Saltar al cuntegna

Depth Anything Video

Integrar

ID dal model 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.ru/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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Datotecas sco l'exempel: $0,40 400 credits API · ≈ ₽42,19 tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
ByteDance Video a video fin a 1080p #video-to-video#motion#edit

Estimescha mapas da profunditad per frame per ina video d'entrada, cun opziuns per grondezza, colormap e cumparegliaziun side-by-side

ByteDance · Video

Tes emprim resultat vegn qua

Construis ina dumonda sutvart e l'exequescha cun tia clav API. Outputs vegnan copiads en nossa memorisaziun, conservads per adina u 7 dis gratuitamain.

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e ​​il pretsch s'actualiseschan durant che ti als midas.

•obligatori video_url
Trametta in datoteca u

URL che mussa il video utilisà per stimar la profunditad.

resolution standard auto

Resoluziun per l'output; `auto` mantegna la resoluziun da l'input fin a 1080p. Valurs disponiblas: 'auto', '360p', '480p', '720p', '1080p'.

Dumber maximal da frame da processar, limità a 2400. La valur None permetta era fin a 2400 frame.

Avanzà model · colormap · output_fps · side_by_side · include_raw_depths
model standard VDA-Large

Grondezza dal model d'estimaziun da la profunditad; VDA-Large porscha la meglra qualitad, entant che VDA-Small va il pli svelt.

colormap standard grayscale

Paletta da visualisaziun da la profunditad: 'grayscale' mussa la profunditad normalisada criva, entant che 'viridis' porscha ina vista adattada per persunas daltonicas e 'inferno' u 'magma' porschan uniformitad perceptiva. La paletta 'turbo' recumandada attribuescha colurs chaudas a las regiuns vischinas e colurs fraidas a las regiuns lontanas.

Frame rate dal video final. None mantegna il frame rate da l'input.

POST /run/depth-anything-video?wait=20 calculaziun → $0,40
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Executar questa dumonda

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Obtegnair ina clav API

Davart Depth Anything Video

Transfurma in video en ina visualisaziun da profunditad cun resultats consistents tranter frames. Tschernì la grondezza dal model (VDA-Small, VDA-Base u VDA-Large), ina paletta da colurs (grayscale, turbo, inferno, magma u viridis) e ina `resolution` d'output fin a 1080p. Facultativamain renda il video original sper il video da profunditad cun `side_by_side`, limita ils frames cun `max_frames` (fin a 2400), u exporta ils values crivs da profunditad sco datoteca .npz.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
video_urlobligatori video
Tipurl · video
URL che mussa il video utilisà per stimar la profunditad.
modelopziunal
Tipenum
StandardVDA-Large
VDA-SmallVDA-BaseVDA-Large
Grondezza dal model d'estimaziun da la profunditad; VDA-Large porscha la meglra qualitad, entant che VDA-Small va il pli svelt.
colormapopziunal
Tipenum
Standardgrayscale
grayscaleturboinfernomagmaviridis
Paletta da visualisaziun da la profunditad: 'grayscale' mussa la profunditad normalisada criva, entant che 'viridis' porscha ina vista adattada per persunas daltonicas e 'inferno' u 'magma' porschan uniformitad perceptiva. La paletta 'turbo' recumandada attribuescha colurs chaudas a las regiuns vischinas e colurs fraidas a las regiuns lontanas.
resolutionopziunal
Tipenum
Standardauto
auto360p480p720p1080p
Resoluziun per l'output; `auto` mantegna la resoluziun da l'input fin a 1080p. Valurs disponiblas: 'auto', '360p', '480p', '720p', '1080p'.
max_framesopziunal
Tipinteger | null
> 0
Dumber maximal da frame da processar, limità a 2400. La valur None permetta era fin a 2400 frame.
output_fpsopziunal
Tipnumber | null
> 0
Frame rate dal video final. None mantegna il frame rate da l'input.
side_by_sideopziunal
Tipboolean
Standardfalse
Controlla l'output d'in video che cumpareglia las vistas originalas e da la profunditad ina sper l'autra.
include_raw_depthsopziunal
Tipboolean
Standardfalse
Controlla l'export da las datas crivas da profunditad float32 en ina datoteca .npz che cuntegna `depths` [N,H,W], `min_depth`, `max_depth`, `fps`, `model` e `shape`.
obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.
La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.
Champs da l'output
video
object {url, content_type, file_name, file_size}Video che mussa la profunditad, codà sco H.264 en format MP4.
raw_depths
object {url, content_type, file_name, file_size} | nullDatas crivas da profunditad en ina datoteca .npz, furnidas sche `include_raw_depths` è True.

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/depth-anything-video.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt