generate_video_v2
Create high-quality videos from text prompts using the SeeDance V2 model. Supports 5-15 second videos up to 1440p resolution with aspect ratio options for vertical or horizontal formats.
Instructions
Generate a video using TensorsLab SeeDance V2 model (highest quality, supports 5-15 seconds, up to 1440p)
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Text description of the desired video | |
| ratio | No | Aspect ratio: 9:16 (vertical/TikTok) or 16:9 (horizontal/YouTube), default: 9:16 | |
| duration | No | Video duration in seconds (5-15, default: 5) | |
| resolution | No | Video resolution (default: 1080p) | |
| fps | No | Frame rate (default: 24) | |
| imageUrl | No | URL of source image for image-to-video generation (1-2 images supported) | |
| generateAudio | No | Generate audio for the video (default: false) | |
| returnLastFrame | No | Return the last frame as an image (default: false) | |
| seed | No | Random seed for reproducibility |