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

ImageGenerationDetails

ImageGenerationDetails

class max.pipelines.request.ImageGenerationDetails(*, width, height, megapixels, steps, image_count)

source

Bases: BaseModel

Image generation usage metadata.

Exposes the generated image dimensions, step count, and image count under usage so downstream consumers can attribute usage from the response instead of re-deriving it from request inputs.

Parameters:

• width (int)
• height (int)
• megapixels (float)
• steps (int)
• image_count (int)

from_images()

classmethod from_images(pixel_data, *, steps)

source

Build image generation details from generated image data.

Parameters:

• pixel_data (ndarray[tuple[Any, ...], dtype[uint8]]) – Generated images as a non-empty uint8 array of shape (image_count, H, W, C).
• steps (int) – The number of denoising steps used to generate.

Returns:

An ImageGenerationDetails describing the generated images.

Raises:

ValueError – If pixel_data contains no images.

Return type:

ImageGenerationDetails

height

height: int

source

image_count

image_count: int

source

megapixels

megapixels: float

source

model_config

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

source

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

steps

steps: int

source

width

width: int

source