Veo โ
Endpoint: POST https://vod.intl.tencentcloudapi.comAction: CreateAigcVideoTask
Veo is a video generation model that supports text-to-video and image-to-video. omni supports multimodal reference generation from images and video, video editing, and state-preserving editing, with natively synchronized audio.
Basic Information โ
| Item | Value |
|---|---|
| ModelName | GV |
| ModelVersion | 3.1 / 3.1-fast / omni |
| Default value | ModelVersion=3.1 / Resolution=1080P |
| Guardrail disable support | Not supported |
Specifications Supported by Version โ
| Version | Resolution | Aspect ratio | Length |
|---|---|---|---|
| Common | 480P / 720P / 1080P / 2K / 4K | โ | โ |
Request Parameters โ
| Parameter | Required | Type | Description |
|---|---|---|---|
ModelName | Required | String | Fixed value GV |
ModelVersion | Optional | String | 3.1 / 3.1-fast / omni |
Prompt | Required | String | Generation prompt |
FileInfos.N | Optional | Array | Reference input. Usage is FirstFrame (first frame) or Reference (reference) |
OutputConfig.Resolution | Optional | String | 480P / 720P / 1080P / 2K / 4K |
OutputConfig.Duration | Optional | Integer | Video length (seconds) |
OutputConfig.AspectRatio | Optional | String | 16:9 / 9:16 / 1:1, etc. |
Request Example โ
{
"SubAppId": 123456789,
"ModelName": "GV",
"ModelVersion": "3.1",
"Prompt": "a calm sunset over the ocean, cinematic",
"OutputConfig": {
"Resolution": "1080P",
"Duration": 5,
"AspectRatio": "16:9",
"StorageMode": "Temporary"
},
"SessionContext": "job-001"
}Response Example โ
{
"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
}
}
]
}
}
}Omni Input Specifications โ
Omni references up to 10 images and up to 3 videos / 10 seconds each. The aspect ratio is 16:9 / 9:16, the length is 3โ10 seconds, and the frame rate is 24fps. The original resolution is 720P, and 1080P / 2K / 4K are upscaled outputs.
Special Settings โ
omni Version Specifications โ
omni is the version in the GV family that supports native audio generation and state-preserving editing.
| Item | Value |
|---|---|
| Generation mode | Text to video, image reference, video reference, video editing, state-preserving editing |
| Reference image | Up to 10 |
| Reference video | Up to 3 / 10 seconds each |
| Prompt length | Up to 20,000 characters |
| Audio | The model generates audio together with the video. |
| Aspect ratio | 16:9 / 9:16 |
| Resolution | 720P / 1080P / 2K / 4K |
| Video length | 3~10 seconds |
| Frame rate | 24 fps |
Prompt Image Markers โ
omni is a marker inside the prompt that specifies the role of an image. Image reference numbers start from 0.
| Marker | Role |
|---|---|
<FIRST_FRAME> | Use this image as the starting frame of the video |
<IMAGE_REF_N> | Use the Nth image as a style or subject reference |
<FIRST_FRAME> a woman is walking
in the style of <IMAGE_REF_0> a woman <IMAGE_REF_1> is walkingThe second example uses the first image as a style reference and the second image as a subject reference.
State-Preserving Editing (PreviousTaskId) โ
With PreviousTaskId, it inherits the context of the previous result and edits it repeatedly with prompts. It reflects only the specified changes and keeps the remaining elements.
Create the first task.
{
"SubAppId": 123456789,
"ModelName": "GV",
"ModelVersion": "omni",
"FileInfos": [
{
"Type": "Url",
"Url": "https://<cos>/f0.jpg"
}
],
"Prompt": "Two man are studying",
"EnhancePrompt": "Enabled",
"OutputConfig": {
"StorageMode": "Temporary"
},
"SessionContext": "job-001"
}Pass the returned TaskId into ExtInfo as its PreviousTaskId to continue editing.
{
"SubAppId": 123456789,
"ModelName": "GV",
"ModelVersion": "omni",
"Prompt": "Make the background invisible",
"EnhancePrompt": "Enabled",
"ExtInfo": "{\"AdditionalParameters\": \"{\\\"PreviousTaskId\\\": \\\"<previous-task-id>\\\"}\"}",
"OutputConfig": {
"StorageMode": "Temporary"
},
"SessionContext": "job-001"
}State-Preserving Editing Works Only for Tasks Within 24 hours
PreviousTaskId specifies a task created within 24 hours after generation.
Other Prompt Uses โ
| Purpose | How to write the prompt |
|---|---|
| Single scene | The default is multi-shot. If you want a single scene, state it in the prompt |
| Removing elements | Specify directly the elements you want removed |
| Audio instructions | Write the sounds or dialogue you want together in the prompt |
| Time-specific events | Describe the actions at specific points in order |
| Text in video | You can specify characters to place inside the video |
| Meta prompt | You can instruct video quality or composition principles |