ImageGenTool Class

Image generation tool.

Constructor

ImageGenTool(*args: Any, **kwargs: Any)

Variables

Name Description
type
str or <xref:azure.ai.projects.models.IMAGE_GENERATION>

The type of the image generation tool. Always image_generation. Required. IMAGE_GENERATION.
model
str or str or str or str

Is one of the following types: Literal["gpt-image-1"], Literal["gpt-image-1-mini"], Literal["gpt-image-1.5"], str
quality
str or str or str or str

The quality of the generated image. One of low, medium, high, or auto. Default: auto. Is one of the following types: Literal["low"], Literal["medium"], Literal["high"], Literal["auto"]
size
str or str or str or str or str

The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792. Is one of the following types: Literal["1024x1024"], Literal["1024x1536"], Literal["1536x1024"], Literal["auto"], str
output_format
str or str or str

The output format of the generated image. One of png, webp, or jpeg. Default: png. Is one of the following types: Literal["png"], Literal["webp"], Literal["jpeg"]
output_compression
int

Compression level for the output image. Default: 100.
moderation
str or str

Moderation level for the generated image. Default: auto. Is either a Literal["auto"] type or a Literal["low"] type.
background
str or str or str

Background type for the generated image. One of transparent, opaque, or auto. Default: auto. Is one of the following types: Literal["transparent"], Literal["opaque"], Literal["auto"]
input_fidelity
str or InputFidelity

Known values are: "high" and "low".
input_image_mask
ImageGenToolInputImageMask

Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).
partial_images
int

Number of partial images to generate in streaming mode, from 0 (default value) to 3.
action
str or ImageGenAction

Whether to generate a new image or edit an existing image. Default: auto. Known values are: "generate", "edit", and "auto".
name
str

Deprecated. This property is deprecated and will be removed in a future version.
description
str

Deprecated. This property is deprecated and will be removed in a future version.
tool_configs
dict[str, ToolConfig]

Deprecated. This property is deprecated and will be removed in a future version.

Methods

as_dict

Return a dict that can be turned into json using json.dump.
clear

Remove all items from D.
copy
get

Get the value for key if key is in the dictionary, else default. :param str key: The key to look up. :param any default: The value to return if key is not in the dictionary. Defaults to None :returns: D[k] if k in D, else d. :rtype: any
items
keys
pop

Removes specified key and return the corresponding value. :param str key: The key to pop. :param any default: The value to return if key is not in the dictionary :returns: The value corresponding to the key. :rtype: any :raises KeyError: If key is not found and default is not given.
popitem

Removes and returns some (key, value) pair :returns: The (key, value) pair. :rtype: tuple :raises KeyError: if D is empty.
setdefault

Same as calling D.get(k, d), and setting D[k]=d if k not found :param str key: The key to look up. :param any default: The value to set if key is not in the dictionary :returns: D[k] if k in D, else d. :rtype: any
update

Updates D from mapping/iterable E and F. :param any args: Either a mapping object or an iterable of key-value pairs.
values

as_dict

Return a dict that can be turned into json using json.dump.

as_dict(*, exclude_readonly: bool = False) -> dict[str, Any]

Keyword-Only Parameters

Name Description
exclude_readonly
bool

Whether to remove the readonly properties.

Default value: False

Returns

Type Description
dict

A dict JSON compatible object

clear

Remove all items from D.

clear() -> None

copy 

copy() -> Model

get

Get the value for key if key is in the dictionary, else default. :param str key: The key to look up. :param any default: The value to return if key is not in the dictionary. Defaults to None :returns: D[k] if k in D, else d. :rtype: any

get(key: str, default: Any = None) -> Any

Parameters

Name Description
key
Required
default
Default value: None

items 

items() -> ItemsView[str, Any]

Returns

Type Description
ItemsView

set-like object providing a view on D's items

keys 

keys() -> KeysView[str]

Returns

Type Description
KeysView

a set-like object providing a view on D's keys

pop

Removes specified key and return the corresponding value. :param str key: The key to pop. :param any default: The value to return if key is not in the dictionary :returns: The value corresponding to the key. :rtype: any :raises KeyError: If key is not found and default is not given.

pop(key: str, default: ~typing.Any = <object object>) -> Any

Parameters

Name Description
key
Required
default

popitem

Removes and returns some (key, value) pair :returns: The (key, value) pair. :rtype: tuple :raises KeyError: if D is empty.

popitem() -> tuple[str, Any]

setdefault

Same as calling D.get(k, d), and setting D[k]=d if k not found :param str key: The key to look up. :param any default: The value to set if key is not in the dictionary :returns: D[k] if k in D, else d. :rtype: any

setdefault(key: str, default: ~typing.Any = <object object>) -> Any

Parameters

Name Description
key
Required
default

update

Updates D from mapping/iterable E and F. :param any args: Either a mapping object or an iterable of key-value pairs.

update(*args: Any, **kwargs: Any) -> None

values 

values() -> ValuesView[Any]

Returns

Type Description
ValuesView

an object providing a view on D's values

Attributes

action

auto. Known values are: "generate", "edit", and "auto".

action: str | _models.ImageGenAction | None

background

Background type for the generated image. One of transparent, opaque, or auto. Default: auto. Is one of the following types: Literal["transparent"], Literal["opaque"], Literal["auto"]

background: Literal['transparent', 'opaque', 'auto'] | None

description

Deprecated. This property is deprecated and will be removed in a future version.

description: str | None

input_fidelity

"high" and "low".

input_fidelity: str | _models.InputFidelity | None

input_image_mask

Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).

input_image_mask: _models.ImageGenToolInputImageMask | None

model

Literal["gpt-image-1"], Literal["gpt-image-1-mini"], Literal["gpt-image-1.5"], str

model: Literal['gpt-image-1'] | Literal['gpt-image-1-mini'] | Literal['gpt-image-1.5'] | str | None

moderation

auto. Is either a Literal["auto"] type or a Literal["low"] type.

moderation: Literal['auto', 'low'] | None

name

Deprecated. This property is deprecated and will be removed in a future version.

name: str | None

output_compression 

output_compression: int | None

output_format

The output format of the generated image. One of png, webp, or jpeg. Default: png. Is one of the following types: Literal["png"], Literal["webp"], Literal["jpeg"]

output_format: Literal['png', 'webp', 'jpeg'] | None

partial_images

Number of partial images to generate in streaming mode, from 0 (default value) to 3.

partial_images: int | None

quality

The quality of the generated image. One of low, medium, high, or auto. Default: auto. Is one of the following types: Literal["low"], Literal["medium"], Literal["high"], Literal["auto"]

quality: Literal['low', 'medium', 'high', 'auto'] | None

size

The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792. Is one of the following types: Literal["1024x1024"], Literal["1024x1536"], Literal["1536x1024"], Literal["auto"], str

size: Literal['1024x1024'] | Literal['1024x1536'] | Literal['1536x1024'] | Literal['auto'] | str | None

tool_configs

Deprecated. This property is deprecated and will be removed in a future version.

tool_configs: dict[str, '_models.ToolConfig'] | None

type

The type of the image generation tool. Always image_generation. Required. IMAGE_GENERATION.

type: IMAGE_GENERATION: 'image_generation'>]