Create image edit

POST /images/edits

Creates an edited or extended image given an original image and a prompt.

multipart/form-data

Body Required

  • image string(binary) Required

    The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.

  • prompt string Required

    A text description of the desired image(s). The maximum length is 1000 characters.

  • mask string(binary)

    An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as image.

  • model string | null

    Any of:
    string-1 string | null string-2 string | null

    The model to use for image generation. Only dall-e-2 is supported at this time.

    Default value is dall-e-2.

    The model to use for image generation. Only dall-e-2 is supported at this time.

    Value is dall-e-2. Default value is dall-e-2.

  • n integer | null

    The number of images to generate. Must be between 1 and 10.

    Minimum value is 1, maximum value is 10. Default value is 1.

  • size string | null

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

    Values are 256x256, 512x512, or 1024x1024. Default value is 1024x1024.

  • response_format string | null

    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.

    Values are url or b64_json. Default value is url.

  • user string

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

Responses

  • 200 application/json

    OK

    Hide response attributes Show response attributes object
    • created integer Required
    • data array[object] Required

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

      Hide data attributes Show data attributes object
      • b64_json string

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

      • url string

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

      • revised_prompt string

        The prompt that was used to generate the image, if there was any revision to the prompt.
POST /images/edits 
curl \
 -X POST https://api.openai.com/v1/images/edits \
 -H "Authorization: Bearer $ACCESS_TOKEN" \
 -H "Content-Type: multipart/form-data" \
 -F "image=@file" \
 -F "prompt=A cute baby sea otter wearing a beret" \
 -F "mask=@file" \
 -F "model=dall-e-2" \
 -F "n=1" \
 -F "size=1024x1024" \
 -F "response_format=url" \
 -F "user=user-1234"
Response examples (200) 
{
  "created": 42,
  "data": [
    {
      "b64_json": "string",
      "url": "string",
      "revised_prompt": "string"
    }
  ]
}