SeedanceImage-to-Video

Method: POSTEndpoint: /v2/videos/generations

Unified Interface Format

Request Parameters

Header Parameters

Authorization
string
Optional
Default Value:
Bearer {{YOUR_API_KEY}}

Body Parameters application/json

prompt
string
Required
The text prompt supports Chinese and English, with a maximum length of 800 characters. Each Chinese character or letter counts as one character. Content that exceeds this limit will be truncated.
Text prompts support both Chinese and English, with a maximum length of 800 characters. Each Chinese character or letter counts as one character. Content beyond this limit is truncated.
Example: A kitten running in the moonlight.
Example: a kitten runs under the moonlight.
model
enum<string>
Required
Model name. Example: doubao-seedance-1-0-pro-250528
Enum Values:
doubao-seedance-1-0-pro-250528
Latest models
  // provider-specific example normalized for English documentation
doubao-seedance-1-0-lite-t2v-250428
Text-to-Video
doubao-seedance-1-0-lite-i2v-250428
Image-to-Video - first frame / start-end frames / reference image
images
array
[string]
  // provider-specific example normalized for English documentation
Required
duration
enum<integer>
Optional
Duration of the generated video in seconds. This parameter is fixed at 5 and cannot be changed. The model always generates a 5-second video.
Enum Values:
5
10
resolution
enum<string>
Video resolution
Optional
Enum Values:
480p
720p
1080p
ratio
string
Optional
Aspect ratio of the generated video
21:9
16:9
4:3
1:1
3:4
9:16
9:21
keep_ratio: the generated video's aspect ratio stays consistent with the uploaded image.
adaptive: automatically chooses the most suitable aspect ratio based on the uploaded image.
watermark
boolean
Optional
Specifies whether to add a watermark. The watermark appears in the lower-right corner and reads "Generated by AI".
seed
integer
Optional
A random seed used to control the randomness of the generated content. The value must be in the range [0, 2147483647].
If this parameter is not provided, the algorithm automatically generates a random seed. To keep the generated content relatively stable, reuse the same seed value.
camerafixed
boolean
Optional
Whether to lock the camera
true: locks the camera. The platform appends a fixed-camera instruction to the prompt, but the effect is not guaranteed.
false: does not lock the camera.
return_last_frame
boolean
Optional
  // provider-specific example normalized for English documentation
true: returns the last frame of the generated video as a PNG image with the same dimensions as the video and no watermark. You can obtain it through the video-task query endpoint.
false: does not return the last-frame image.
generate_audio
boolean
Optional
Example
{
"prompt"
:
"dance"
,
"model"
:
"doubao-seedance-1-0-lite-t2v-250428"
,
"images"
:
[
"https://webstatic.aiproxy.vip/dist/demo.jpg"
]
}

Example Request

Shell

curl --location --request POST '/v2/videos/generations' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "prompt": "dance",
    "model": "doubao-seedance-1-0-lite-t2v-250428",
    "images": [
        "https://webstatic.aiproxy.vip/dist/demo.jpg"
    ]
}'

Response

🟢 200 Success

Content Type: application/json

Response Schema

task_id
string
Required

Example

{
    "task_id": "cgt-20250831141439-sqmgf"
}