创建 Seedance 视频

POST

videos

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="4"' \
  -F 'size="3840x2160"'

{
  "id": "task_abc123",
  "task_id": "task_abc123",
  "object": "video",
  "model": "doubao-seedance-2-0",
  "status": "queued",
  "progress": 0,
  "created_at": 1776681149
}

从下表中为 WxH 字段选择已文档化的 size 值。

使用参考图像

只有 Seedance 2.0 模型接受 input_reference。添加一个 input_reference 文件以进行图像引导生成。对于高级多参考 Prompt，请按上传顺序重复使用同一个 multipart 字段。 Seedance 2.0 对 Prompt 如何将每张参考图像与场景关联起来很敏感。按顺序引用上传的文件，例如 [Image 1]、[Image 2] 和 [Image 3]，然后为每张图像分配明确的角色：

将 [Image 1] 用于主要主体、角色或产品。
将 [Image 2] 用于次要主体、道具或陪衬。
将 [Image 3] 用于背景、场景、光照或风格。

说明哪些内容应保持可识别、哪些可以变化，以及动作、镜头运动、视觉风格和场景。即使上传已被接受，模糊的 Prompt 也可能使生成的视频看起来像是未使用参考图像。这种 Prompt 结构比仅列出图像更可靠：

Use the uploaded images in order: keep the boy wearing glasses and a blue T-shirt from [Image 1], add the corgi puppy from [Image 2], and use the lawn from [Image 3] as the setting. Create a 4-second 3D cartoon video with the boy and puppy sitting together, a slow camera push-in, soft daylight, and no extra characters.

按模型划分的时长

如果省略 seconds，CometAPI 会请求一个 5 秒的视频片段。需要特定时长时，请将 seconds 作为字符串发送。

模型系列	支持情况 `seconds`	默认值	边界行为
Seedance 2.0 和 Seedance 2.0 Fast	`4`-`15`	`5`	使用范围内的整数秒数。
Seedance 1.5 Pro	`4`-`12`	`5`	使用范围内的整数秒数。
Seedance 1.0 Pro	`2`-`10`	`5`	使用范围内的整数秒数。

按模型划分的尺寸支持情况

下表遵循官方 Seedance 分辨率映射，并将已发布的尺寸值集中列出。对于 1080p，最右侧列列出了文档中规定的 Seedance 1.5 Pro 和 Seedance 2.0 值。Seedance 2.0 Fast 未列在该官方 1080p 表中。 4K 条目仅适用于 doubao-seedance-2-0。您可以将其用于文生视频，或用于包含 input_reference 的图生视频请求。它们不适用于 doubao-seedance-2-0-fast。请传递表中所示的准确 WxH 值。

分辨率类别	宽高比	Seedance 1.0 系列的像素值	Seedance 1.5 Pro / Seedance 2.0 / Seedance 2.0 Fast 的像素值
`480p`	`16:9`	`864x480`	`864x496`
	`4:3`	`736x544`	`752x560`
	`1:1`	`640x640`	`640x640`
	`3:4`	`544x736`	`560x752`
	`9:16`	`480x864`	`496x864`
	`21:9`	`960x416`	`992x432`
`720p`	`16:9`	`1248x704`	`1280x720`
	`4:3`	`1120x832`	`1112x834`
	`1:1`	`960x960`	`960x960`
	`3:4`	`832x1120`	`834x1112`
	`9:16`	`704x1248`	`720x1280`
	`21:9`	`1504x640`	`1470x630`
`1080p`	`16:9`	`1920x1088`	`1920x1080`
	`4:3`	`1664x1248`	`1664x1248`
	`1:1`	`1440x1440`	`1440x1440`
	`3:4`	`1248x1664`	`1248x1664`
	`9:16`	`1088x1920`	`1080x1920`
	`21:9`	`2176x928`	`2206x946`
`4K`	`16:9`	—	`3840x2160` (仅限 Seedance 2.0)
	`4:3`	—	`3326x2494` (仅限 Seedance 2.0)
	`1:1`	—	`2880x2880` (仅限 Seedance 2.0)
	`3:4`	—	`2494x3326` (仅限 Seedance 2.0)
	`9:16`	—	`2160x3840` (仅限 Seedance 2.0)
	`21:9`	—	`4398x1886` (仅限 Seedance 2.0)

请为目标模型选择文档中规定的 WxH 值。准确的 WxH 支持情况仍取决于模型，因此在依赖未记录的尺寸之前，请检查生成完成的媒体。

授权

Authorization

string

header

必填

Bearer token authentication. Use your CometAPI key.

请求体

multipart/form-data

prompt

string

必填

Text prompt that describes the video. Required. When using reference images, describe what each uploaded image should control, such as the subject from [Image 1], the secondary object from [Image 2], and the background or style from [Image 3]. Also state the action, camera motion, visual style, and scene.

示例:

"A slow cinematic camera push across a coastal landscape at sunrise."

model

enum<string>

必填

Seedance model id. Only the two 2.0 models accept input_reference.

可用选项:

doubao-seedance-2-0,

doubao-seedance-2-0-fast,

doubao-seedance-1-5-pro,

doubao-seedance-1-0-pro

示例:

"doubao-seedance-2-0"

seconds

integer

默认值:5

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.

必填范围: 2 <= x <= 15

示例:

5

size

string

Output size as an exact WxH value, such as 1280x720. For doubao-seedance-2-0 4K output, use 3840x2160, 3326x2494, 2880x2880, 2494x3326, 2160x3840, or 4398x1886. These 4K values work for text-to-video and requests with input_reference, but they do not apply to doubao-seedance-2-0-fast. Exact WxH support remains model-dependent, and an undocumented value can normalize to another size or fail.

Pattern: ^[1-9]\d{2,3}x[1-9]\d{2,3}$

示例:

"1280x720"

"1920x1080"

"3840x2160"

"3326x2494"

"2880x2880"

"2494x3326"

"2160x3840"

"4398x1886"

"1112x834"

"960x960"

"834x1112"

"720x1280"

"1080x1920"

"1470x630"

input_reference

file

Optional reference image uploaded as a multipart file. Repeat this field to send multiple reference images; the order of repeated fields is the order you should reference in the prompt as [Image 1], [Image 2], and so on. Use JPEG or PNG files for best compatibility. 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.

响应

Task created. Save the returned id and poll GET /v1/videos/{id}.

string

必填

Task id. Use it as the path parameter for GET /v1/videos/{id}.

object

string

必填

Object type, always video.

model

string

必填

Echo of the requested model id.

status

enum<string>

必填

Initial task status. Newly created tasks are returned as queued.

可用选项:

queued,

in_progress,

completed,

failed,

error

progress

integer

必填

Completion percentage. 0 at creation.

必填范围: 0 <= x <= 100

created_at

integer

必填

Task creation time as a Unix timestamp in seconds.

task_id

string

Alias of id returned for compatibility. The value matches id.

视频生成 API

获取 Seedance 视频

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="4"' \
  -F 'size="3840x2160"'

{
  "id": "task_abc123",
  "task_id": "task_abc123",
  "object": "video",
  "model": "doubao-seedance-2-0",
  "status": "queued",
  "progress": 0,
  "created_at": 1776681149
}

内容审核

API 密钥

使用参考图像

按模型划分的时长

按模型划分的尺寸支持情况

授权

请求体

响应

​使用参考图像

​按模型划分的时长

​按模型划分的尺寸支持情况

授权

请求体

响应

使用参考图像

按模型划分的时长

按模型划分的尺寸支持情况