CreateAigcVideoTask

Model name.
Supported models:
Hunyuan.
Hailuo.
Kling.
Vidu.
PixVerse.
Mingmou.
H2.

Specific version number of the model. By default, the system uses the supported stable version of the model.

1. Hunyuan: [1.5].
2. Hailuo: [02, 2.3, and 2.3-fast].
3. Kling: [1.6, 2.0, 2.1, 2.5, O1, 2.6, 3.0, and 3.0-Omni].
4. Vidu: [q2, q2-pro, q2-turbo, q3-pro, q3-turbo, q3, and q3-mix].
5. PixVerse: [v5.6, v6, and c1].
6. H2: [1.0].

Scenario for the generated video.
Note: Not all models support scenarios.

1. Kling supports: motion control (motion_control), digital human (avatar_i2v), and lip sync (lip_sync).
2. Mingmou supports: landscape-to-portrait conversion (land2port).
3. Vidu supports: effect templates (template_effect).
4. Hunyuan supports: 3D world model (3d_scene). The returned file is not a video.

Description of the generated video. This parameter is required when no image is specified.

Specifies the content you want to prevent the model from generating.
Note: Not all models support this.
For example:
Top lighting and bright colors.
People and animals.
Multiple vehicles and wind.

The default value is False, meaning the model follows instructions strictly.
For better results with more nuanced prompts, set this parameter to True to automatically optimize the input prompt and improve generation quality.

Image URL used for video generation. The URL must be accessible from the public network.
Note:

1. The recommended image size is no more than 10 MB. Different models have different size limits. See the model website for a more complete description.
2. Supported image formats: JPEG and PNG.

The model will generate a video using the image of this parameter as the ending frame.
Models that support this parameter:

1. Kling 2.0, O1, 3.0, and 3.0-Omni support starting and ending frames.
2. Kling 1.6, 2.1, 2.5, and 2.6 support starting and ending frames with Resolution:1080p.
3. Vidu q2-pro, q2-turbo, q3-pro, and q3-turbo support starting and ending frames.
4. PixVerse v5.6, v6, and c1 support starting and ending frames.
5. Hailuo 02 supports starting and ending frames.

Note:

1. The recommended image size is no more than 10 MB. Different models have different limits.
2. Supported image formats: JPEG and PNG.

List of multiple asset resource images used to describe the resource images used by the model for video generation.

Models that support multiple images:

1. Vidu q2, q2-pro, q3-turbo, q3, and q3-mix support video generation with multiple reference images. One to 7 images can be uploaded. The ReferenceType in ImageInfos can be used to specify the subject ID for the input.
2. Kling O1, 3.0-Omni, and 1.6 support video generation with multiple reference images.
   1. Kling 1.6 allows uploading 1 to 4 images.
   2. Kling O1 and 3.0-Omni allow uploading 1 to 7 images. If a reference video is present, 0 to 4 images can be uploaded.
3. PixVerse, v5.6, v6, and c1 support video generation with multiple reference images. One to 7 images can be uploaded, and image names need to be specified via the Text field in ImageInfos.
4. H2 1.0 supports video generation with multiple image parameters. One to 9 images can be uploaded. If a reference video is present, 0 to 5 images can be uploaded.

Note:

1. The image size cannot exceed 10 MB.
2. Supported image formats: JPEG and PNG.

Only Kling O1, Kling 3.0-Omni, Vidu q2-pro, and H2 1.0 support reference video information.

1. For Kling O1 and 3.0-Omni, the reference video can be used as a feature reference video or a video for editing. The default type is video for editing. You can choose to keep the original sound of the video.
2. Vidu q2-pro supports video reference.
3. H2 1.0 supports video reference.

Duration of the generated video.
Note:

1. Kling: default value: 5 seconds.
   • O1 supports 3 to 10 seconds.
   • 3.0-Omni supports 3 to 15 seconds, or 3 to 10 seconds when a video reference is used.
   • 3.0 supports 3 to 15 seconds.
   • Other versions support 5 and 10 seconds.
2. The std mode of Hailuo supports 6 and 10 seconds, and other modes support 6 seconds. Default value: 6 seconds.
3. Vidu: default value: 5 seconds.
   • q3-pro, q3-turbo, q3, and q3-mix support 3 to 16 seconds.
   • q2-pro, q2-turbo, and q2 support 1 to 10 seconds.
4. PixVerse: default value: 5 seconds.
   • v5.6 supports 5, 8, and 10 seconds.
   • v6 and c1 support 1 to 15 seconds.
5. H2 supports 3 to 15 seconds. Default value: 5 seconds.

Additional parameters required.

COS bucket information for the file result. Note: COS is required and the MPS_QcsRole role needs to be created and authorized.

Special scenario parameters or storyboard prompts required by the model, formatted as a JSON serialized string.
Example:
{"camera_control":{"type":"simple"}}.

API operator name.

Returned task ID after the task is created successfully.
The task progress and generation results can be obtained by calling the query API.