Crea un job video asincrono ByteDance Seedance su CometAPI con POST /v1/videos. Un unico endpoint serve Seedance 1.0 Pro, 1.5 Pro e 2.0, con richieste multipart/form-data.
curl https://api.cometapi.com/v1/videos \
-H "Authorization: Bearer <COMETAPI_KEY>" \
-F 'prompt="A slow cinematic camera push across a coastal landscape at sunrise"' \
-F 'model="doubao-seedance-2-0-fast"' \
-F 'seconds="5"' \
-F 'size="16:9"' \
-F 'resolution="720p"'{
"id": "task_abc123",
"task_id": "task_abc123",
"object": "video",
"model": "doubao-seedance-2-0-fast",
"status": "SUBMITTED",
"progress": 0,
"created_at": 1776681149
}model. La chiamata restituisce immediatamente un id del task e il rendering continua in background.
| Model id | Tier | Notes |
|---|---|---|
doubao-seedance-2-0 | 2.0 | Output della qualità più alta nella famiglia 2.0. |
doubao-seedance-2-0-fast | 2.0 | Variante più veloce di 2.0 per iterazioni rapide e anteprime. |
doubao-seedance-1-5-pro | 1.5 Pro | Supporta 1080p. Solo text-to-video. |
doubao-seedance-1-0-pro | 1.0 Pro | Supporta 1080p e clip più brevi a partire da 2 secondi. Solo text-to-video. |
| Field | Type | Required | Default | Allowed values |
|---|---|---|---|---|
prompt | string | yes | — | qualsiasi testo |
model | string | yes | — | doubao-seedance-2-0, doubao-seedance-2-0-fast, doubao-seedance-1-5-pro, doubao-seedance-1-0-pro |
seconds | integer | no | 5 | dipende dal modello (vedi sotto) |
size | string | no | 16:9 | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
resolution | string | no | 720p | 480p, 720p per i modelli 2.0; 480p, 720p, 1080p per 1.5 Pro e 1.0 Pro |
input_reference | file | no | — | JPEG, PNG o WebP. Accettato solo dai modelli 2.0. |
| Model | seconds range |
|---|---|
doubao-seedance-2-0, doubao-seedance-2-0-fast | da 4 a 15 |
doubao-seedance-1-5-pro | da 4 a 12 |
doubao-seedance-1-0-pro | da 2 a 10 |
400 con code: "InvalidParameter" e un messaggio relativo a duration.
input_reference. L’invio di input_reference con doubao-seedance-1-5-pro o doubao-seedance-1-0-pro restituisce HTTP 400 con un messaggio nella forma the specified task_type r2v does not support model seedance-1-5-pro. Usa questi modelli solo per text-to-video.
multipart/form-data. Per eseguire image-to-video su un modello 2.0, allega l’immagine come parte input_reference nella stessa richiesta:
curl https://api.cometapi.com/v1/videos \
-H "Authorization: Bearer <COMETAPI_KEY>" \
-F 'prompt="A slow cinematic camera push across a coastal landscape at sunrise."' \
-F 'model="doubao-seedance-2-0"' \
-F 'seconds="5"' \
-F 'size="16:9"' \
-F 'resolution="720p"' \
-F 'input_reference=@/path/to/reference.jpg'
/path/to/reference.jpg con il percorso assoluto o relativo dell’immagine che vuoi usare come ancoraggio del primo frame. I formati supportati sono JPEG, PNG e WebP.
Submit the task
prompt e model. Salva l’id restituito per il passaggio successivo.Poll the task
400 quando manca un campo obbligatorio, un valore è fuori dall’intervallo accettato oppure input_reference viene inviato a un modello che non supporta image-to-video. Restituisce HTTP 401 quando il bearer token manca o non è valido. Il body di errore usa una di due strutture; consulta gli esempi 400 e 401 nel playground per i campi esatti.Bearer token authentication. Use your CometAPI key.
Text prompt that describes the video. Required.
"A slow cinematic camera push across a coastal landscape at sunrise."
Seedance model id. Choose doubao-seedance-2-0 for the highest quality 2.0 output, doubao-seedance-2-0-fast for quick iteration on 2.0, doubao-seedance-1-5-pro for the 1.5 Pro tier, or doubao-seedance-1-0-pro for the 1.0 Pro tier. Only the two 2.0 models accept input_reference.
doubao-seedance-2-0, doubao-seedance-2-0-fast, doubao-seedance-1-5-pro, doubao-seedance-1-0-pro "doubao-seedance-2-0-fast"
Video duration in seconds. The accepted range depends on the model: doubao-seedance-2-0 and doubao-seedance-2-0-fast accept 4 to 15, doubao-seedance-1-5-pro accepts 4 to 12, and doubao-seedance-1-0-pro accepts 2 to 10. The default is 5 for every model.
2 <= x <= 155
Output aspect ratio. All Seedance models accept the same set of values.
21:9, 16:9, 4:3, 1:1, 3:4, 9:16 "16:9"
Output resolution. 480p and 720p are accepted by every model; 1080p is supported only by doubao-seedance-1-5-pro and doubao-seedance-1-0-pro.
480p, 720p, 1080p "720p"
Optional reference image. When included, the job runs in image-to-video mode and uses the image as the visual anchor. Only doubao-seedance-2-0 and doubao-seedance-2-0-fast accept this field; sending it with a 1.0 Pro or 1.5 Pro model returns HTTP 400.
Task created. Save the returned id and poll GET /v1/videos/{id}.
Task id. Use it as the path parameter for GET /v1/videos/{id}.
Object type, always video.
Echo of the requested model id.
Initial task status. A newly created task is returned as SUBMITTED.
SUBMITTED, IN_PROGRESS, SUCCESS, FAILED, ERROR Completion percentage. 0 at creation.
0 <= x <= 100Task creation time as a Unix timestamp in seconds.
Alias of id returned for compatibility. The value matches id.
curl https://api.cometapi.com/v1/videos \
-H "Authorization: Bearer <COMETAPI_KEY>" \
-F 'prompt="A slow cinematic camera push across a coastal landscape at sunrise"' \
-F 'model="doubao-seedance-2-0-fast"' \
-F 'seconds="5"' \
-F 'size="16:9"' \
-F 'resolution="720p"'{
"id": "task_abc123",
"task_id": "task_abc123",
"object": "video",
"model": "doubao-seedance-2-0-fast",
"status": "SUBMITTED",
"progress": 0,
"created_at": 1776681149
}