AdsTurbo Image API

openapi: 3.2.0
info:
  title: AdsTurbo Open Image API
  description: 'AdsTurbo Open API documentation. All endpoints are under `/openapi/v1/`.


    **Base URL**: `https://adsturbo.ai/klian/novartapi`


    **Authentication**: Use **HTTP Bearer** (RFC 6750). Send `Authorization: Bearer `, where `` is the API key created in the AdsTurbo console.


    **Request body**: `Content-Type: application/json`


    **Success response**: HTTP 200 with `{ "ret": 1, "data": { "ent": } }`


    **Business errors**: HTTP 200 may still contain `ret` other than `1`. Read `msg` for the error reason.'
  version: 1.0.0
servers:
- url: https://adsturbo.ai/klian/novartapi
  description: API base URL
security:
- bearerAuth: []
tags:
- name: Image
  description: Image creation and editing
paths:
  /openapi/v1/img/create:
    post:
      tags:
      - Image
      summary: Create or edit images
      operationId: saasImageCreate
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ImageCreateBody'
            examples:
              basic:
                summary: Basic example
                value:
                  prompt: Create an anime-style Asian child riding a winged teddy dog
                  model: nanobanana-pro
                  image_urls: []
                  ratio: '9:16'
                  resolution: 2k
                  concurrency: 1
                  sync_mod: false
      responses:
        '200':
          description: JSON business response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiSuccessImageCreateEnt'
      description: Create a new image from a text prompt, or edit one or more input images depending on the selected model.
components:
  schemas:
    ApiSuccessImageCreateEnt:
      type: object
      required:
      - ret
      properties:
        ret:
          type: integer
          example: 1
        msg:
          type: string
        data:
          type: object
          properties:
            ent:
              $ref: '#/components/schemas/ImageCreateData'
    ImageCreateData:
      type: object
      description: Image generation result, including image URLs and related task IDs.
      properties:
        images:
          type: array
          items:
            type: string
        workspace_ids:
          type: array
          items:
            type: string
    ImageCreateBody:
      type: object
      description: 'Create or edit images. `model` is the short model name. If omitted, the server defaults to `nanobanana-pro`.

        For text-to-image, send an empty `image_urls` array. For image editing, send one or more `image_urls`.


        **Mode support**:

        - Text-to-image only: `grok-2-image`

        - Editing only: `seedream-4.5-seq`, `seedream-5.0-lite-seq`, `grok-imagine-image`

        - Text-to-image + editing: `nanobanana-pro`, `nano-banana-2`, `nano-banana-2-fast`, `seedream-4.5`, `seedream-5.0-lite`, `gpt-image-2`


        **Model-specific parameters**:

        - Supported `ratio` values vary by model.

        - `resolution` is supported only by `nanobanana-pro`, `nano-banana-2`, `nano-banana-2-fast`, and `gpt-image-2`.

        - `quality` is supported only by `gpt-image-2`.

        - `num_images` is supported only by `seedream-4.5-seq` and `seedream-5.0-lite-seq`, with a maximum of 15.'
      properties:
        prompt:
          type: string
          description: Text prompt for image generation.
        image_urls:
          type: array
          items:
            type: string
          description: Empty for text-to-image. Non-empty for image editing.
        model:
          type: string
          example: nanobanana-pro
          enum:
          - nanobanana-pro
          - nano-banana-2
          - nano-banana-2-fast
          - seedream-4.5
          - seedream-4.5-seq
          - seedream-5.0-lite
          - seedream-5.0-lite-seq
          - gpt-image-2
          - grok-2-image
          - grok-imagine-image
          description: Optional. Defaults to `nanobanana-pro`.
        ratio:
          type: string
          example: '9:16'
          description: Supported values vary by model. See the request body description.
          enum:
          - '1:1'
          - '3:2'
          - '2:3'
          - '3:4'
          - '4:3'
          - '4:5'
          - '5:4'
          - '16:9'
          - '9:16'
          - '21:9'
        resolution:
          type: string
          example: 2k
          description: Supported only by selected models. See the request body description.
          enum:
          - 0.5k
          - 1k
          - 2k
          - 4k
          - 8k
        quality:
          type: string
          description: Supported only by `gpt-image-2`.
          enum:
          - low
          - medium
          - high
        num_images:
          type: integer
          format: int32
          minimum: 1
          maximum: 15
          description: Supported only by `seedream-4.5-seq` and `seedream-5.0-lite-seq`.
        concurrency:
          type: integer
          format: int32
          description: Number of concurrent outputs to generate.
          example: 1
        sync_mod:
          type: boolean
          example: false
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: '在 [adsturbo.ai](https://adsturbo.ai) 控制台创建的密钥。调用时在请求头设置：`Authorization: Bearer <your_api_key>`。

        '