wan_generate_video
Create a video from a text prompt with Wan AI. Describe scene, motion, style, and mood to generate video with adjustable resolution, duration, and audio.
Instructions
Generate AI video from a text prompt using Wan text-to-video model.
This uses the wan2.6-t2v model to create video from text descriptions.
For creating video from images, use wan_generate_video_from_image instead.
Returns:
Task ID and generated video information including URLs and state.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | The size of the generated video (e.g., '1280x720'). | |
| audio | No | Whether the generated video should include audio. Default is true. | |
| prompt | Yes | Description of the video to generate. Be descriptive about the scene, motion, style, and mood. | |
| timeout | No | Timeout in seconds for the API to return data. Default is 1800. | |
| duration | No | Video duration in seconds. Options: 5, 10, or 15. Default depends on model. | |
| audio_url | No | URL of reference audio to use in the video. Only used when audio is enabled. | |
| resolution | No | Video resolution. Options: '480P', '720P' (default), '1080P'. | 720P |
| callback_url | No | Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the video is generated. | |
| prompt_extend | No | Enable LLM-based prompt rewriting for better results. Default is true. | |
| negative_prompt | No | Content to exclude from the video. Maximum 500 characters. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |