Start Now
ByteDance's flagship text-to-video model with multi-shot narrative, superior semantic understanding, and cinematic 1080P output in diverse styles.
Input
Description of the desired output.
Whether to keep the camera fixed during generation.
Duration of the generated video in seconds.
5
Task expiration time in seconds.
Total number of frames to generate.
Aspect ratio of the generated video.
16:9
Output resolution of the video.
1080p
Whether to return the last frame of the generated video.
Random seed for reproducible generation. Use -1 for random.
Service tier for generation (e.g., default or flex).
default
Result
No results yet
Run the model to preview the output here.
