Overview

This node performs text-to-video generation based on user-provided prompts and settings. It is useful for creating short videos from descriptive text, such as generating a 3D animation of a boy skateboarding in a park. Users can specify the video model, aspect ratio, duration, and whether to wait for the video to be returned before continuing the workflow.

Use Case Examples

1. Generating a 5-second 3D animation video from a text prompt describing a scene.
2. Creating videos with different aspect ratios like 16:9 or 9:16 for social media content.
3. Choosing between different video generation models for quality or speed preferences.

Properties

Name	Meaning
提示词	The text prompt describing the video content to be generated, e.g., 'A 3D boy skateboarding in the park.'
模型	The video generation model to use, such as video-S2.0, video-S3.0, or their Pro versions, affecting video quality and features.
视频比例	The aspect ratio of the generated video, such as 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16.
视频时长	Duration of the generated video in milliseconds. Note that video-S2.0 and video-S2.0-Pro models only support 5-second videos.
是否等待视频返回	Boolean flag indicating whether the node should wait for the video generation to complete and return the video before continuing the workflow.

Output

JSON

• videoUrl - URL of the generated video file.
• videoId - Identifier of the generated video.
• status - Status of the video generation process.

Dependencies

• An API key credential for the video generation service is required.

Troubleshooting

• If the node throws an error about an unimplemented method, it means the selected resource-operation combination is not supported or incorrectly configured.
• Errors related to video duration may occur if an unsupported duration is selected for the chosen model (e.g., video-S2.0 only supports 5 seconds).
• Network or API errors may cause failures; ensure the API key credential is valid and the service is reachable.