NAME
OpenAPI::Client::OpenAI::Path::images-variations - Documentation for the /images/variations path.
OPERATIONS
POST /images/variations
createImageVariation
$client->create_image_variation({
body => { ... },
});
Creates a variation of a given image. This endpoint only supports dall-e-2 .
Responses
200 - OK
Content-Type: application/json
Example:
{
"background" : "transparent",
"created" : 1713833628,
"data" : [
{
"b64_json" : "..."
}
],
"output_format" : "png",
"quality" : "high",
"size" : "1024x1024",
"usage" : {
"input_tokens" : 50,
"input_tokens_details" : {
"image_tokens" : 40,
"text_tokens" : 10
},
"output_tokens" : 50,
"total_tokens" : 100
}
}
SCHEMAS
CreateImageVariationRequest
Properties:
image(string, required) - The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.model(anyOf) - The model to use for image generation. Onlydall-e-2is supported at this time.Default: dall-e-2
n(integer) - The number of images to generate. Must be between 1 and 10.Default: 1
response_format(string) - The format in which the generated images are returned. Must be one ofurlorb64_json. URLs are only valid for 60 minutes after the image has been generated.Allowed values: url, b64_json
Default: url
size(string) - The size of the generated images. Must be one of256x256,512x512, or1024x1024.Allowed values: 256x256, 512x512, 1024x1024
Default: 1024x1024
user(string) - A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more .
Image
Properties:
b64_json(string) - The base64-encoded JSON of the generated image. Returned by default for the GPT image models, and only present ifresponse_formatis set tob64_jsonfordall-e-2anddall-e-3.revised_prompt(string) - Fordall-e-3only, the revised prompt that was used to generate the image.url(string) - When usingdall-e-2ordall-e-3, the URL of the generated image ifresponse_formatis set tourl(default value). Unsupported for the GPT image models.
ImageGenInputUsageDetails
Properties:
image_tokens(integer, required) - The number of image tokens in the input prompt.text_tokens(integer, required) - The number of text tokens in the input prompt.
ImageGenOutputTokensDetails
Properties:
image_tokens(integer, required) - The number of image output tokens generated by the model.text_tokens(integer, required) - The number of text output tokens generated by the model.
ImageGenUsage
Properties:
input_tokens(integer, required) - The number of tokens (images and text) in the input prompt.input_tokens_details(ImageGenInputUsageDetails, required)See "ImageGenInputUsageDetails" below for shape.
output_tokens(integer, required) - The number of output tokens generated by the model.output_tokens_details(ImageGenOutputTokensDetails)See "ImageGenOutputTokensDetails" below for shape.
total_tokens(integer, required) - The total number of tokens (images and text) used for the image generation.
ImagesResponse
Properties:
background(string) - The background parameter used for the image generation. Eithertransparentoropaque.Allowed values: transparent, opaque
created(integer, required) - The Unix timestamp (in seconds) of when the image was created.data(array of Image) - The list of generated images.output_format(string) - The output format of the image generation. Eitherpng,webp, orjpeg.Allowed values: png, webp, jpeg
quality(string) - The quality of the image generated. Eitherlow,medium, orhigh.Allowed values: low, medium, high
size(string) - The size of the image generated. Either1024x1024,1024x1536, or1536x1024.Allowed values: 1024x1024, 1024x1536, 1536x1024
usage(ImageGenUsage)See "ImageGenUsage" below for shape.
SEE ALSO
COPYRIGHT AND LICENSE
Copyright (C) 2023-2026 by Nelson Ferraz
This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.14.0 or, at your option, any later version of Perl 5 you may have available.