xinference.client.handlers.VideoModelHandle.text_to_video

VideoModelHandle.text_to_video(prompt: str, n: int = 1, **kwargs) → VideoList

Creates a video by the input text.

Parameters:

• prompt (str or List[str]) – The prompt or prompts to guide video generation. If not defined, you need to pass prompt_embeds.

• n (int, defaults to 1) – The number of videos to generate per prompt. Must be between 1 and 10.

Returns:

A list of video objects.

Return type:

VideoList