Skip to main content
POST
/
vidu
/
ent
/
v2
/
start-end2video
curl --request POST \
  --url https://api.powertokens.ai/vidu/ent/v2/start-end2video \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "viduq3-turbo",
  "images": [
    "https://example.com/start_frame.png",
    "https://example.com/end_frame.png"
  ],
  "prompt": "A person moving from standing to sitting",
  "duration": 5
}
'
{
  "task_id": "your_task_id_here",
  "state": "created",
  "model": "viduq3-turbo",
  "images": [
    "https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/startend2video-1.jpeg",
    "https://prod-ss-images.s3.cn-northwest-1.amazonaws.com.cn/vidu-maas/template/startend2video-2.jpeg"
  ],
  "prompt": "The camera zooms in on the bird, which then flies to the right. The bird flight is smooth and natural, with a red light effect following and surrounding it from behind.",
  "duration": 5,
  "seed": 123456789,
  "resolution": "1080p",
  "audio": true,
  "off_peak": false,
  "credits": 10,
  "created_at": "2025-01-01T15:41:31.968916Z"
}

Authorizations

​
Authorization
string
header
required

Pass Authorization: Bearer <token> in the request header.

Body

application/json
​
model
enum<string>
required

Video generation model name.

  • viduq3-turbo: Compared to viduq3-pro, the generation speed is faster
Available options:
viduq3-turbo
​
images
string[]
required

Two images: first is start frame, second is end frame. Notes:

  1. Public URL or Base64 format supported
  2. Aspect ratios must be close: ratio between start/end frame must be in 0.8~1.25
  3. Supported formats: png, jpeg, jpg, webp
  4. Max size per image: 50MB
  5. The post body of the HTTP request should not exceed 20MB, and it must include an appropriate content type string
  6. Base64 format example: data:image/png;base64,{base64_encode}
Required array length: 2 elements
​
prompt
string

Text prompt for describing video generation content, with a maximum length of 5000 characters. Note: If the is_rec parameter for recommended prompts is used, the model will ignore the manually entered prompt for this parameter.

Maximum string length: 5000
​
is_rec
boolean
default:false

Whether to use the recommended prompt.

  • true: Yes, the system will automatically generate and apply a recommended prompt to create the video. The number of recommended prompts = 1
  • false: No, the video will be generated based on the user-provided prompt Note: When the recommended prompt feature is enabled, each task will consume an additional 10 credits.
​
duration
integer

Video duration in seconds. Default values vary by model:

  • viduq3-pro, viduq3-turbo: default 5, available: 1-16
  • viduq2-pro-fast, viduq2-pro, viduq2-turbo: default 5, available: 1-8
  • viduq1, viduq1-classic: default 5, available: 5
  • vidu2.0: default 4, available: 4, 8
​
seed
integer

Random seed.

  • Defaults to a random seed number
  • Manually set values will override the default random seed
​
resolution
enum<string>

Resolution (based on model & duration):

  • viduq3-pro, viduq3-turbo (1-16s): default 720p, options: 540p, 720p, 1080p
  • viduq2-pro-fast (1-8s): default 720p, options: 720p, 1080p
  • viduq2-pro, viduq2-turbo (1-8s): default 720p, options: 540p, 720p, 1080p
  • viduq1, viduq1-classic (5s): default 1080p, options: 1080p
  • vidu2.0 (4s): default 360p, options: 360p, 720p, 1080p
  • vidu2.0 (8s): default 720p, options: 720p
Available options:
360p,
540p,
720p,
1080p
​
movement_amplitude
enum<string>
default:auto

The movement amplitude of objects in the frame.

  • Default: auto
  • Accepted values: auto, small, medium, large Note: Modifying this parameter is ineffective for q2, q3 models.
Available options:
auto,
small,
medium,
large
​
bgm
boolean
default:false

Whether to add background music to the generated video.

  • Default: false
  • Acceptable values: true, false When true, the system will automatically add a suitable BGM. BGM has no time limit and the system automatically adapts. Note: BGM does not take effect when the duration of the q2 model is 9 or 10 seconds; BGM does not available in q3 models.
​
audio
boolean
default:true

Whether to use direct audio-video generation capability.

  • false: No direct audio-video generation, outputs silent video
  • true: Requires audio-video synchronization, outputs video with sound (including dialogue and sound effects) Note 1: Only the q3 models supports this parameter
​
payload
string

Transparent transmission parameters. No processing, only data transmission, with a maximum length of 1048576 characters.

Maximum string length: 1048576
​
off_peak
boolean
default:false

Off peak mode.

  • true: Off peak generate mode
  • false: Normal generate mode Notes:
  1. The off_peak mode consumes lower points (see Pricing for details)
  2. Tasks submitted in off peak mode will be generated within 48 hours. Tasks that are not completed will be automatically cancelled and their points will be refunded
  3. We also support cancel off_peak tasks
  4. Except for q3, other direct audio-video generation functions
​
callback_url
string

Callback 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 will be the same as the return body of the GET Generation 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). Vidu uses a callback signature algorithm for verification, check out the details here: Callback Signature

Response

Submission successful, returns a video task object.

​
task_id
string

Task ID.

​
state
enum<string>

Task processing state:

  • created: Task created successfully
  • queueing: Task in queue
  • processing: Task processing
  • success: Generation successful
  • failed: Task failed
Available options:
created,
queueing,
processing,
success,
failed
​
model
string

Model parameter used for this call.

​
images
string[]

Images used for this call (start frame and end frame).

​
prompt
string

Text prompt used for this call.

​
duration
integer

Video duration parameter used for this call.

​
seed
integer

Random seed parameter used for this call.

​
resolution
string

Resolution parameter used for this call.

​
bgm
boolean

Background music parameter used for this call.

​
movement_amplitude
string

Camera movement amplitude parameter used for this call.

​
payload
string

Payload parameter used for this call.

​
off_peak
boolean

Off-peak mode parameter used for this call.

​
credits
integer

Credits consumed for this call.

​
created_at
string<date-time>

Task creation time.