Adobe Creative Suite Image Generation API

openapi: 3.1.0
info:
  title: Adobe Creative Suite Adobe Firefly Accessibility Image Generation API
  description: The Adobe Firefly API provides access to Adobe's generative AI capabilities for creating and editing images, vectors, and video from natural language prompts. Built on Adobe's Firefly family of creative generative models, which are trained on licensed and public domain content. Supports text-to-image generation, generative fill, generative expand, generating similar images, object compositing, and video generation. All generation operations are asynchronous.
  version: 3.0.0
  termsOfService: https://www.adobe.com/legal/terms.html
  contact:
    name: Adobe Developer Support
    url: https://developer.adobe.com/support/
  license:
    name: Adobe Developer Terms
    url: https://www.adobe.com/legal/developer-terms.html
servers:
- url: https://firefly-api.adobe.io/v3
  description: Adobe Firefly API v3 production server
security:
- bearerAuth: []
tags:
- name: Image Generation
  description: Text-to-image and image variation generation operations
paths:
  /images/generate-async:
    post:
      operationId: generateImagesAsync
      summary: Adobe Creative Suite Generate Images from Text Prompt
      description: Generates one or more images from a text prompt using the Adobe Firefly generative AI model. Supports optional style presets, content class selection, negative prompts, and seed values for reproducibility. The operation is asynchronous; use the returned job ID to poll for completion and retrieve output image URLs.
      tags:
      - Image Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ImageGenerateRequest'
      responses:
        '202':
          description: Generation job accepted and queued
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncJobSubmitted'
        '400':
          description: Bad request - invalid prompt or parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized - invalid or missing bearer token
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Forbidden - insufficient permissions or quota exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /images/generate-similar-async:
    post:
      operationId: generateSimilarImagesAsync
      summary: Adobe Creative Suite Generate Similar Images
      description: Generates images that are visually similar to a provided reference image while optionally being guided by a text prompt. Useful for producing variations of an existing image or exploring stylistic alternatives based on a visual reference.
      tags:
      - Image Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenerateSimilarRequest'
      responses:
        '202':
          description: Generate similar job accepted and queued
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncJobSubmitted'
        '400':
          description: Bad request - invalid input parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized - invalid or missing bearer token
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    AsyncJobSubmitted:
      type: object
      description: Response returned immediately after an async generation job is submitted
      properties:
        jobId:
          type: string
          description: Unique identifier for the generation job
          example: urn:firefly:jobs:abc123def456
        statusUrl:
          type: string
          description: URL to poll for job status updates
          example: https://firefly-api.adobe.io/v3/status/urn:firefly:jobs:abc123def456
    StyleOptions:
      type: object
      description: Style guidance for image generation
      properties:
        presets:
          type: array
          description: List of style preset identifiers to apply
          items:
            type: string
            enum:
            - photo
            - art
            - graphic
            - bw
            - cool_colors
            - warm_tone
            - muted_color
            - vibrant_color
            - pastel_color
            - golden_hour
            - closeup_portrait
            - wide_angle
            - aerial_view
            - landscape_photography
          example:
          - photo
          - golden_hour
        strength:
          type: integer
          description: Style influence strength from 1 (subtle) to 100 (strong)
          minimum: 1
          maximum: 100
          example: 60
        referenceImage:
          $ref: '#/components/schemas/InputImageReference'
    InputImageReference:
      type: object
      description: Reference to an input image for generative operations
      required:
      - source
      properties:
        source:
          type: object
          description: Source of the input image
          properties:
            url:
              type: string
              description: Publicly accessible URL of the input image
              example: https://my-bucket.s3.amazonaws.com/source-image.jpg
            uploadId:
              type: string
              description: Upload ID for a previously uploaded image via the Firefly upload API
    ErrorResponse:
      type: object
      description: Standard error response body
      properties:
        code:
          type: string
          description: Machine-readable error code
          example: example_value
        message:
          type: string
          description: Human-readable description of the error
          example: example_value
        requestId:
          type: string
          description: Unique identifier for the failed request, for support purposes
          example: asset_abc123
    ImageSize:
      type: object
      description: Dimensions for the output image
      properties:
        width:
          type: integer
          description: Output image width in pixels
          example: 1024
        height:
          type: integer
          description: Output image height in pixels
          example: 1024
    ImageGenerateRequest:
      type: object
      description: Request body for text-to-image generation
      required:
      - prompt
      properties:
        prompt:
          type: string
          description: Text description of the image to generate
          maxLength: 1024
          example: A serene mountain lake at golden hour with reflections of pine trees
        negativePrompt:
          type: string
          description: Text description of elements to avoid in the generated image
          maxLength: 1024
          example: blurry, low quality, distorted
        contentClass:
          type: string
          description: Broad content category to guide the generation model
          enum:
          - photo
          - art
          example: photo
        numVariations:
          type: integer
          description: Number of image variations to generate (1 to 4)
          minimum: 1
          maximum: 4
          default: 1
          example: 2
        size:
          $ref: '#/components/schemas/ImageSize'
        style:
          $ref: '#/components/schemas/StyleOptions'
        seeds:
          type: array
          description: Array of integer seed values for reproducible generation. Providing the same seed with the same prompt produces the same output.
          items:
            type: integer
          example:
          - 42
          - 1337
        locale:
          type: string
          description: BCP 47 language locale for prompt interpretation
          example: en-US
    GenerateSimilarRequest:
      type: object
      description: Request body for generating images similar to a reference image
      required:
      - image
      properties:
        prompt:
          type: string
          description: Optional text prompt to further guide the style or content
          maxLength: 1024
          example: example_value
        image:
          $ref: '#/components/schemas/InputImageReference'
        numVariations:
          type: integer
          minimum: 1
          maximum: 4
          default: 1
          example: 1920
        size:
          $ref: '#/components/schemas/ImageSize'
        seeds:
          type: array
          items:
            type: integer
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: OAuth 2.0 access token obtained from Adobe IMS