Saltar al cuntegna

Wan v2.6 Reference to Video

Integrar

ID dal model wan/v2.6/reference-to-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/wan/v2.6/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "videos": [
      "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"

Questa dumonda: $0,75 750 credits API Lantschar sin questa pagina

Obtegna ina clav API
Alibaba Referenza a video Inputs da referenza5–10 sfin a 1080p #reference-to-video

Generaziun da video che mantegna subjects da 1 a 3 videos da referenza, citads sco @Video1 fin @Video3

Alibaba · 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

Prompt da fin a 1500 caracters, cun subjects dal video identifitgads tras @Video1, @Video2, @Video3; ils subjects pon esser persunas, animals u objects. Prompts multi-shot utilisan questa furma: '[0-3s] Shot 1. [3-6s] Shot 2.'

•obligatori video_urls
Trametta in datoteca u

Furnir 1–3 videos da referenza per mantegnair subjects consistents, inclus persunas, animals u objects, e identifitgar els en il prompt cun @Video1, @Video2, @Video3. Mintga video sto avair almain 16 FPS, durar 2 fin 30 secundas ed esser pli pitschen che 100 MB.

duration 5 s

Definir quant ditg dura il video generà, en secundas. Per R2V tscherner 5 u 10 secundas; 15 secundas na vegnan betg sustegnidas.

aspect_ratio standard 16:9

Proporziun d'aspect dal video d'output.

resolution standard 1080p

Nivel da resoluziun per l'output video; R2V accepta 720p u 1080p, ma betg 480p.

Avanzà negative_prompt · seed · enable_prompt_expansion · multi_shots · enable_safety_checker
standard

Prompt negativ che inditgescha il cuntegnair betg giavischà, limità a 500 caracters.

Seed che renda la generaziun reproducibla. Cun definir None vegn tschernì in seed casualmain.

POST /run/wan/v2.6/reference-to-video?wait=20 calculaziun → $0,75
# 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/wan/v2.6/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "videos": [
      "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"

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 Wan v2.6 Reference to Video

Generescha in clip dals subjects (persunas, animals u objects) da 1 a 3 videos en `video_urls`, mintgin cun almain 16 FPS. Il prompt als cita sco @Video1, @Video2 ed @Video3 e po descriver scenas temporisadas. `aspect_ratio` porscha tschintg opziuns, `resolution` è 720p u 1080p, e `duration` è 5 u 10 secundas.

Parameters

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

NumTip StandardPermess Descripziun
promptobligatori
Tipstring
Prompt da fin a 1500 caracters, cun subjects dal video identifitgads tras @Video1, @Video2, @Video3; ils subjects pon esser persunas, animals u objects. Prompts multi-shot utilisan questa furma: '[0-3s] Shot 1. [3-6s] Shot 2.'
video_urlsobligatori videos
Tipurl[] · video
Furnir 1–3 videos da referenza per mantegnair subjects consistents, inclus persunas, animals u objects, e identifitgar els en il prompt cun @Video1, @Video2, @Video3. Mintga video sto avair almain 16 FPS, durar 2 fin 30 secundas ed esser pli pitschen che 100 MB.
aspect_ratioopziunal
Tipenum
Standard16:9
16:99:161:14:33:4
Proporziun d'aspect dal video d'output.
resolutionopziunal
Tipenum
Standard1080p
720p1080p
Nivel da resoluziun per l'output video; R2V accepta 720p u 1080p, ma betg 480p.
durationopziunal
Tipenum
Standard5
510
Definir quant ditg dura il video generà, en secundas. Per R2V tscherner 5 u 10 secundas; 15 secundas na vegnan betg sustegnidas.
negative_promptopziunal
Tipstring | null
Standard
Prompt negativ che inditgescha il cuntegnair betg giavischà, limità a 500 caracters.
enable_prompt_expansionopziunal
Tipboolean
Standardtrue
Controlla sche in LLM rescriva il prompt.
multi_shotsopziunal
Tipboolean
Standardtrue
Controlla da la segmentaziun da shots, disponibla mo cun enable_prompt_expansion definì a True. Il standard true utilisescha segmentaziun intelligenta per construir ina narrativa coerenta tranter shots; false mantegna il video sco in singul shot cuntinuà.
seedopziunal
Tipinteger | null
Seed che renda la generaziun reproducibla. Cun definir None vegn tschernì in seed casualmain.
enable_safety_checkeropziunal
Tipboolean
Standardtrue
Interrutur da controlla da segirezza, dal qual la configuraziun spustada pretenda l'autorisaziun dal conto. Senza questa autorisaziun vegn mintga dumonda controllada independentamain da la configuraziun; true activa il controllader.
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": "wan/v2.6/reference-to-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": 750,
    "usd": "0.75",
    "charged": 750,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_urls": [
      "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "actual_prompt": "Dance battle between Character1 and Character2, cinematic lighting, dynamic camera movement."
  },
  "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"
  }
}
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, width, height, fps, duration, num_frames}Datoteca video resultanta.
seed
integerValur seed utilisada durant la generaziun.
actual_prompt
string | nullPrompt utilisà effectivamain cura che la rescrittira è activada.

Dapli models: Referenza a video

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/wan/v2.6/reference-to-video.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt