Implementation:Openai Openai python Image Generate Params

Knowledge Sources	openai-python OpenAI Image API
Domains	Computer_Vision, Image_Generation
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete TypedDict parameter types for configuring image generation and editing requests provided by the OpenAI Python SDK.

Description

ImageGenerateParams and ImageEditParams are TypedDicts defining all valid parameters for image generation and editing API calls. They specify the prompt, model, size, quality, format, and advanced options like streaming partial images and transparent backgrounds.

Usage

Parameters are typically passed directly to images.generate() or images.edit() as keyword arguments. The TypedDicts provide type checking and IDE support.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/image_generate_params.py
• Lines: L1-145
• File: src/openai/types/image_edit_params.py
• Lines: L1-143

Signature

class ImageGenerateParams(TypedDict, total=False):
    prompt: Required[str]
    model: Union[str, ImageModel, None]
    n: Optional[int]
    quality: Literal["standard", "hd", "low", "medium", "high", "auto"]
    response_format: Optional[Literal["url", "b64_json"]]
    size: Optional[Literal["auto", "1024x1024", "1536x1024", "1024x1536", "256x256", "512x512", "1792x1024", "1024x1792"]]
    style: Optional[Literal["vivid", "natural"]]
    user: str
    background: Optional[Literal["transparent", "opaque", "auto"]]
    output_format: Optional[Literal["png", "jpeg", "webp"]]
    output_compression: Optional[int]
    partial_images: Optional[int]
    moderation: Optional[Literal["low", "auto"]]

class ImageEditParams(TypedDict, total=False):
    image: Required[Union[FileTypes, List[FileTypes]]]
    prompt: Required[str]
    mask: FileTypes
    model: Union[str, ImageModel, None]
    n: Optional[int]
    quality: Optional[Literal["standard", "low", "medium", "high", "auto"]]
    size: Optional[Literal["auto", "1024x1024", "1536x1024", "1024x1536", "256x256", "512x512"]]
    background: Optional[Literal["transparent", "opaque", "auto"]]
    input_fidelity: Optional[Literal["high", "low"]]

Import

from openai.types import ImageGenerateParams, ImageEditParams

I/O Contract

Inputs

Name	Type	Required	Description
prompt	str	Yes	Image description
model	str	No	dall-e-2, dall-e-3, or gpt-image-1
size	str	No	Image dimensions
quality	str	No	Quality level
response_format	str	No	url or b64_json
output_format	str	No	png, jpeg, webp
background	str	No	transparent, opaque, auto
partial_images	int	No	Number of streaming partial previews

Outputs

Name	Type	Description
params	TypedDict	Configuration dict passed to generate/edit

Usage Examples

Generation Parameters

from openai import OpenAI

client = OpenAI()
response = client.images.generate(
    prompt="A sunset over mountains",
    model="gpt-image-1",
    size="1024x1024",
    quality="high",
    output_format="png",
    background="opaque",
)

Edit Parameters

response = client.images.edit(
    image=open("photo.png", "rb"),
    prompt="Add a rainbow in the sky",
    model="gpt-image-1",
    size="1024x1024",
    quality="high",
)

Related Pages

Implements Principle

• Principle:Openai_Openai_python_Image_Generation_Parameters