Skip to content

Vega Video 1.0 Lite โ€‹

Updated

โ† Back to the Vega Video overview for version comparison and selection.

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

Vega Video 1.0 Lite (1.0-lite) is the cost- and speed-oriented video generation version: text-to-video, first-frame / last-frame / first-and-last-frame generation, and multimodal reference generation from mixed image, video and audio inputs (up to 12 in total). It outputs 480Pโ€“4K at 4โ€“15 seconds per clip, enables prompt enhancement by default, and offers fast or cinematic modes via GenerateMode / VideoQualityMode.

Basic Information โ€‹

ItemValue
ModelNamewand-vega-video
ModelVersion1.0-lite
Resolution480P / 768P / 1080P / 2K / 4K
Aspect ratio21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive
Duration4~15 seconds
Output soundSupported (AudioGeneration: Enabled)
Guardrail bypass supportSupported

Input Specifications โ€‹

1.0 Lite Reference Images โ€‹

ItemSpecification
Number of reference imagesUp to 9
Size per image file30MB or less
Image width / height256~5760px each
Image aspect ratio0.4~2.5 for the first / last frame
Image formatsJPEG / PNG / WEBP / HEIC / HEIF
First / last frame1 each
Total mixed inputsUp to 12 for images / videos / audio combined

1.0 Lite Reference Video / Audio โ€‹

ItemSpecification
Number of reference videosUp to 3
Size per video file50MB or less
Video duration2~15 seconds each, 15 seconds or less in total
Video width / height256~5760px each, width/height ratio 0.4~2.5
Video format / codecH.264 / H.265, internal audio AAC / MP3
Video resolution / total pixelsThe width / height conditions above apply
Video frame rateโ€”
Number of reference audio filesUp to 3
Size per audio file15MB or less
Audio duration2~15 seconds each, 15 seconds or less in total
Audio formatsWAV / MP3
Audio input conditionMust be submitted together with 1 or more images or videos. Audio cannot be submitted on its own

Lite applies its size limits per file, with no separate aggregate size limit. The prompt can be at most 7,000 characters. First / last frame mode uses the aspect ratio of the input image, and reference generation supports adaptive.

Request Parameters โ€‹

ParameterRequiredTypeDescription
ModelNameRequiredStringFixed value wand-vega-video
ModelVersionRequiredString1.0-lite
PromptConditionalStringAt most 7000 characters. Required when FileInfos is empty
FileInfos.NOptionalArrayReference inputs. Usage is FirstFrame (first frame) / LastFrame (last frame) / Reference (reference)
OutputConfig.ResolutionOptionalString480P / 768P / 1080P / 2K / 4K
OutputConfig.DurationOptionalInteger4~15
OutputConfig.AspectRatioOptionalString21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive
OutputConfig.StorageModeOptionalStringTemporary (7 days) / Permanent (permanently stored as a VOD media asset)
OutputConfig.MediaNameOptionalStringMedia name shown when StorageMode=Permanent
OutputConfig.AudioGenerationOptionalStringEnabled / Disabled
ExtInfoOptionalStringA JSON-encoded string within 2. Used to pass the additional parameters below (WandVegaParameters).

Recommended Notation for the First Frame

The first frame is specified with FileInfos.Usage="FirstFrame", and the last frame specifies Usage="LastFrame" in a separate entry. LastFrameUrl / LastFrameFileId are kept for compatibility with legacy calls, but Usage="LastFrame" is recommended for new implementations.

Output Resolution โ€‹

Specified via OutputConfig.Resolution and AspectRatio. Output sizes based on 16:9 are as follows.

ResolutionAspectRatioOutput resolution
480P16:9864x480
768P16:91344x768
1080P16:91920x1080
2K16:92560x1440
4K16:93840x2160
ParameterRequiredTypeDescription
OutputConfig.
InputComplianceCheck
OptionalStringPassing Disabled explicitly bypasses input moderation. Contact your sales representative before using it
OutputConfig.
OutputComplianceCheck
OptionalStringPassing Disabled explicitly bypasses output moderation. Contact your sales representative before using it

Request Examples โ€‹

Text-to-Video โ€‹

json
{
  "SubAppId": 0,
  "ModelName": "wand-vega-video",
  "ModelVersion": "1.0-lite",
  "Prompt": "a calico cat sitting on a wooden windowsill, sunlight streaming in, gentle breeze",
  "OutputConfig": {
    "Resolution": "1080P",
    "Duration": 5,
    "AspectRatio": "16:9",
    "StorageMode": "Temporary"
  }
}

First Frame Generation (FirstFrame) โ€‹

Pins a single image as the first frame and generates what follows.

json
{
  "SubAppId": 0,
  "ModelName": "wand-vega-video",
  "ModelVersion": "1.0-lite",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Usage": "FirstFrame",
      "Url": "https://<cdn>/first.png"
    }
  ],
  "Prompt": "she slowly opens her eyes and looks into the distance",
  "OutputConfig": {
    "Resolution": "1080P",
    "Duration": 5,
    "AspectRatio": "16:9",
    "StorageMode": "Temporary"
  }
}

Last Frame Generation (LastFrame) โ€‹

Specifying Usage="LastFrame" pins only the last frame; the model picks the starting point freely.

json
{
  "SubAppId": 0,
  "ModelName": "wand-vega-video",
  "ModelVersion": "1.0-lite",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Usage": "LastFrame",
      "Url": "https://<cdn>/last.png"
    }
  ],
  "Prompt": "the scene settles on a quiet window at dusk",
  "OutputConfig": {
    "Resolution": "1080P",
    "Duration": 5,
    "AspectRatio": "16:9",
    "StorageMode": "Temporary"
  }
}

First & Last Frame Generation (FirstFrame + LastFrame) โ€‹

Putting both FirstFrame and LastFrame into FileInfos at once bridges the two frames naturally.

json
{
  "SubAppId": 0,
  "ModelName": "wand-vega-video",
  "ModelVersion": "1.0-lite",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Usage": "FirstFrame",
      "Url": "https://<cdn>/first.png"
    },
    {
      "Type": "Url",
      "Category": "Image",
      "Usage": "LastFrame",
      "Url": "https://<cdn>/last.png"
    }
  ],
  "Prompt": "smooth transition between the two scenes",
  "OutputConfig": {
    "Resolution": "1080P",
    "Duration": 5,
    "AspectRatio": "16:9",
    "StorageMode": "Temporary"
  }
}

Multimodal Reference (Reference) โ€‹

Submits images, video, and audio together to build a reference video. Images are specified with Usage="Reference".

json
{
  "SubAppId": 0,
  "ModelName": "wand-vega-video",
  "ModelVersion": "1.0-lite",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Usage": "Reference",
      "Url": "https://<cdn>/ref1.png"
    },
    {
      "Type": "Url",
      "Category": "Image",
      "Usage": "Reference",
      "Url": "https://<cdn>/ref2.png"
    },
    {
      "Type": "Url",
      "Category": "Video",
      "Usage": "Reference",
      "Url": "https://<cdn>/ref.mp4"
    }
  ],
  "Prompt": "blend the subjects naturally into the reference video environment",
  "OutputConfig": {
    "Resolution": "1080P",
    "Duration": 5,
    "AspectRatio": "16:9",
    "StorageMode": "Temporary"
  }
}

Responses and Result Query โ€‹

Task Acceptance Response โ€‹

TaskId is returned when the generation request is accepted. Use that ID to query the completion status and the output.

json
{
  "TaskId": "<task-id>",
  "RequestId": "<request-id>"
}

Result Query โ€‹

Poll DescribeTaskDetail at intervals of 3 seconds. While Status is PROCESSING, keep querying; FINISH together with ErrCode=0 means success; if it is FAIL, check the cause via Message.

json
{
  "SubAppId": 0,
  "TaskId": "<task-id>"
}

Completion Response โ€‹

The default storage method is a temporary URL valid for 7 days. Download it within that period, or store it with StorageMode=Permanent.

json
{
  "AigcVideoTask": {
    "Status": "FINISH",
    "ErrCode": 0,
    "Progress": 100,
    "Output": {
      "FileInfos": [
        {
          "FileUrl": "http://<host>.vod2.myqcloud.com/.../aigcVideoGenFile.mp4",
          "ExpireTime": "2026-09-15T10:29:48Z",
          "MetaData": {
            "Width": 1920,
            "Height": 1080,
            "Duration": 5.07,
            "Container": "mov,mp4,m4a",
            "Bitrate": 9494850
          }
        }
      ]
    }
  }
}

Special Settings โ€‹

ExtInfo (WandVegaParameters) โ€‹

Lite accepts model-specific options through the WandVegaParameters key of ExtInfo. It is JSON-encoded within 2, and the inner object is wrapped as a string once more.

ParameterTypeValue / behavior
EnhancePromptModeStringauto / enable / disable. Omitting it or setting auto enables prompt optimization
ReturnVegaUsageBooleanRequests that usage be returned. Default false
ModerationModeStringModeration_L1: basic moderation, the default. Moderation_L2: enhanced moderation. Independent of guardrail bypass
GenerateModeStringStandard / Fast / StandardMovie
VideoQualityModeStringStandard / Fast / SuperFast. Specify OutputConfig.Resolution together with it

Standard is used for standard generation, Fast for fast generation, and StandardMovie for a natural cinematic texture.

python
import json

ext_inner = {
    "EnhancePromptMode": "disable",
    "ReturnVegaUsage": True,
    "GenerateMode": "Standard",
    "VideoQualityMode": "Standard",
}
ext_info = json.dumps({
    "WandVegaParameters": json.dumps(ext_inner)
})

The following example turns prompt optimization off and requests that usage be returned.

json
{
  "SubAppId": 123456789,
  "ModelName": "wand-vega-video",
  "ModelVersion": "1.0-lite",
  "Prompt": "A blue ceramic cup on a wooden table. A slow camera dolly forward, soft natural light.",
  "OutputConfig": {
    "StorageMode": "Temporary",
    "Resolution": "480P",
    "AspectRatio": "16:9",
    "Duration": 4,
    "AudioGeneration": "Disabled"
  },
  "ExtInfo": "{\"WandVegaParameters\":\"{\\\"EnhancePromptMode\\\":\\\"disable\\\",\\\"ReturnVegaUsage\\\":true}\"}"
}

When usage is returned, AigcVideoTask.Output.Usage.CompletionTokens is the number of output tokens and AigcVideoTask.Output.Usage.TotalTokens is the total number of tokens including the input.

Permanent Storage โ€‹

To keep the result as a VOD media asset, set OutputConfig.StorageMode to Permanent. From then on you can manage it just like regular VOD media.

json
{
  "OutputConfig": {
    "StorageMode": "Permanent",
    "MediaName": "wand-vega-video-lite-sample"
  }
}

Guardrail Bypass โ€‹

Input and output moderation can be configured separately.

Before using the guardrail bypass parameters, you must contact your sales representative to confirm your usage permissions. Even on supported engines, guardrails are bypassed only when the corresponding parameter is passed explicitly. Omitting the parameter leaves them in place.

ParameterBypass valueApplies to
OutputConfig.InputComplianceCheckDisabledBypasses input moderation
OutputConfig.OutputComplianceCheckDisabledBypasses output moderation

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

json
{
  "OutputConfig": {
    "InputComplianceCheck": "Disabled",
    "OutputComplianceCheck": "Disabled"
  }
}

Built with VitePress ยท Deployed on Tencent EdgeOne Pages