Skip to content

Depth Anything Video

Integrate

Model id depth-anything-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/depth-anything-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Files like the example: $0.40 400 API credits your files are measured before the run Run it on this page

Get API key
ByteDance Video to Video up to 1080p #video-to-video#motion#edit

Estimates per-frame depth maps for an input video, with size, colormap and side-by-side comparison options

ByteDance · Video

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required video_url
Drop a file, or

URL pointing to the video used for depth estimation.

resolution default auto

Resolution for the output; `auto` retains the input resolution up to 1080p. Available values: 'auto', '360p', '480p', '720p', '1080p'.

Frame processing limit, capped at 2400. Setting None also allows up to 2400 frames.

Advanced model · colormap · output_fps · side_by_side · include_raw_depths
model default VDA-Large

Size of the depth estimation model; VDA-Large provides the highest quality, while VDA-Small runs fastest.

colormap default grayscale

Depth visualization palette: 'grayscale' displays raw normalized depth, while 'viridis' offers a colorblind-friendly view and 'inferno' or 'magma' provides perceptual uniformity. The recommended 'turbo' palette maps nearby regions to warm colors and distant regions to cool colors.

Frame rate of the output video. None retains the input frame rate.

POST /run/depth-anything-video?wait=20 quote → $0.40
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/depth-anything-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Depth Anything Video

Turns a video into a depth visualization with consistent results across frames. Select a model size (VDA-Small, VDA-Base or VDA-Large), a colormap (grayscale, turbo, inferno, magma or viridis) and an output `resolution` up to 1080p. Optionally render the original next to the depth video with `side_by_side`, cap frames with `max_frames` (up to 2400), or export raw depth values as an .npz file.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
video_urlrequired video
Typeurl · video
URL pointing to the video used for depth estimation.
modeloptional
Typeenum
DefaultVDA-Large
VDA-SmallVDA-BaseVDA-Large
Size of the depth estimation model; VDA-Large provides the highest quality, while VDA-Small runs fastest.
colormapoptional
Typeenum
Defaultgrayscale
grayscaleturboinfernomagmaviridis
Depth visualization palette: 'grayscale' displays raw normalized depth, while 'viridis' offers a colorblind-friendly view and 'inferno' or 'magma' provides perceptual uniformity. The recommended 'turbo' palette maps nearby regions to warm colors and distant regions to cool colors.
resolutionoptional
Typeenum
Defaultauto
auto360p480p720p1080p
Resolution for the output; `auto` retains the input resolution up to 1080p. Available values: 'auto', '360p', '480p', '720p', '1080p'.
max_framesoptional
Typeinteger | null
> 0
Frame processing limit, capped at 2400. Setting None also allows up to 2400 frames.
output_fpsoptional
Typenumber | null
> 0
Frame rate of the output video. None retains the input frame rate.
side_by_sideoptional
Typeboolean
Defaultfalse
Controls output of a video comparing the original and depth views side by side.
include_raw_depthsoptional
Typeboolean
Defaultfalse
Controls export of raw float32 depth data to a .npz file containing `depths` [N,H,W], `min_depth`, `max_depth`, `fps`, `model`, and `shape`.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "depth-anything-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 400,
    "usd": "0.40",
    "charged": 400,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "raw_depths": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
video
object {url, content_type, file_name, file_size}Video displaying depth, encoded as H.264 in MP4 format.
raw_depths
object {url, content_type, file_name, file_size} | nullRaw depth data in a .npz file, provided when `include_raw_depths` is True.

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/depth-anything-video.md. All models and guides: https://doitong.com/developers/llms.txt