Vidu Image-to-Video viduq3-pro-fast

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-pro-fast: Efficiently generate high-quality audio and video content with faster generation speed and high cost-effectiveness

Available options:

viduq3-pro-fast

images

string[]

required

An image to be used as the start frame of the generated video.

Only accepts 1 image
Accepts public URL or Base64 format
Supported formats: png, jpeg, jpg, webp
The aspect ratio of the images must be between 1:4 and 4:1
Single image limited to 50MB
HTTP request body should not exceed 20MB
Base64 format example: data:image/png;base64,{base64_encode}

Required array length: 1 element

prompt

string

Text prompt for describing video generation content. Note: If the recommended prompt feature is enabled (is_rec=true), the model will ignore the manually entered prompt parameter.

Maximum string length: 5000

voice_id

string

Voice ID, used to determine the voice character in the video. Q3 series models are not effective. The system will automatically recommend a suitable voice, and you can also clone any voice through the Voice Cloning API.

is_rec

boolean

default:false

Whether to use the recommended prompt.

true: Yes, the system will automatically generate and apply a recommended prompt. 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.

bgm

boolean

default:false

Whether to add background music to the generated video. Ineffective for q3 model.

true: The system will automatically add a suitable BGM, no time limit, system automatically adapts
false: Do not add background music Note: BGM does not take effect when the duration of the q2 model is 9 or 10 seconds; BGM is not available in q3 models.

audio

boolean

default:false

Whether to use direct audio-video generation capability.

false: No direct audio-video generation, outputs silent video
true: Direct audio-video generation required, outputs video with sound (including dialogue and sound effects) Note 1: The voice_id parameter takes effect only when this parameter is true Note 2: When this parameter is true, staggered mode is not supported (q3 model supports staggered mode) Note 3: When model is q3, the default value for this parameter is true

audio_type

enum<string>

default:all

Audio type, required when audio is true.

all: Sound effects + vocals
speech_only: Vocal only
sound-effect_only: Sound effects only Note: Currently, this parameter only supports audio splitting for q2, q1, and 2.0 series models.

Available options:

all,

speech_only,

sound-effect_only

duration

integer

Video duration in seconds. Default values vary by model:

viduq3-pro-fast, viduq3-pro, viduq3-turbo: default 5, available: 1-16

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-fast (1-16s): default 720p, options: 720p, 1080p
viduq3-pro, viduq3-turbo (1-16s): default 720p, options: 540p, 720p, 1080p

Available options:

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

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 The off_peak mode consumes lower points (see Pricing for details). 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. We also support cancel off_peak tasks.

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).

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.

prompt

string

Text prompt used for this call.

images

string[]

Images used for this call.

duration

integer

Video duration parameter used for this call.

audio

boolean

Whether to use audio for this call.

audio_type

string

Audio type parameter used for this call.

seed

integer

Random seed parameter used for this call.

resolution

string

Resolution 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.