Saltar al cuntegna

Seedance 2.0 US Reference to Video

Integrar

ID dal model bytedance/seedance-2.0/us/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/bytedance/seedance-2.0/us/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"
  }'

# 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"

Datotecas sco l'exempel: $5,571 5 571 credits API tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
ByteDance Referenza a video Audio nativOutput 4KInputs da referenzaLipsync4–15 sfin a 4k #stylized#transform

Video dad in prompt plus maletgs, videos e clips audio da referenza, cun proporziuns fin a 21:9 e 4k

Fatg sin Doitong

Ovras publicas fatgas cun Seedance 2.0 US da la communitad Doitong. Reutilisescha in prompt cun in clic.

Ovras publicas mussadas: 16
Use the input image as the base scene and visual appearance. Use the reference video strictly as ... Video

Use the input image as the base scene and visual appearance. Use the reference video strictly as a motion reference for the dog’s movement. The dog must move exactly like in the reference video: - same gait (trotting rhythm) - same speed and tempo - same head motion and body dynamics - same ear...

First-person POV of a dog trotting forward along the path at a realistic, moderate speed (approxi... Video

First-person POV of a dog trotting forward along the path at a realistic, moderate speed (approximately 8 km/h). The camera is positioned low, at the natural height of the dog’s head. The motion follows a true trotting gait: steady, rhythmic, grounded movement with gentle vertical bounce and...

Subject: Young woman with dark hair, pale skin, glowing green eyes. Context: Dark, shadowy room. ... Video

Subject: Young woman with dark hair, pale skin, glowing green eyes. Context: Dark, shadowy room. Action: Slow subtle breathing, slight blink. Cold direct gaze at camera. Finger pressed to lips. Minimal movement. Style: Cinematic, hyperrealistic, mysterious, intense. Camera motion: Static shot, no...

First-person POV of a dog running forward along the path at a realistic, moderate speed (approxim... Video

First-person POV of a dog running forward along the path at a realistic, moderate speed (approximately 10 km/h). The camera is positioned low, at the natural height of the dog’s head. The motion follows a true trotting gait: steady, rhythmic, grounded movement with gentle vertical bounce and...

Очень медленный финальный наезд камеры. Пламя свечи на переднем плане горит ярче, создавая блики.... Video

Очень медленный финальный наезд камеры. Пламя свечи на переднем плане горит ярче, создавая блики. Dialogue in this scene: Астролог: "Но в марте будет одна дата… когда решение изменит всё. Напишите в комментариях “Овен” — и я сделаю отдельный разбор." No background music.

A close-up portrait of a striking cyberpunk woman with sleek dark hair partially wet and falling ... Video

A close-up portrait of a striking cyberpunk woman with sleek dark hair partially wet and falling around her face. She’s wearing glossy, high-tech neon visor goggles with a vivid color gradient — bright yellow, orange, and pink reflecting glowing city lights. Her expression is confident and...

Ultra-realistic scene featuring miniature construction workers in orange vests and hard hats, act... Video

Ultra-realistic scene featuring miniature construction workers in orange vests and hard hats, actively working on a giant [pizza]. The tiny workers are using small tools, cranes, and machines to [assemble]. The [pizza] is placed on a metal surface or kitchen countertop. Steam or particles rise...

Slow motion. Low angle camera tilting up at Ilya. Warm light from the kitchen intensifies behind ... Video

Slow motion. Low angle camera tilting up at Ilya. Warm light from the kitchen intensifies behind him, making him look heroic. On-screen dialogue (characters speak with lip-sync): Илья: "Не трогай её!"; Бабушка Нина: "Илья, отойди! Он же…" No background music.

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 text che dirigia la generaziun dal video.

video_urls
Trametta in datoteca u · fin a 3

Referenzas video per la generaziun, furnidas sco datotecas MP4 u MOV e identifitgadas en il prompt cun @Video1, @Video2 e las ulteriuras designaziuns numeradas. Mintga video sto avair ina resoluziun da circa 480p (640x640) fin circa 720p (834x1112). Il set è limità a 3 videos cun totalmain main che 50 MB e ina durada aggregada da 2 fin 15 secundas.

duration auto

Selecziun da la lunghezza dal video: `auto` surdat la tscherna al model cun agid dal prompt, entant che ina durada explicita sto esser da 4 fin 15 secundas.

resolution standard 720p

Resoluziun output: 480p prioritisescha la sveltezza, 720p porscha in equiliber, 1080p dat auta qualitad e 4k la qualitad la pli auta.

aspect_ratio standard auto

Quotiant d'aspect da l'output: 16:9 dat format panoramic, 9:16 format vertical, 1:1 format quadrat e 21:9 format cinematic ultralarg. Tscherna `auto` per laschar il model tscherner il quotiant.

Avanzà images · audios · bitrate_mode · codec · end_user_id
image_urls
Trametta in datoteca u · fin a 9

Referenzas da maletgs per la direcziun dal video, limitadas a 9 maletgs e suttamessas ad ina limita da 12 datotecas per tut las modalidades. Mintga maletg po avair maximalmain 30 MB e sto utilisar JPEG, PNG u WebP. Utilisescha @Image1, @Image2 e las ulteriuras designaziuns numeradas per identifitgar questas referenzas en il prompt.

audio_urls
Trametta in datoteca u · fin a 3

Las referenzas audio per la direcziun dal video pretendan almain ina referenza da maletg u video accumpagnanta. Furnescha datotecas MP3 u WAV da maximalmain 15 MB mintgina, cun maximalmain 3 datotecas e ina durada aggregada limitada a 15 secundas. Identifitgescha ellas en il prompt cun @Audio1, @Audio2 e las ulteriuras designaziuns numeradas.

bitrate_mode standard standard

Tscherna il bitrate da la codificaziun output: 'standard' mantegna il standard, entant che 'high' dumonda al model da meglierar la qualitad da codificaziun a cust d'ina datoteca pli gronda.

codec standard auto

Selecziun dal codec video: `auto` lascha il cumportament dal codec standard invarià, `H264` tscherna H.264 e `H265` tscherna H.265.

Identifitgader unic attribuì a l'utilisader final.

POST /run/bytedance/seedance-2.0/us/reference-to-video?wait=20 calculaziun → $5,571
# 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/bytedance/seedance-2.0/us/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"
  }'

# 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 Seedance 2.0 US Reference to Video

Construes in video a partir d’in prompt textual guidà da medias da referenza: fin a 9 maletgs en `image_urls`, 3 clips en `video_urls` e 3 datotecas audio en `audio_urls`. Referenziescha ad els en il prompt sco @Image1, @Video1, @Audio1 e uschia vinavant. L’output ha ina durada da 4 fin a 15 secunda u auto, en 480p, 720p, 1080p u 4k, en proporziuns da maletg da 9:16 fin a 21:9. L’audio sincronisà vegn generà per standard.

Parameters

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

NumTip StandardPermess Descripziun
promptobligatori
Tipstring
Prompt da text che dirigia la generaziun dal video.
image_urlsopziunal images
Tipurl[] · image
≤ 9 elements
Referenzas da maletgs per la direcziun dal video, limitadas a 9 maletgs e suttamessas ad ina limita da 12 datotecas per tut las modalidades. Mintga maletg po avair maximalmain 30 MB e sto utilisar JPEG, PNG u WebP. Utilisescha @Image1, @Image2 e las ulteriuras designaziuns numeradas per identifitgar questas referenzas en il prompt.
video_urlsopziunal videos
Tipurl[] · video
≤ 3 elements
Referenzas video per la generaziun, furnidas sco datotecas MP4 u MOV e identifitgadas en il prompt cun @Video1, @Video2 e las ulteriuras designaziuns numeradas. Mintga video sto avair ina resoluziun da circa 480p (640x640) fin circa 720p (834x1112). Il set è limità a 3 videos cun totalmain main che 50 MB e ina durada aggregada da 2 fin 15 secundas.
audio_urlsopziunal audios
Tipurl[] · audio
≤ 3 elements
Las referenzas audio per la direcziun dal video pretendan almain ina referenza da maletg u video accumpagnanta. Furnescha datotecas MP3 u WAV da maximalmain 15 MB mintgina, cun maximalmain 3 datotecas e ina durada aggregada limitada a 15 secundas. Identifitgescha ellas en il prompt cun @Audio1, @Audio2 e las ulteriuras designaziuns numeradas.
resolutionopziunal
Tipenum
Standard720p
480p720p1080p4k
Resoluziun output: 480p prioritisescha la sveltezza, 720p porscha in equiliber, 1080p dat auta qualitad e 4k la qualitad la pli auta.
durationopziunal
Tipenum
Standardauto
auto456789101112131415
Selecziun da la lunghezza dal video: `auto` surdat la tscherna al model cun agid dal prompt, entant che ina durada explicita sto esser da 4 fin 15 secundas.
aspect_ratioopziunal
Tipenum
Standardauto
auto21:916:94:31:13:49:16
Quotiant d'aspect da l'output: 16:9 dat format panoramic, 9:16 format vertical, 1:1 format quadrat e 21:9 format cinematic ultralarg. Tscherna `auto` per laschar il model tscherner il quotiant.
generate_audioopziunal
Tipboolean
Standardtrue
Activa quai per accumpagnar il video cun audio sincronisà. L'audio generà cuntegna discurrer adattà als moviments dals lefs, atmosfera ambientala ed effects da tun.
bitrate_modeopziunal
Tipenum
Standardstandard
standardhigh
Tscherna il bitrate da la codificaziun output: 'standard' mantegna il standard, entant che 'high' dumonda al model da meglierar la qualitad da codificaziun a cust d'ina datoteca pli gronda.
codecopziunal
Tipenum
Standardauto
autoH264H265
Selecziun dal codec video: `auto` lascha il cumportament dal codec standard invarià, `H264` tscherna H.264 e `H265` tscherna H.265.
end_user_idopziunal
Tipstring | null
Identifitgader unic attribuì a l'utilisader final.
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": "bytedance/seedance-2.0/us/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": 5571,
    "usd": "5.571",
    "charged": 5571,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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
    },
    "seed": 42
  },
  "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}Datoteca video producida da la generaziun.
seed
integerValur da seed applitgada durant la generaziun.

Dapli models: Referenza a video

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/bytedance/seedance-2.0/us/reference-to-video.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt