Create video

The model to be used for the video creation request.

Text prompt that describes the video to generate.

Video resolution.

Aspect ratio of the video.

Clip duration in seconds.

Frames per second. Defaults to 24.

The number of denoising steps the model performs during video generation. More steps typically result in higher quality output but require longer processing time.

Seed to use in initializing the video generation. Using the same seed allows deterministic video generation. If not provided a random seed is generated for each request.

Controls how closely the video generation follows your prompt. Higher values make the model adhere more strictly to your text description, while lower values allow more creative freedom. guidence_scale affects both visual content and temporal consistency.Recommended range is 6.0-10.0 for most video models. Values above 12 may cause over-guidance artifacts or unnatural motion patterns.

Compression quality. Defaults to 20.

Similar to prompt, but specifies what to avoid instead of what to include

Whether to generate audio for the video.

Unique identifier for the video job.

The object type, which is always video.

The video generation model that produced the job.

Current lifecycle status of the video job.

Unix timestamp (seconds) for when the job was created.

Unix timestamp (seconds) for when the job completed, if finished.

The resolution of the generated video.

Duration of the generated clip in seconds.