number	Y-coordinate of the top-left corner
x*	number	X-coordinate of the top-left corner

BoundingBoxesobject

bboxes*

BoundingBox[]

List of bounding boxes

Imageobject

Represents an image file.

file_size	integer	The size of the file in bytes.	nullable
width	integer	The width of the image in pixels.	nullable
height	integer	The height of the image in pixels.	nullable
file_name	string	The name of the file. It will be auto-generated if not provided.	nullable
content_type	string	The mime type of the file.	nullable
url*	string	The URL where the file can be downloaded from.

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/florence-2-large/caption-to-phrase-grounding","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}