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

Python class

ImageProviderOptions

`ImageProviderOptions`

class max.pipelines.request.provider_options.ImageProviderOptions(*, 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.b64_json, secondary_prompt=None, secondary_negative_prompt=None, num_images=1, strength=0.6, output_format='jpeg')

source

Bases: PixelProviderOptionsBase

Options specific to image generation pipelines.

Inherits all generation options shared with other pixel modalities from PixelProviderOptionsBase; adds image-specific fields (secondary text-encoder prompts, num_images, strength, output_format) and tightens the dimension constraints to image-specific limits.

Parameters:

negative_prompt (str | None)
guidance_scale (float)
true_cfg_scale (float)
width (int | None)
height (int | None)
steps (int | None)
cfg_normalization (bool)
cfg_truncation (float)
flow_shift (float | None)
response_format (GeneratedMediaResponseFormat)
secondary_prompt (str | None)
secondary_negative_prompt (str | None)
num_images (int)
strength (float)
output_format (str)

`height`

height: int | 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_images`

num_images: int

source

`output_format`

output_format: str

source

`secondary_negative_prompt`

secondary_negative_prompt: str | None

source

`secondary_prompt`

secondary_prompt: str | None

source

`strength`

strength: float

source

`width`

width: int | None

source

ImageProviderOptions​

height​

model_config​

num_images​

output_format​

secondary_negative_prompt​

secondary_prompt​

strength​

width​