Create Task
POST
/ent/v2/img2videoVidu 1.5
Authorizationstring*Replace {your api key} with your API key
Token {your api key}modelstring*Model name
vidu1.5: Large motion amplitudeimagesstring*The first frame image.The model uses the image provided in this parameter as the first frame to generate the video.Note 1: Accepts a Base64-encoded image or an image URL (make sure it is accessible).Note 2: Only accepts .Note 3: Supported formats: , , , .Note 4: The aspect ratio of the image must be less than .Note 5: The image size must not exceed .Note 6: The byte length after Base64 decoding must be less than , and the encoding must include an appropriate content type string. For instance,
Authorizationstring*Replace {your api key} with your API key
Token {your api key}idstring*Task ID, returned by the task creation API upon successful creation
data:image/png;base64,{base64_encode}promptstringText prompt
A textual description for video generation.
Note 1: Maximum length: 2000 characters.
Note 2: If the is_rec parameter for recommended prompts is used, the model will ignore the prompt entered in this parameter.
audiobooleanWhether to use direct audio-video generation capability. Default: false. Enumerated values:
false: No direct audio-video generation, outputs silent video.true: Direct audio-video generation, outputs video with dialogue and background sound.voice_id parameter takes effect only when this parameter is true.true.voice_idstringVoice ID, used to determine the voice character in the video. The system will automatically recommend one if left empty. Optional values can be found in the Voice List.
You can also use the Voice Cloning API to clone any voice. The voice_id parameters can be used interchangeably.
is_recbooleanWhether to use the recommended prompt.
true: Yes. The system automatically recommends a prompt and generates the video using the recommended prompt content. The number of recommended prompts = 1.false: No. The video is generated based on the input prompt.durationintegerVideo duration.
seedintegerRandom seed
resolutionstringResolution. The default value depends on the model and video duration:
movement_amplitudestringThe movement amplitude of objects in the frame
Defaults to auto, accepted values: auto, small, medium, large
payloadstringTransparent transmission parameter
No processing, only data transmission.
Note: Maximum of 1048576 characters.
off_peakbooleanOff-peak mode. Defaults to false, accepted values:
true: Generate the video in off-peak mode.false: Generate the video immediately.watermarkbooleanWhether to add a watermark.
true: Add a watermark.false: Do not add a watermark.watermarked_url field to retrieve the watermarked video content. See the Get Creation API for details.wm_positionintegerWatermark position, indicating where the watermark appears in the video. Accepted values:
1: Top-left corner
2: Top-right corner
3: Bottom-right corner
4: Bottom-left corner
Default: 3
wm_urlstringWatermark content. This is an image URL.
If not provided, the default watermark is used: "Content generated by AI".
meta_datastringMetadata label. A JSON-format string, passed through transparently. You can customize the format or use the sample format below:
{
"Label": "your_label", "ContentProducer": "yourcontentproducer", "ContentPropagator": "your_content_propagator", "ProduceID": "yourproductid", "PropagateID": "your_propagate_id", "ReservedCode1": "yourreservedcode1", "ReservedCode2": "your_reserved_code2"
}
When this parameter is empty, the metadata label generated by Vidu is used by default.
callback_urlstringCallback
When creating a task, you need to actively set the callback_url with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content is the same as the return body of the Get Creation API.
The "status" in the callback response includes the following states:
processing: Task is being processed.success: Task is completed (if sending fails, it will retry the callback three times).failed: Task failed (if sending fails, it will retry the callback three times).application/jsonResponse fields
idstringTask ID
statestringProcessing state.
Accepted values:created Task created successfullyqueueing Task in queueprocessing Task is being processedsuccess Task succeededfailed Task failed
err_codestringapplication/jsonResponse fields
task_idstringTask ID generated by Vidu
statestringProcessing state.
Accepted values:
created: Task created successfullyqueueing: Task in queueprocessing: Task is being processedError code. See the Error Code table for details
creditsintegerThe number of credits consumed by this task
payloadstringThe payload parameter passed in this task call
bgmbooleanWhether BGM is used for this task call
off_peakbooleanWhether off-peak mode is used for this task call
creationsarrayCreation results
idstringCreation ID, used to identify different creations
urlstringCreation URL, valid for 24 hours
cover_urlstringCreation cover, valid for 24 hours
watermarked_urlstringsuccessfailed: Task failedmodelstringThe model name used for this call
promptstringThe prompt parameter used for this call
imagesstringThe image parameter used for this call
durationintegerThe video duration parameter used for this call
seedintegerThe random seed parameter used for this call
resolutionstringThe resolution parameter used for this call
movement_amplitudestringThe camera movement amplitude parameter used for this call
payloadstringThe payload parameter passed in this call
off_peakbooleanWhether off-peak mode is used for this call
creditsintegerThe credits used for this call
watermarkbooleanWhether the submitted task uses a watermark
created_atstringTask creation time
Watermarked creation URL, valid for 24 hours
curl --request POST \
--url 'https://api.vidu.com/ent/v2/img2video' \
--header 'Authorization: Token {your api key}' \
--header 'Content-Type: application/json' \
--data '{
"model": "vidu1.5",
"images": [
"https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/image2video.png"
],
"prompt": "The astronaut waved and the camera moved up.",
"audio": true,
"voice_id": "professional_host",
"is_rec": true,
"duration": 5,
"seed": 0,
"resolution": "1080p",
"movement_amplitude": "auto",
"payload": "string",
"off_peak": false,
"watermark": true,
"wm_position": 0,
"wm_url": "string",
"meta_data": "string",
"callback_url": "string"
}'{
"task_id": "your_task_id_here",
"state": "created",
"model": "viduq1.5",
"images": ["https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/image2video.png"],
"prompt": "The astronaut waved and the camera moved up.",
"duration": 5,
"seed": random_number,
"resolution": "1080p",
"movement_amplitude": "auto",
"payload":"",
"off_peak": false,
"credits":credits_number,
"created_at": "2025-01-01T15:41:31.968916Z"
}curl --request GET \
--url 'https://api.vidu.com/ent/v2/tasks/{your_id}/creations' \
--header 'Authorization: Token {your api key}'{
"id":"your_task_id",
"state": "success",
"err_code": "",
"credits": 4,
"payload": "",
"creations": [
{
"id": "your_creations_id",
"url": "your_generated_results_url",
"cover_url": "your_generated_results_cover_url",
"watermarked_url": "your_generated_results_watermarked_url"
}
]
}