infery
← All models

Depth Anything Video

depth-anything-video

Video generationby Depth Anything Video

Generates depth maps from video using Video Depth Anything (CVPR 2025). Produces per-frame depth estimation with temporal consistency across frames. Supports 3 model sizes (Small, Base, Large), 5 colormaps including grayscale, side-by-side comparison with the original video, and raw depth export as .npz. Useful for 3D reconstruction, video effects, compositing, and scene understanding.

Example

Details

Accepts
video

Pricing

Price
5 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
modelstringenum: VDA-Small, VDA-Base, VDA-LargeDepth estimation model size. VDA-Large = best quality, VDA-Small = fastest.
colormapstringenum: grayscale, turbo, inferno, magma, viridisColormap for depth visualization. 'turbo' (recommended) shows near=warm, far=cool. 'grayscale' for raw normalized depth. 'inferno'/'magma' for perceptually uniform. 'viridis' for colorblind-friendly.
video_urlrequiredstringURL of the input video to estimate depth for.
max_framesMax frames to process (max 2400). None = up to 2400.
output_fpsOutput video FPS. None = same as input.
resolutionstringenum: auto, 360p, 480p, 720p, 1080pOutput resolution. 'auto' preserves input (max 1080p). Options: 'auto', '360p', '480p', '720p', '1080p'.
side_by_sidebooleanOutput original | depth comparison video.
include_raw_depthsbooleanExport raw float32 depths as .npz file with: 'depths' [N,H,W], 'min_depth', 'max_depth', 'fps', 'model', 'shape'.

Output

FieldTypeDescription
videoDepth visualization video (MP4, H.264).
raw_depthsRaw depth values as .npz (if include_raw_depths=True).