Skip to content

Wan โ€‹

Updated

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

Wan is a video generation model that supports text-to-video, first-frame / first-and-last-frame video generation, and multimodal reference generation from images (10), video (5), and audio (5). Durations range from 2 to 30 seconds, with up to 1080P output that can be upscaled to 4K.

Basic Information โ€‹

ItemValue
ModelNameWan
ModelVersion3.0 / 3.0-prime
Prompt lengthUp to 20,000 characters
Default valueModelVersion=3.0 / Duration=5 / AspectRatio=adaptive
Guardrail disable supportSupported

Specifications Supported by Version โ€‹

VersionResolutionAspect ratioLength
3.0 / 3.0-primeDefault output: 480P / 720P / 1080P
Upscaled output: 2K / 4K
16:9 / 9:16 / 4:3 / 3:4 / 1:1 / adaptive2โ€“30 seconds; with a reference video, input + output must be 30 seconds or less

Input Conditions โ€‹

ItemCondition
Output frame rate30fps
Reference imageUp to 10
Reference videoUp to 5, 15 seconds in total
Reference audioUp to 5, 15 seconds in total

3.0 is the standard version and 3.0-prime is the fast version.

Request Parameters โ€‹

ParameterRequiredTypeDescription
ModelNameRequiredStringFixed value Wan
ModelVersionOptionalString3.0 / 3.0-prime
PromptRequiredStringGeneration prompt. Up to 20,000 characters
FileInfos.NOptionalArrayReference input. Usage is FirstFrame / LastFrame / Reference
OutputConfig.ResolutionOptionalString480P / 720P / 1080P / 2K / 4K
OutputConfig.DurationOptionalIntegerVideo length (seconds). Default 5
OutputConfig.AspectRatioOptionalStringadaptive / 16:9 / 4:3 / 1:1 / 3:4 / 9:16
OutputConfig.
InputComplianceCheck
OptionalStringPassing Disabled explicitly disables input moderation. Contact your sales representative before use
OutputConfig.
OutputComplianceCheck
OptionalStringPassing Disabled explicitly disables output moderation. Contact your sales representative before use

Request Example โ€‹

json
{
  "SubAppId": 123456789,
  "ModelName": "Wan",
  "ModelVersion": "3.0",
  "Prompt": "a woman walks through a sunlit marketplace, camera follows behind her",
  "OutputConfig": {
    "Resolution": "1080P",
    "Duration": 10,
    "AspectRatio": "9:16",
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

Response Example โ€‹

json
{
  "AigcVideoTask": {
    "Status": "FINISH",
    "ErrCode": 0,
    "Progress": 100,
    "Output": {
      "FileInfos": [
        {
          "FileUrl": "http://<host>.vod2.myqcloud.com/.../aigcVideoGenFile.mp4",
          "ExpireTime": "2026-08-01T10:29:48Z",
          "MetaData": {
            "Width": 1920,
            "Height": 1080,
            "Duration": 5.07,
            "Container": "mov,mp4,m4a",
            "Bitrate": 9494850
          }
        }
      ]
    }
  }
}

Special Settings โ€‹

Guardrail Disable โ€‹

Input and output moderation can be configured separately.

To use the guardrail disable parameters, first contact your sales representative to confirm usage permission. Even on supported engines, guardrails are disabled only when the corresponding parameter is passed explicitly. If the parameter is omitted, guardrails are not disabled.

ParameterDisable valueApplies to
OutputConfig.InputComplianceCheckDisabledInput moderation disabled
OutputConfig.OutputComplianceCheckDisabledOutput moderation disabled

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

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

First/Last Frame Generation โ€‹

With FileInfos.N.Usage, specify FirstFrame / LastFrame.

json
{
  "SubAppId": 123456789,
  "ModelName": "Wan",
  "ModelVersion": "3.0",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/first.png",
      "Usage": "FirstFrame"
    },
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/last.jpg",
      "Usage": "LastFrame"
    }
  ],
  "Prompt": "she opens the window, looks into the distance, then runs out of the castle and rides away",
  "OutputConfig": {
    "Duration": 10,
    "Resolution": "2K",
    "AspectRatio": "9:16",
    "StorageMode": "Permanent"
  },
  "SessionContext": "job-001"
}
InputConstraint
First/last frame formatJPEG / JPG / opaque PNG / BMP / WEBP
First/last frame resolution[240, 8000] pixels on one side
First/last frame aspect ratio8:1 or less
First/last frame size20MB or less

First/Last Frame Input

Wan generates with a first frame 1 or a first/last frame combination.

Multimodal Reference Generation โ€‹

Specify images, video, and audio as references with Usage=Reference, and distinguish the type with Category.

InputConstraint
ImageUp to 10. JPEG / JPG / opaque PNG / BMP / WEBP. [240, 8000] pixels on one side, aspect ratio 8:1 or less, 20MB or less
VideoUp to 5. mp4 / mov. 1~15 seconds each, 15 seconds or less in total. [240, 4096] pixels on one side, aspect ratio 8:1 or less, 100MB or less each
AudioUp to 5. wav / mp3. 1~15 seconds each, 15 seconds or less in total. 15MB or less each
json
{
  "SubAppId": 123456789,
  "ModelName": "Wan",
  "ModelVersion": "3.0",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/ref1.png",
      "Usage": "Reference"
    },
    {
      "Type": "Url",
      "Category": "Video",
      "Url": "https://<cos>/ref2.mp4",
      "Usage": "Reference"
    }
  ],
  "Prompt": "the character from the reference image walks through the scene in the reference video",
  "OutputConfig": {
    "Duration": 10,
    "Resolution": "1080P",
    "AspectRatio": "16:9",
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

First/Last Frame and Reference Modes

Choose either the first/last frame mode or the multimodal reference mode. In reference mode, images / video / audio can be combined.

Video Length โ€‹

ConditionAllowed range
No video inputInteger within the [2, 30] range
With video inputTotal input video length + output video length is 30 seconds or less
Duration=-1Smart length. The model determines the length automatically from the prompt and input media
json
{
  "OutputConfig": {
    "Duration": -1,
    "Resolution": "1080P",
    "StorageMode": "Temporary"
  }
}

Built with VitePress ยท Deployed on Tencent EdgeOne Pages