Skip to content

PixVerse โ€‹

Updated

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

PixVerse is a video generation model that supports text-to-video, first-frame / first-and-last-frame video generation, and multi-image reference generation with up to 7 images (c1 also accepts a reference video). It can generate audio at the same time and supports lip sync, with output from 360P to 1080P and durations of 1โ€“15 seconds.

Basic information โ€‹

ItemValue
ModelNamePixVerse
ModelVersionv6 / v5.6 / c1 (lowercase)
DefaultModelVersion=v6 / Resolution=1080P
Disable guardrails supportNot supported

Supported specs by version โ€‹

VersionResolutionRatioLength
Common480P / 720P / 1080P / 2K / 4Kโ€”โ€”
c1360P / 540P / 720P / 1080Pโ€”1โ€“15 seconds
v6360P / 540P / 720P / 1080Pโ€”1โ€“15 seconds
v5.6360P / 540P / 720P / 1080Pโ€”5 / 8 / 10 seconds; 1080P excludes 10 seconds

Input conditions โ€‹

VersionCondition
c1Reference / audio: up to 7 images, video reference, simultaneous audio generation
v6Reference / audio: up to 7 images, simultaneous audio generation
v5.6Reference / audio: distinct from the reference / audio features of c1/v6

Request parameters โ€‹

ParameterRequiredTypeDescription
ModelNameRequiredStringFixed value PixVerse
ModelVersionOptionalStringv6 / v5.6 / c1 (lowercase)
PromptRequiredStringGeneration prompt
FileInfos.NOptionalArrayReference input. Usage is FirstFrame (first frame) or Reference (reference)
OutputConfig.ResolutionOptionalString480P / 720P / 1080P / 2K / 4K
OutputConfig.DurationOptionalIntegerVideo length (seconds)
OutputConfig.AspectRatioOptionalString16:9 / 9:16 / 1:1, etc.

Request example โ€‹

json
{
  "SubAppId": 123456789,
  "ModelName": "PixVerse",
  "ModelVersion": "v6",
  "Prompt": "a calm sunset over the ocean, cinematic",
  "OutputConfig": {
    "Resolution": "1080P",
    "Duration": 5,
    "AspectRatio": "16:9",
    "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€‹

Lip Sync โ€‹

Applies lip sync to a source video in which a person speaks. Specify it with SceneType=lip_sync, and specify the voice in one of two modes.

TTS mode: specify the lines and the speaker โ€‹

json
{
  "SubAppId": 123456789,
  "ModelName": "PixVerse",
  "ModelVersion": "lip_sync",
  "SceneType": "lip_sync",
  "Prompt": "talking",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Video",
      "Url": "https://<cdn>/talking_head.mp4"
    }
  ],
  "ExtInfo": "{\"AdditionalParameters\":\"{\\\"lip_sync_tts_content\\\":\\\"Hello, nice to meet you.\\\",\\\"lip_sync_tts_speaker_id\\\":\\\"14\\\"}\"}",
  "OutputConfig": {
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

Reference audio mode: provide an audio file โ€‹

json
{
  "SubAppId": 123456789,
  "ModelName": "PixVerse",
  "ModelVersion": "lip_sync",
  "SceneType": "lip_sync",
  "Prompt": "talking",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Video",
      "Url": "https://<cdn>/talking_head.mp4"
    },
    {
      "Type": "Url",
      "Category": "Audio",
      "Url": "https://<cdn>/voice.mp3"
    }
  ],
  "OutputConfig": {
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

Use a public URL for the source video

The source video URL must be a public URL accessible from outside. Preset speakers are mostly based on Chinese speakers, so for Korean lines the reference audio mode is recommended.

Version selection โ€‹

ModelVersionCharacteristics
c1Latest version. Best character consistency; supports reference video input and lip sync
v6General-purpose high-quality version
v5.6Previous-generation stable version. Video length is one of 5 / 8 / 10 seconds

c1 and v6 are 1~15 seconds, and v5.6 supports only 5 / 8 / 10 seconds.

Specifying the first and last frames โ€‹

Distinguish the first and last frames with FileInfos.N.Usage. The approach using LastFrame is recommended.

json
{
  "SubAppId": 123456789,
  "ModelName": "PixVerse",
  "ModelVersion": "v6",
  "Prompt": "Smooth transition",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/first.jpg",
      "Usage": "FirstFrame"
    },
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/last.jpg",
      "Usage": "LastFrame"
    }
  ],
  "OutputConfig": {
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}
UsageMeaning
FirstFrameFirst frame
LastFrameLast frame
ReferenceReference image

There are two ways to set the last frame

The approach using FileInfos.Usage=LastFrame is the baseline. The top-level LastFrameUrl also works for backward compatibility, but use Usage=LastFrame in new implementations. The last frame URL must be 5MB or less.

Multi-image reference (Text / @Name) โ€‹

Name each reference image with Text and point to it with @Name in the prompt. Images are limited to 7.

json
{
  "SubAppId": 123456789,
  "ModelName": "PixVerse",
  "ModelVersion": "c1",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/character.png",
      "Text": "hero",
      "Usage": "Reference"
    },
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/fan.jpg",
      "Text": "fan",
      "Usage": "Reference"
    },
    {
      "Type": "Url",
      "Category": "Image",
      "Url": "https://<cos>/earring.jpg",
      "Text": "earring",
      "Usage": "Reference"
    }
  ],
  "Prompt": "the woman in @hero slowly raises her hand and opens the @fan, while the @earring sways gently as she turns her head",
  "OutputConfig": {
    "Duration": 8,
    "AspectRatio": "3:4",
    "AudioGeneration": "Enabled",
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

Always leave a space after @Name

Use it with a space after the reference target name, as in @hero runs. Match the name in the prompt with the Text value, and write names in English letters / digits.

Reference type (ReferenceType) โ€‹

On items that are Category=Video, specify ReferenceType to set the nature of the reference. Applies to GV, Kling, and PixVerse.

ValueMeaning
subjectSubject-centered reference
backgroundBackground-centered reference
json
{
  "SubAppId": 123456789,
  "ModelName": "PixVerse",
  "ModelVersion": "v5.6",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Video",
      "Url": "https://<cos>/source.mp4",
      "ReferenceType": "subject"
    }
  ],
  "Prompt": "change the color of the main character's dress to white",
  "OutputConfig": {
    "StorageMode": "Permanent",
    "MediaName": "PixVerse-video-edit"
  },
  "SessionContext": "job-001"
}

Lip sync (lip_sync) โ€‹

Specify ModelVersion=lip_sync and SceneType=lip_sync together. Specify the voice with an audio file or TTS.

Preset speaker list โ€‹

Specify one of the values below in ExtInfo's lip_sync_tts_speaker_id. The latest list can be checked with the PixVerse TTS voice lookup API.

speaker_idDescription
AutoAuto select
2Zhen Youyu
4Foreign male
6Li Jie
10Jiang Jianghao
11Lao Sen
12Li Jieke
13Qian Duoduo
14Wang Xiaopai
16Country loud voice
18Henan dialect
19Taiwanese accent
20Shaanxi dialect
21Hong Kong accent
json
{
  "SubAppId": 123456789,
  "ModelName": "PixVerse",
  "ModelVersion": "lip_sync",
  "SceneType": "lip_sync",
  "FileInfos": [
    {
      "Type": "Url",
      "Category": "Video",
      "Url": "https://<cos>/talking_head.mp4"
    }
  ],
  "Prompt": "dancing",
  "ExtInfo": "{\"AdditionalParameters\": \"{\\\"lip_sync_tts_content\\\": \\\"lets dance and sing with me\\\", \\\"lip_sync_tts_speaker_id\\\": \\\"2\\\"}\"}",
  "OutputConfig": {
    "StorageMode": "Temporary"
  },
  "SessionContext": "job-001"
}

ExtInfo.AdditionalParameters fields:

FieldDescription
lip_sync_tts_contentLines to match to the mouth shapes
lip_sync_tts_speaker_idPreset speaker ID

Input specification โ€‹

ItemConstraint
Image size10MB or less
Image formatjpeg / jpg / png
Last frame URL5MB or less
Reference imagesUp to 7

Other parameters โ€‹

ParameterDescription
NegativePromptPrompt describing elements to exclude from the result
EnhancePromptAutomatic prompt correction. Enabled / Disabled
SeedRandom seed. The same value reproduces the result
SessionContextValue passed through to the callback unchanged. Up to 1000 characters
SessionIdDeduplication identifier. Requests with the same ID within 3 days are handled based on the existing request

Built with VitePress ยท Deployed on Tencent EdgeOne Pages