About Depth Anything Video
Estimate temporally consistent depth maps from video using Video Depth Anything.
Ready to build with Depth Anything Video?
Try Depth Anything Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "bytedance-depth-anything-video",
"video_url": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/videos/waterfall.mp4",
"depth_model": "VDA-Large",
"colormap": "grayscale",
"resolution": "auto",
"side_by_side": false,
"include_raw_depths": false
}'Request parameters
Every field Depth Anything Video accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
video_url | stringuri | Yes | — | URL of the input video to estimate depth for. |
depth_model | string | No | "VDA-Large" | Depth estimation model size. VDA-Large = best quality, VDA-Small = fastest.VDA-SmallVDA-BaseVDA-Large |
colormap | string | No | "grayscale" | Colormap for depth visualization.grayscaleturboinfernomagmaviridis |
resolution | string | No | "auto" | auto360p480p720p1080p |
max_frames | integer | No | — | Maximum number of frames to process. Leave unset to process all frames. |
output_fps | number | No | — | Output video FPS. Leave unset to use the input frame rate. |
side_by_side | boolean | No | false | If true, output a side-by-side original and depth comparison video. |
include_raw_depths | boolean | No | false | If true, exports raw float32 depths as an NPZ file. |