openai/src/resources/images.ts

The official TypeScript library for the OpenAI API

// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.

import { APIResource } from '../resource';
import * as Core from '../core';

export class Images extends APIResource {
  /**
   * Creates a variation of a given image. This endpoint only supports `dall-e-2`.
   */
  createVariation(
    body: ImageCreateVariationParams,
    options?: Core.RequestOptions,
  ): Core.APIPromise<ImagesResponse> {
    return this._client.post('/images/variations', Core.multipartFormRequestOptions({ body, ...options }));
  }

  /**
   * Creates an edited or extended image given one or more source images and a
   * prompt. This endpoint only supports `gpt-image-1` and `dall-e-2`.
   */
  edit(body: ImageEditParams, options?: Core.RequestOptions): Core.APIPromise<ImagesResponse> {
    return this._client.post('/images/edits', Core.multipartFormRequestOptions({ body, ...options }));
  }

  /**
   * Creates an image given a prompt.
   * [Learn more](https://platform.openai.com/docs/guides/images).
   */
  generate(body: ImageGenerateParams, options?: Core.RequestOptions): Core.APIPromise<ImagesResponse> {
    return this._client.post('/images/generations', { body, ...options });
  }
}

/**
 * Represents the content or the URL of an image generated by the OpenAI API.
 */
export interface Image {
  /**
   * The base64-encoded JSON of the generated image. Default value for `gpt-image-1`,
   * and only present if `response_format` is set to `b64_json` for `dall-e-2` and
   * `dall-e-3`.
   */
  b64_json?: string;

  /**
   * For `dall-e-3` only, the revised prompt that was used to generate the image.
   */
  revised_prompt?: string;

  /**
   * When using `dall-e-2` or `dall-e-3`, the URL of the generated image if
   * `response_format` is set to `url` (default value). Unsupported for
   * `gpt-image-1`.
   */
  url?: string;
}

export type ImageModel = 'dall-e-2' | 'dall-e-3' | 'gpt-image-1';

/**
 * The response from the image generation endpoint.
 */
export interface ImagesResponse {
  /**
   * The Unix timestamp (in seconds) of when the image was created.
   */
  created: number;

  /**
   * The list of generated images.
   */
  data?: Array<Image>;

  /**
   * For `gpt-image-1` only, the token usage information for the image generation.
   */
  usage?: ImagesResponse.Usage;
}

export namespace ImagesResponse {
  /**
   * For `gpt-image-1` only, the token usage information for the image generation.
   */
  export interface Usage {
    /**
     * The number of tokens (images and text) in the input prompt.
     */
    input_tokens: number;

    /**
     * The input tokens detailed information for the image generation.
     */
    input_tokens_details: Usage.InputTokensDetails;

    /**
     * The number of image tokens in the output image.
     */
    output_tokens: number;

    /**
     * The total number of tokens (images and text) used for the image generation.
     */
    total_tokens: number;
  }

  export namespace Usage {
    /**
     * The input tokens detailed information for the image generation.
     */
    export interface InputTokensDetails {
      /**
       * The number of image tokens in the input prompt.
       */
      image_tokens: number;

      /**
       * The number of text tokens in the input prompt.
       */
      text_tokens: number;
    }
  }
}

export interface ImageCreateVariationParams {
  /**
   * The image to use as the basis for the variation(s). Must be a valid PNG file,
   * less than 4MB, and square.
   */
  image: Core.Uploadable;

  /**
   * The model to use for image generation. Only `dall-e-2` is supported at this
   * time.
   */
  model?: (string & {}) | ImageModel | null;

  /**
   * The number of images to generate. Must be between 1 and 10.
   */
  n?: number | 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.
   */
  response_format?: 'url' | 'b64_json' | null;

  /**
   * The size of the generated images. Must be one of `256x256`, `512x512`, or
   * `1024x1024`.
   */
  size?: '256x256' | '512x512' | '1024x1024' | null;

  /**
   * A unique identifier representing your end-user, which can help OpenAI to monitor
   * and detect abuse.
   * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
   */
  user?: string;
}

export interface ImageEditParams {
  /**
   * The image(s) to edit. Must be a supported image file or an array of images. For
   * `gpt-image-1`, each image should be a `png`, `webp`, or `jpg` file less than
   * 25MB. For `dall-e-2`, you can only provide one image, and it should be a square
   * `png` file less than 4MB.
   */
  image: Core.Uploadable | Array<Core.Uploadable>;

  /**
   * A text description of the desired image(s). The maximum length is 1000
   * characters for `dall-e-2`, and 32000 characters for `gpt-image-1`.
   */
  prompt: string;

  /**
   * An additional image whose fully transparent areas (e.g. where alpha is zero)
   * indicate where `image` should be edited. If there are multiple images provided,
   * the mask will be applied on the first image. Must be a valid PNG file, less than
   * 4MB, and have the same dimensions as `image`.
   */
  mask?: Core.Uploadable;

  /**
   * The model to use for image generation. Only `dall-e-2` and `gpt-image-1` are
   * supported. Defaults to `dall-e-2` unless a parameter specific to `gpt-image-1`
   * is used.
   */
  model?: (string & {}) | ImageModel | null;

  /**
   * The number of images to generate. Must be between 1 and 10.
   */
  n?: number | null;

  /**
   * The quality of the image that will be generated. `high`, `medium` and `low` are
   * only supported for `gpt-image-1`. `dall-e-2` only supports `standard` quality.
   * Defaults to `auto`.
   */
  quality?: 'standard' | 'low' | 'medium' | 'high' | 'auto' | 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. This parameter is only supported for `dall-e-2`, as `gpt-image-1`
   * will always return base64-encoded images.
   */
  response_format?: 'url' | 'b64_json' | null;

  /**
   * The size of the generated images. Must be one of `1024x1024`, `1536x1024`
   * (landscape), `1024x1536` (portrait), or `auto` (default value) for
   * `gpt-image-1`, and one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`.
   */
  size?: '256x256' | '512x512' | '1024x1024' | null;

  /**
   * A unique identifier representing your end-user, which can help OpenAI to monitor
   * and detect abuse.
   * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
   */
  user?: string;
}

export interface ImageGenerateParams {
  /**
   * A text description of the desired image(s). The maximum length is 32000
   * characters for `gpt-image-1`, 1000 characters for `dall-e-2` and 4000 characters
   * for `dall-e-3`.
   */
  prompt: string;

  /**
   * Allows to set transparency for the background of the generated image(s). This
   * parameter is only supported for `gpt-image-1`. Must be one of `transparent`,
   * `opaque` or `auto` (default value). When `auto` is used, the model will
   * automatically determine the best background for the image.
   *
   * If `transparent`, the output format needs to support transparency, so it should
   * be set to either `png` (default value) or `webp`.
   */
  background?: 'transparent' | 'opaque' | 'auto' | null;

  /**
   * The model to use for image generation. One of `dall-e-2`, `dall-e-3`, or
   * `gpt-image-1`. Defaults to `dall-e-2` unless a parameter specific to
   * `gpt-image-1` is used.
   */
  model?: (string & {}) | ImageModel | null;

  /**
   * Control the content-moderation level for images generated by `gpt-image-1`. Must
   * be either `low` for less restrictive filtering or `auto` (default value).
   */
  moderation?: 'low' | 'auto' | null;

  /**
   * The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only
   * `n=1` is supported.
   */
  n?: number | null;

  /**
   * The compression level (0-100%) for the generated images. This parameter is only
   * supported for `gpt-image-1` with the `webp` or `jpeg` output formats, and
   * defaults to 100.
   */
  output_compression?: number | null;

  /**
   * The format in which the generated images are returned. This parameter is only
   * supported for `gpt-image-1`. Must be one of `png`, `jpeg`, or `webp`.
   */
  output_format?: 'png' | 'jpeg' | 'webp' | null;

  /**
   * The quality of the image that will be generated.
   *
   * - `auto` (default value) will automatically select the best quality for the
   *   given model.
   * - `high`, `medium` and `low` are supported for `gpt-image-1`.
   * - `hd` and `standard` are supported for `dall-e-3`.
   * - `standard` is the only option for `dall-e-2`.
   */
  quality?: 'standard' | 'hd' | 'low' | 'medium' | 'high' | 'auto' | null;

  /**
   * The format in which generated images with `dall-e-2` and `dall-e-3` are
   * returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes
   * after the image has been generated. This parameter isn't supported for
   * `gpt-image-1` which will always return base64-encoded images.
   */
  response_format?: 'url' | 'b64_json' | null;

  /**
   * The size of the generated images. Must be one of `1024x1024`, `1536x1024`
   * (landscape), `1024x1536` (portrait), or `auto` (default value) for
   * `gpt-image-1`, one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`, and
   * one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3`.
   */
  size?:
    | 'auto'
    | '1024x1024'
    | '1536x1024'
    | '1024x1536'
    | '256x256'
    | '512x512'
    | '1792x1024'
    | '1024x1792'
    | null;

  /**
   * The style of the generated images. This parameter is only supported for
   * `dall-e-3`. Must be one of `vivid` or `natural`. Vivid causes the model to lean
   * towards generating hyper-real and dramatic images. Natural causes the model to
   * produce more natural, less hyper-real looking images.
   */
  style?: 'vivid' | 'natural' | null;

  /**
   * A unique identifier representing your end-user, which can help OpenAI to monitor
   * and detect abuse.
   * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#end-user-ids).
   */
  user?: string;
}

export declare namespace Images {
  export {
    type Image as Image,
    type ImageModel as ImageModel,
    type ImagesResponse as ImagesResponse,
    type ImageCreateVariationParams as ImageCreateVariationParams,
    type ImageEditParams as ImageEditParams,
    type ImageGenerateParams as ImageGenerateParams,
  };
}