Adobe Creative Cloud Image Editing API

openapi: 3.2.0
info:
  title: Adobe Creative Cloud Adobe Firefly Image Editing API
  description: The Adobe Firefly API provides programmatic access to generative AI capabilities for commercial-safe image creation and manipulation. Supports text-to-image generation, generative fill (inpainting), image expansion, and style reference matching. All generated content includes Content Credentials for provenance tracking. Part of Adobe Firefly Services, authenticated via OAuth Server-to-Server credentials from the Adobe Developer Console.
  version: v3
  contact:
    name: Adobe Developer Support
    url: https://developer.adobe.com/
  license:
    name: Proprietary
    url: https://www.adobe.com/legal/terms.html
servers:
- url: https://firefly-api.adobe.io
  description: Adobe Firefly API production server.
security:
- bearerAuth: []
- apiKey: []
tags:
- name: Image Editing
  description: Generative fill, expand, and editing operations.
paths:
  /v3/images/generate-object-composite:
    post:
      operationId: generateObjectComposite
      summary: Adobe Creative Cloud Generate Object Composite
      description: Generates a composite image by placing an object from a source image into a scene, blending lighting, perspective, and style to create a realistic result.
      tags:
      - Image Editing
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ObjectCompositeRequest'
      responses:
        '200':
          description: Composite image generated successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenerateImagesResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /v3/images/fill:
    post:
      operationId: fillImage
      summary: Adobe Creative Cloud Generative Fill
      description: Fills masked regions of an image with AI-generated content guided by a text prompt. The mask defines which areas to regenerate while preserving the rest of the image. Useful for removing objects, adding elements, or replacing backgrounds.
      tags:
      - Image Editing
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FillImageRequest'
      responses:
        '200':
          description: Image filled successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenerateImagesResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /v3/images/expand:
    post:
      operationId: expandImage
      summary: Adobe Creative Cloud Generative Expand
      description: Expands an image beyond its original boundaries using AI to generate new content that seamlessly extends the scene. Specify the target dimensions to control the expansion direction and amount.
      tags:
      - Image Editing
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExpandImageRequest'
      responses:
        '200':
          description: Image expanded successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GenerateImagesResponse'
        '400':
          $ref: '#/components/responses/BadRequest'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  responses:
    BadRequest:
      description: Invalid request parameters.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  schemas:
    ImageReference:
      type: object
      description: Reference to an image by upload ID or presigned URL.
      properties:
        source:
          type: object
          properties:
            uploadId:
              type: string
              description: Upload ID from the image upload endpoint.
            url:
              type: string
              format: uri
              description: Presigned URL to the image.
    ErrorResponse:
      type: object
      properties:
        error_code:
          type: string
          description: Machine-readable error code.
          example: example_value
        message:
          type: string
          description: Human-readable error description.
          example: example_value
    ObjectCompositeRequest:
      type: object
      required:
      - image
      - placement
      properties:
        image:
          $ref: '#/components/schemas/ImageReference'
        placement:
          type: object
          description: Placement configuration for the object.
          properties:
            inpaint:
              type: boolean
              description: Whether to harmonize the placed object.
        prompt:
          type: string
          description: Optional text to guide the composition.
          example: A beautiful sunset over the ocean
        numVariations:
          type: integer
          minimum: 1
          maximum: 4
          example: 42
    ExpandImageRequest:
      type: object
      required:
      - image
      - size
      properties:
        image:
          $ref: '#/components/schemas/ImageReference'
        size:
          type: object
          required:
          - width
          - height
          properties:
            width:
              type: integer
              description: Target width in pixels.
            height:
              type: integer
              description: Target height in pixels.
        prompt:
          type: string
          description: Text describing the content to generate in expanded areas.
          example: A beautiful sunset over the ocean
        placement:
          type: object
          description: How to position the original image within the expanded canvas.
          properties:
            alignment:
              type: object
              properties:
                horizontal:
                  type: string
                  enum:
                  - left
                  - center
                  - right
                vertical:
                  type: string
                  enum:
                  - top
                  - center
                  - bottom
    GenerateImagesResponse:
      type: object
      properties:
        size:
          type: object
          properties:
            width:
              type: integer
            height:
              type: integer
        outputs:
          type: array
          items:
            type: object
            properties:
              seed:
                type: integer
                description: Random seed used for this variation.
              image:
                type: object
                properties:
                  url:
                    type: string
                    format: uri
                    description: URL to the generated image. Expires after 24 hours.
        contentClass:
          type: string
          example: example_value
    FillImageRequest:
      type: object
      required:
      - image
      - mask
      properties:
        image:
          $ref: '#/components/schemas/ImageReference'
        mask:
          $ref: '#/components/schemas/ImageReference'
        prompt:
          type: string
          description: Text describing what to generate in the masked region.
          example: A beautiful sunset over the ocean
        numVariations:
          type: integer
          minimum: 1
          maximum: 4
          default: 1
          example: 42
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: OAuth 2.0 access token obtained via client_credentials grant from https://ims-na1.adobelogin.com/ims/token/v3.
    apiKey:
      type: apiKey
      in: header
      name: x-api-key
      description: Client ID from the Adobe Developer Console project.