Skip to content

Vidu โ€‹

Updated

Endpoint: POST https://mps.intl.tencentcloudapi.comAction: CreateAigcVideoTask

Vidu is a video generation model that supports text-to-video, first-frame / first-and-last-frame video generation, and multi-image reference generation (1โ€“7 images for q3-ad, 1โ€“14 for q3-drama). q3-mix supports multi-shot composition, and it also offers digital humans, lip sync, and effect templates, and can generate audio at the same time.

Basic Information โ€‹

ItemValue
ModelNameVidu
ModelVersionq3-ad / q3-drama / q3-mix / q3-turbo / q3-pro / q3 / q2-pro / q2 / q2-turbo
Guardrail release supportSupported

Supported Specifications by Version โ€‹

VersionResolutionAspect RatioLength
q3-ad720P / 1080P16:9 / 1:1 / 9:16โ€”
q3-drama1080P16:9 / 9:16โ€”
q3-adโ€”โ€”โ€”
q3-adโ€”โ€”โ€”
q3-adโ€”โ€”โ€”
q3-dramaโ€”โ€”โ€”
q3-dramaโ€”โ€”โ€”

Input Conditions โ€‹

VersionCondition
q3-adReference image: 1โ€“7 images
q3-dramaReference image: 1โ€“7 images
q3-adResolution: 720P
AspectRatio: 16:9
Output pixels: 1280ร—720
q3-adResolution: 1080P
AspectRatio: 1:1
Output pixels: 1440ร—1440
q3-adResolution: 720P
AspectRatio: 9:16
Output pixels: 720ร—1280
q3-dramaResolution: 1080P
AspectRatio: 16:9
Output pixels: 1920ร—1080
q3-dramaResolution: 1080P
AspectRatio: 9:16
Output pixels: 1080ร—1920

Video generation based on image references and registered reference subjects is supported. The q3 series supports automatic cut transitions and simultaneous audio generation.

Request Parameters โ€‹

ParameterRequiredTypeDescription
ModelNameRequiredStringFixed value Vidu
ModelVersionOptionalStringq3-ad / q3-drama / q3-mix / q3-turbo / q3-pro / q3 / q2-pro / q2 / q2-turbo
PromptRequiredStringGeneration prompt. In text input mode, write up to 2000 characters
NegativePromptOptionalStringElements to exclude from the result. Applied in supported models
EnhancePromptOptionalBooleanAutomatic prompt correction. Default value false
ImageUrlOptionalStringFirst frame image URL. Must be externally accessible and no larger than 10MB
LastImageUrlOptionalStringLast frame image URL. Used together with ImageUrl
ImageInfos.NOptionalArrayReference image array. ImageUrl / ReferenceType, etc.
DurationOptionalIntegerGeneration length (seconds). Only the allowed values for each model are applied
ExtraParametersOptionalObjectResolution / AspectRatio / EnableAudio
AdditionalParametersOptionalStringA JSON string containing model-specific options. For the seed delivery format, see Additional settings
SubjectInfos.NOptionalArrayInformation about registered reference subjects. Id / Name / VoiceId / ImageUrls / VideoUrls
SceneTypeOptionalStringtemplate_effect (effect template)
ExtraParameters.
EnablelnputComplianceCheck
OptionalBooleanIf false is explicitly passed, input moderation is released. Contact your sales representative before use
ExtraParameters.
EnableOutputComplianceCheck
OptionalBooleanIf false is explicitly passed, output moderation is released. Contact your sales representative before use

Request Example โ€‹

text-to-video โ€‹

json
{
  "ModelName": "Vidu",
  "ModelVersion": "q3-pro",
  "Prompt": "a paper boat drifting down a rainy street, warm lamplight",
  "Duration": 5,
  "ExtraParameters": {
    "Resolution": "1080P",
    "AspectRatio": "16:9",
    "EnableAudio": true
  },
  "Operator": "admin",
  "StoreCosParam": {
    "CosBucketName": "<bucket-appid>",
    "CosBucketRegion": "<bucket-region>",
    "CosBucketPath": "/aigc/"
  },
  "EnhancePrompt": false
}

Response Example โ€‹

json
{
  "Response": {
    "Status": "DONE",
    "ErrCode": "",
    "Message": "ok",
    "Resolution": "1280x720",
    "VideoUrls": [
      "https://example.com/output/vidu.mp4"
    ],
    "RequestId": "7c43c2f7-ff98-45c4-9ac5-5742367c1a21"
  }
}

Special Settings โ€‹

Guardrail Release โ€‹

Input and output moderation can be configured separately.

To use the guardrail release parameter, you must first contact your sales representative to confirm usage permission. Even on supported engines, the guardrail release is applied only when the parameter is explicitly passed. If the parameter is omitted, it is not released.

ParameterRelease ValueApplied To
ExtraParameters.EnablelnputComplianceCheckfalseInput moderation release
ExtraParameters.EnableOutputComplianceCheckfalseOutput moderation release

Merge the following settings into an existing generation request. To release both input and output moderation, pass both fields together.

json
{
  "ExtraParameters": {
    "EnablelnputComplianceCheck": false,
    "EnableOutputComplianceCheck": false
  }
}

Supported Capabilities by Version โ€‹

VersionFeature
q3-mixHigh screen completeness with support for automatic cut transitions and simultaneous audio generation. Dedicated to reference-based generation
q3-turboAutomatic cut transitions, simultaneous audio generation, fastest generation speed
q3-proHigh-quality results with audio
q3Automatic cut transitions, simultaneous audio generation, multi-angle scene composition
q2-proSupports reference video, video editing, and video replacement
q2 / q2-turboDynamic motion and detail expression

Supported Modes โ€‹

ModeDescriptionSupported Version
text-to-videoGenerates from a prompt only. Up to 5000 charactersq3-turbo / q3-pro / q2
image-to-videoUses image 1 image as the first frameq3-turbo / q3-pro / q2-pro / q2-turbo
First / Last FrameUses image 2 images as the first and last framesq3-turbo / q3-pro / q2-pro / q2-turbo
Reference generation (general image)Maintains the same subject across multiple imagesq3-ad / q3-drama / q3-mix / q3-turbo / q3 / q2-pro / q2
Reference generation (reference subject)Creates a reference subject ID and references it with @reference subject idq3-turbo / q3 / q2-pro / q2 (video reference subject is q2-pro only)

Reference Image Generation โ€‹

Specify the reference image in ImageInfos.ImageUrl.

json
{
  "ModelName": "Vidu",
  "ModelVersion": "q3-ad",
  "Prompt": "The red car moves slowly along the street. Smooth continuous camera movement.",
  "ImageInfos": [
    {
      "ImageUrl": "https://example.com/reference.jpg"
    }
  ],
  "Duration": 3,
  "ExtraParameters": {
    "Resolution": "720P",
    "AspectRatio": "16:9",
    "EnableAudio": true
  },
  "StoreCosParam": {
    "CosBucketName": "example-1250000000",
    "CosBucketRegion": "ap-seoul",
    "CosBucketPath": "/aigc/video/"
  },
  "Operator": "app"
}
json
{
  "ModelName": "Vidu",
  "ModelVersion": "q3-drama",
  "Prompt": "The red car moves slowly along the street. Smooth continuous camera movement.",
  "ImageInfos": [
    {
      "ImageUrl": "https://example.com/reference.jpg"
    }
  ],
  "Duration": 12,
  "ExtraParameters": {
    "Resolution": "1080P",
    "AspectRatio": "16:9",
    "EnableAudio": true
  },
  "StoreCosParam": {
    "CosBucketName": "example-1250000000",
    "CosBucketRegion": "ap-seoul",
    "CosBucketPath": "/aigc/video/"
  },
  "Operator": "app"
}

Additional Options โ€‹

Length Range

q3-ad is 3โ€“16 seconds. q3-drama is 8โ€“12 seconds. Enter reference images as ImageInfos.ImageUrl with a maximum of 7 images. The q2 series is 1โ€“10 seconds. Write Prompt in 2000 characters or fewer.

Built with VitePress ยท Deployed on Tencent EdgeOne Pages