Skip to content

Veo โ€‹

Updated

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

Veo is a video generation model that supports text-to-video and first-frame / first-and-last-frame video generation. omni supports multimodal reference generation from images and video, video editing, and state-preserving editing, with natively synchronized audio; faster versions such as 3.1-fast and 3.1-lite are also available.

Basic Information โ€‹

ItemValue
ModelNameGV
ModelVersion3.1 / 3.1-fast / 3.1-lite / omni
Guardrail release supportNot supported

It supports video reference generation and state-preserving video editing, and generates audio natively along with the video.

Request Parameters โ€‹

ParameterRequiredTypeDescription
ModelNameRequiredStringFixed value GV
ModelVersionOptionalString3.1 / 3.1-fast / 3.1-lite / omni
PromptRequiredStringGeneration prompt. See the per-version limits below
NegativePromptOptionalStringElements to exclude from the result. Applied on supported models
EnhancePromptOptionalBooleanAutomatic prompt correction. Default value false
ImageUrlOptionalStringFirst frame image URL. Must be externally accessible and 10MB or less
LastImageUrlOptionalStringLast frame image URL. Used together with ImageUrl
ImageInfos.NOptionalArrayReference image array. Category / Url / ReferenceType, etc.
DurationOptionalIntegerGeneration length (seconds). Only model-specific allowed values are applied
ExtraParametersOptionalObjectResolution / AspectRatio / EnableAudio
AdditionalParametersOptionalStringJSON string containing model-specific options. For the seed delivery format, see Additional settings

Request Example โ€‹

text-to-video โ€‹

json
{
  "ModelName": "GV",
  "ModelVersion": "3.1",
  "Prompt": "a timelapse of a blooming flower, soft sunlight",
  "Duration": 8,
  "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",
    "Message": "ok",
    "Resolution": "1920x1080",
    "VideoUrls": [
      "https://aigc-output-video-<id>.cos.<region>.myqcloud.com/<file>.mp4?q-sign-algorithm=sha1&..."
    ],
    "RequestId": "<request-id>"
  }
}

Special Settings โ€‹

Model Specifications โ€‹

ItemValue
Generation modetext-to-video, image reference generation, video reference generation, state-preserving video editing
Reference constraintsUp to 7 images without video, up to 5 images when used with video, total quota 7. Reference video must be 3 seconds or less
Prompt maximum20000 characters
AudioGenerated natively at the same time. External audio upload is โ€”
Aspect ratio16:9 / 9:16
Resolution720P / 1080P (upscale output), 2K (upscale output), 4K (upscale output)
Length and frame rate3~10 seconds, 24fps

State-Preserving Video Editing โ€‹

It continues editing from the result of a previous generation task. Put PreviousTaskId into AdditionalParameters; only tasks created within the last day can be specified.

json
{
  "ModelName": "GV",
  "ModelVersion": "3.1",
  "Prompt": "extend the shot, camera pans to the right",
  "Duration": 8,
  "AdditionalParameters": "{\"PreviousTaskId\":\"<previous-task-id>\"}",
  "Operator": "admin",
  "StoreCosParam": {
    "CosBucketName": "<bucket-appid>",
    "CosBucketRegion": "<bucket-region>",
    "CosBucketPath": "/aigc/"
  },
  "EnhancePrompt": false
}

Built with VitePress ยท Deployed on Tencent EdgeOne Pages