For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python class

VideoProviderOptions

VideoProviderOptions

class max.pipelines.request.provider_options.VideoProviderOptions(*, negative_prompt=None, guidance_scale=3.5, true_cfg_scale=1.0, width=None, height=None, steps=None, cfg_normalization=False, cfg_truncation=1.0, flow_shift=None, response_format=GeneratedMediaResponseFormat.url, frames_per_second=None, num_frames=None, guidance_scale_2=None)

source

Bases: PixelProviderOptionsBase

Options specific to video generation pipelines.

Inherits all generation options shared with other pixel modalities from PixelProviderOptionsBase; adds video-specific fields (frames_per_second, num_frames, guidance_scale_2) and overrides the default response format.

Parameters:

• negative_prompt (str | None)
• guidance_scale (Annotated[float, Ge(ge=0)])
• true_cfg_scale (Annotated[float, Gt(gt=0)])
• width (Annotated[int | None, Gt(gt=0)])
• height (Annotated[int | None, Gt(gt=0)])
• steps (Annotated[int | None, Gt(gt=0)])
• cfg_normalization (bool)
• cfg_truncation (Annotated[float, Gt(gt=0)])
• flow_shift (Annotated[float | None, Gt(gt=0.0)])
• response_format (GeneratedMediaResponseFormat)
• frames_per_second (Annotated[int | None, Gt(gt=0)])
• num_frames (Annotated[int | None, Gt(gt=0)])
• guidance_scale_2 (Annotated[float | None, Gt(gt=0.0)])

frames_per_second

frames_per_second: int | None

source

guidance_scale_2

guidance_scale_2: float | None

source

model_config

model_config: ClassVar[ConfigDict] = {'extra': 'forbid', 'frozen': True}

source

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

num_frames

num_frames: int | None

source

response_format

response_format: GeneratedMediaResponseFormat

source