Skip to content
Lucero

Creates a variation of a given image.

POST
/images/variations

Authorizations

Section titled “Authorizations ”

Request Body required

Section titled “Request Body required ”
object
image
required

The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.

string format: binary
model
Any of:
string
n

The number of images to generate. Must be between 1 and 10. For dall-e-3, only n=1 is supported.

integer
default: 1 nullable >= 1 <= 10 
1
response_format

The format in which the generated images are returned. Must be one of url or b64_json. URLs are only valid for 60 minutes after the image has been generated.

string
default: url nullable
Allowed values: url b64_json 
url
size

The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.

string
default: 1024x1024 nullable
Allowed values: 256x256 512x512 1024x1024 
1024x1024
user

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

string
user-1234

Responses

Section titled “ Responses ”

200

Section titled “200 ”

OK

object
created
required
integer
data
required
Array<object>

Represents the url or the content of an image generated by the OpenAI API.

object
b64_json

The base64-encoded JSON of the generated image, if response_format is b64_json.

string
url

The URL of the generated image, if response_format is url (default).

string
revised_prompt

The prompt that was used to generate the image, if there was any revision to the prompt.

string