GET

/v1/schemas/fal/video/fal-ai/depth-anything-video

Accept:

kind inputactivity videohash 4bfdefb6…extracted Jul 22, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `44c51b7466f7c9292e0ea96c8a67144cbc2553c6d2eb2b0186c64a1a3f54a2a3` { "fetchedAt": 1784696551, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 1 required · 0 $defs

property	type	description	constraints
video_url*	string	URL of the input video to estimate depth for.
model	enum	Depth estimation model size. VDA-Large = best quality, VDA-Small = fastest.	VDA-Small \| VDA-Base \| VDA-Large · default: "VDA-Large"
side_by_side	boolean	Output original \| depth comparison video.	default: false
max_frames	integer	Max frames to process (max 2400). None = up to 2400.	n > 0 · nullable
resolution	enum	Output resolution. 'auto' preserves input (max 1080p). Options: 'auto', '360p', '480p', '720p', '1080p'.	auto \| 360p \| 480p \| 720p \| 1080p · default: "auto"
colormap	enum	Colormap for depth visualization. 'turbo' (recommended) shows near=warm, far=cool. 'grayscale' for raw normalized depth. 'inferno'/'magma' for perceptually uniform. 'viridis' for colorblind-friendly.	grayscale \| turbo \| inferno \| magma \| viridis · default: "grayscale"
include_raw_depths	boolean	Export raw float32 depths as .npz file with: 'depths' [N,H,W], 'min_depth', 'max_depth', 'fps', 'model', 'shape'.	default: false
output_fps	number	Output video FPS. None = same as input.	n > 0 · nullable

Validate a payload

before you spend tokens

shell

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