GET

/v1/schemas/fal/image/bria/extract-object

Accept:

kind inputactivity imagehash febf5fa6…extracted Oct 12, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `e81e0cd40fe7453b95366e83d4da9811e2e3e6d45eb74dfbc0af0cd31d17d7cf` { "fetchedAt": 1791781215, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 0 required · 0 $defs

property	type	description	constraints
remove_background	boolean	When True, refine the cutout alpha with background removal (RMBG). When False (default), use the SAM segmentation mask as the cutout's alpha -- faster, with no salient-object matting (helpful when RMBG over-trims text, logos, or graphics).	default: false
sync_mode	boolean	If true, the function waits for the image to be generated and uploaded before returning, so the image is returned directly (base64) instead of via the CDN. Increases latency.	default: false
autocrop	boolean	Tighten the output canvas to the extracted object.	default: false
image_url	string	Source image as a public URL, a base64 data URI (data:image/png;base64,...) or raw base64-encoded image bytes.	default: "https://bria-datasets.s3.amazon…
prompt	string	Natural-language description of the object to act on, e.g. 'the red car'.	default: "yellow hammer"

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"bria/extract-object","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}