> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hiperai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 画像の生成

> Generate new images from text prompts or transform existing images using Google Gemini 2.5 Flash Image.
All requests and responses are processed through SMLTP for security and compliance.

This endpoint supports:
- **Text-to-Image**: Generate images from text descriptions
- **Image-to-Image**: Transform or edit existing images (upload an image file)

All prompts and responses are automatically processed through SMLTP for audit logging and compliance.


# 画像を生成する

テキスト プロンプトから新しい画像を生成するか、Google Gemini 2.5 Flash Image を使用して既存の画像を変換します。

## エンドポイント

```
POST /images/generations
```

## 説明

テキストの説明から新しい画像を生成するか、既存の画像を変換します。このエンドポイントは以下をサポートします。

* **Text-to-Image**: テキストの説明から画像を生成します
* **画像から画像**: 既存の画像を変換または編集します (画像ファイルをアップロードします)

すべてのプロンプトと応答は、監査ログとコンプライアンスのために SMLTP を通じて自動的に処理されます。

## 認証

必須: API キー

```bash theme={null}
Authorization: Bearer sk-your-api-key-here
```

## リクエスト本文

このエンドポイントは、`multipart/form-data` (ファイルのアップロード用) と `application/json` の両方の形式を受け入れます。

### パラメータ

| パラメータ             | タイプ  | 必須  | 説明                                                     |
| ----------------- | ---- | --- | ------------------------------------------------------ |
| `prompt`          | 文字列  | はい  | 生成する画像、またはアップロードした画像の変換方法を説明するテキスト プロンプト (1 ～ 4000 文字) |
| `image`           | バイナリ | いいえ | 画像から画像を生成するための画像ファイル (JPEG、PNG、WEBP、または GIF、最大 10MB)   |
| `smltp_policy`    | 文字列  | いいえ | SMLTP セキュリティ ポリシー (デフォルト: "内部")                        |
| `response_format` | 文字列  | いいえ | 応答形式: "url" または "b64\_json" (デフォルト: "url")             |
| `size`            | 文字列  | いいえ | 画像サイズ (デフォルト: "1024x1024")                             |
| `n`               | 整数   | いいえ | 生成する画像の数 (1 ～ 4、デフォルト: 1)                              |

## リクエストの例

### テキストから画像への変換 (JSON)

```bash theme={null}
curl -X POST "https://{customer.name}.hiperai.ai/api/external/images/generations" \
  -H "Authorization: Bearer sk-your-api-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A beautiful sunset over the ocean with mountains in the background, digital art style",
    "smltp_policy": "internal",
    "response_format": "url",
    "n": 1
  }'
```

### 画像から画像 (マルチパート フォーム データ)

```bash theme={null}
curl -X POST "https://{customer.name}.hiperai.ai/api/external/images/generations" \
  -H "Authorization: Bearer sk-your-api-key-here" \
  -F "prompt=Add dramatic sunset colors to the sky" \
  -F "image=@/path/to/image.jpg" \
  -F "smltp_policy=internal" \
  -F "response_format=url"
```

### JavaScript/Node.js

```javascript theme={null}
// Text-to-Image
const response = await fetch('https://{customer.name}.hiperai.ai/api/external/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-your-api-key-here',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    prompt: 'A beautiful sunset over the ocean with mountains in the background, digital art style',
    smltp_policy: 'internal',
    response_format: 'url',
    n: 1
  })
});

const data = await response.json();
console.log('Generated image URL:', data.data[0].url);

// Image-to-Image
const formData = new FormData();
formData.append('prompt', 'Add dramatic sunset colors to the sky');
formData.append('image', fileInput.files[0]);
formData.append('smltp_policy', 'internal');
formData.append('response_format', 'url');

const response2 = await fetch('https://{customer.name}.hiperai.ai/api/external/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-your-api-key-here'
  },
  body: formData
});

const data2 = await response2.json();
console.log('Edited image URL:', data2.data[0].url);
```

### パイソン

```python theme={null}
import requests

# Text-to-Image
url = "https://{customer.name}.hiperai.ai/api/external/images/generations"
headers = {
    "Authorization": "Bearer sk-your-api-key-here",
    "Content-Type": "application/json"
}
data = {
    "prompt": "A beautiful sunset over the ocean with mountains in the background, digital art style",
    "smltp_policy": "internal",
    "response_format": "url",
    "n": 1
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print('Generated image URL:', result['data'][0]['url'])

# Image-to-Image
with open('image.jpg', 'rb') as f:
    files = {'image': f}
    data = {
        'prompt': 'Add dramatic sunset colors to the sky',
        'smltp_policy': 'internal',
        'response_format': 'url'
    }
    response = requests.post(url, headers={'Authorization': 'Bearer sk-your-api-key-here'}, files=files, data=data)
    result = response.json()
    print('Edited image URL:', result['data'][0]['url'])
```

## 応答

### 成功の応答 (200)

```json theme={null}
{
  "success": true,
  "id": "90d3756f-41c3-4f86-a18d-e257bfbc33a3",
  "object": "image.generation",
  "created": 1705312200,
  "data": [
    {
      "url": "http://localhost:5173/uploads/secureai_image_api_68c5c6d2d57c85b102eb05e2_90d3756f_0.png",
      "revised_prompt": "A beautiful sunset over the ocean with mountains in the background, digital art style"
    }
  ],
  "metadata": {
    "model": "google/gemini-2.5-flash-image-preview",
    "provider": "Google",
    "total_images": 1,
    "is_image_to_image": false,
    "text_response": null,
    "smltp_trace_id": "trx-220eca66-5e3a-4a72-886b-e6ba8cde18a6",
    "smltp_bundle_id": "jti-bb850e61-fbfe-412a-8b0d-d180d4a36d22",
    "smltp_policy": "internal"
  }
}
```

### 応答フィールド

| フィールド      | タイプ    | 説明                            |
| ---------- | ------ | ----------------------------- |
| `success`  | ブール値   | リクエストが成功した場合は常に true          |
| `id`       | 文字列    | 一意のリクエスト識別子                   |
| `object`   | 文字列    | オブジェクトタイプ: "image.generation" |
| `created`  | 整数     | イメージが作成されたときの Unix タイムスタンプ    |
| `data`     | 配列     | 生成された画像の配列                    |
| `metadata` | オブジェクト | SMLTP 追跡を含む追加のメタデータ           |

### 画像オブジェクト

| フィールド            | タイプ | 説明                                                    |
| ---------------- | --- | ----------------------------------------------------- |
| `url`            | 文字列 | 生成された画像にアクセスするための URL (response\_format が "url" の場合)  |
| `b64_json`       | 文字列 | Base64でエンコードされた画像データ（response\_formatが「b64\_json」の場合） |
| `revised_prompt` | 文字列 | 実際に生成に使用されるプロンプト (入力とは異なる場合があります)                     |

### メタデータ オブジェクト

| フィールド               | タイプ       | 説明                                               |
| ------------------- | --------- | ------------------------------------------------ |
| `model`             | 文字列       | 使用したモデル: "google/gemini-2.5-flash-image-preview" |
| `provider`          | 文字列       | プロバイダー: 「Google」                                 |
| `total_images`      | 整数        | 生成された画像の総数                                       |
| `is_image_to_image` | ブール値      | これがイメージ間の生成かどうか                                  |
| `text_response`     | 文字列\|null | モデルからのオプションのテキスト応答                               |
| `smltp_trace_id`    | 文字列       | 監査追跡用の SMLTP トレース ID                             |
| `smltp_bundle_id`   | 文字列       | 監査追跡用の SMLTP バンドル ID                             |
| `smltp_policy`      | 文字列       | 適用された SMLTP ポリシー                                 |

## エラー応答

### 400 不正なリクエスト

```json theme={null}
{
  "success": false,
  "error": "Invalid prompt",
  "message": "Prompt is required and must be a non-empty string",
  "request_id": "90d3756f-41c3-4f86-a18d-e257bfbc33a3"
}
```

### 401 不正

```json theme={null}
{
  "success": false,
  "error": "Invalid API key",
  "message": "The provided API key is invalid or has been revoked"
}
```

### 403 禁止

```json theme={null}
{
  "success": false,
  "error": "Access denied",
  "message": "SMLTP policy not allowed"
}
```

### 413 ペイロードが大きすぎます

```json theme={null}
{
  "success": false,
  "error": "File too large",
  "message": "Maximum image size is 10MB",
  "request_id": "90d3756f-41c3-4f86-a18d-e257bfbc33a3"
}
```

### 500 内部サーバーエラー

```json theme={null}
{
  "success": false,
  "error": "Internal server error",
  "message": "Image generation failed"
}
```

### 503 サービスは利用できません

```json theme={null}
{
  "success": false,
  "error": "Service unavailable",
  "message": "Image generation service is not configured",
  "request_id": "90d3756f-41c3-4f86-a18d-e257bfbc33a3"
}
```

## 注意事項

* アップロードでサポートされている画像形式: JPEG、PNG、WEBP、GIF
* 最大ファイルサイズ: 画像あたり 10MB
* 画像をアップロードするときに、画像を変換する方法について説明するプロンプトが表示されます
* Gemini は通常、リクエストごとに 1 ～ 4 つのイメージを生成します
* セキュリティとコンプライアンスのために、すべてのリクエストは SMLTP を通じて処理されます
* URL の代わりに `response_format: "b64_json"` を使用して、base64 でエンコードされた画像データを受信します


## OpenAPI

````yaml POST /images/generations
openapi: 3.0.3
info:
  title: SecureAI External API
  description: >
    SecureAI External API provides AI chat completion and image generation
    capabilities with knowledge base retrieval, 

    security policies, and comprehensive usage tracking. This API is designed
    for external developers 

    and integrations using API key authentication.


    ## Key Features

    - **RAG (Retrieval-Augmented Generation)**: Automatically search knowledge
    bases for relevant context

    - **Multi-Model Support**: OpenAI, Anthropic, Google, Meta, and other AI
    models

    - **Model Redundancy & Failover**: Caller-defined failover chains (primary +
    fallbacks) with per-attempt timeouts

    - **OpenAI-Compatible Endpoint**: Point any OpenAI SDK at `/api/external/v1`
    — no code changes

    - **Image Generation**: Generate and edit images using Google Gemini 2.5
    Flash Image

    - **Speech-to-Speech (S2S)**: Real-time voice conversations using OpenAI
    Realtime API with WebRTC

    - **Security Policies**: SMLTP policy enforcement, per-call Prompt Shield,
    and signed compliance receipts

    - **Usage Tracking**: Comprehensive usage monitoring, self-service quota,
    and rate limiting

    - **Knowledge Base Integration**: Access to personal and shared knowledge
    bases

    - **User Management**: Complete user, group, and role management
    capabilities

    - **Audit Logging**: Comprehensive activity and security audit logs


    ## Authentication

    All endpoints (except health check) require API key authentication using
    Bearer token:

    ```

    Authorization: Bearer sk-your-api-key-here

    ```


    ## Billing and Usage

    By default, API requests are billed to the user account that owns the API
    key. You can specify 

    a different user to bill by including the `user_id` parameter in your
    request. This allows for:

    - Multi-tenant applications with per-user billing

    - Flexible completion limit management

    - Per-user "Usage by Model" settings


    ## Rate Limits

    - Default: 60 requests per minute, 1000 requests per hour

    - Daily limits: 100 requests (configurable)

    - Monthly limits: 10,000 requests (configurable)


    ## Base URL

    ```

    https://secureai.hiperai.ai/api/external

    ```
  version: 1.1.0
  contact:
    name: SecureAI Support
    email: support@secureai.hiperai.ai
  license:
    name: Proprietary
    url: https://secureai.hiperai.ai/terms
servers:
  - url: https://secureai.hiperai.ai/api/external
    description: Production server
  - url: http://localhost:3010/api/external
    description: Development server
security:
  - ApiKeyAuth: []
tags:
  - name: System
    description: System health and status endpoints
  - name: Discovery
    description: Endpoints to discover available models, indexes, and policies
  - name: Chat
    description: AI chat completion endpoints
  - name: User Management
    description: Endpoints for managing user accounts and roles
  - name: Index Management
    description: Endpoints for managing knowledge base indexes
  - name: Group Management
    description: Endpoints for managing user groups
  - name: SMLTP Security
    description: Endpoints for managing SMLTP security policies and audit logs
  - name: Role Management
    description: Endpoints for managing user roles
  - name: Activity Logs
    description: Endpoints for retrieving activity logs
externalDocs:
  description: SecureAI Documentation
  url: https://secureai.hiperai.ai/docs
paths:
  /images/generations:
    post:
      tags:
        - Images
      summary: Generate or Edit Images
      description: >
        Generate new images from text prompts or transform existing images using
        Google Gemini 2.5 Flash Image.

        All requests and responses are processed through SMLTP for security and
        compliance.


        This endpoint supports:

        - **Text-to-Image**: Generate images from text descriptions

        - **Image-to-Image**: Transform or edit existing images (upload an image
        file)


        All prompts and responses are automatically processed through SMLTP for
        audit logging and compliance.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
                - prompt
              properties:
                prompt:
                  type: string
                  description: >-
                    The text prompt describing the image to generate or how to
                    transform the uploaded image
                  example: >-
                    A beautiful sunset over the ocean with mountains in the
                    background, digital art style
                  minLength: 1
                  maxLength: 4000
                image:
                  type: string
                  format: binary
                  description: >-
                    Optional image file for image-to-image generation (JPEG,
                    PNG, WEBP, or GIF, max 10MB)
                smltp_policy:
                  type: string
                  description: >-
                    SMLTP security policy to apply (e.g., 'internal', 'public',
                    'confidential', 'hipaa', 'gdpr')
                  default: internal
                  example: internal
                response_format:
                  type: string
                  description: The format of the response images
                  enum:
                    - url
                    - b64_json
                  default: url
                  example: url
                size:
                  type: string
                  description: >-
                    The size of the generated images (for future use, currently
                    uses default size)
                  default: 1024x1024
                  example: 1024x1024
                'n':
                  type: integer
                  description: >-
                    Number of images to generate (Gemini typically generates 1-4
                    images)
                  minimum: 1
                  maximum: 4
                  default: 1
                  example: 1
          application/json:
            schema:
              type: object
              required:
                - prompt
              properties:
                prompt:
                  type: string
                  description: The text prompt describing the image to generate
                  example: >-
                    A beautiful sunset over the ocean with mountains in the
                    background, digital art style
                  minLength: 1
                  maxLength: 4000
                smltp_policy:
                  type: string
                  description: SMLTP security policy to apply
                  default: internal
                  example: internal
                response_format:
                  type: string
                  description: The format of the response images
                  enum:
                    - url
                    - b64_json
                  default: url
                  example: url
                size:
                  type: string
                  description: The size of the generated images (for future use)
                  default: 1024x1024
                  example: 1024x1024
                'n':
                  type: integer
                  description: Number of images to generate
                  minimum: 1
                  maximum: 4
                  default: 1
                  example: 1
            example:
              prompt: >-
                A beautiful sunset over the ocean with mountains in the
                background, digital art style
              smltp_policy: internal
              response_format: url
              'n': 1
      responses:
        '200':
          description: Images generated successfully
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    example: true
                  id:
                    type: string
                    description: Unique request identifier
                    example: 90d3756f-41c3-4f86-a18d-e257bfbc33a3
                  object:
                    type: string
                    example: image.generation
                  created:
                    type: integer
                    description: Unix timestamp of when the images were created
                    example: 1705312200
                  data:
                    type: array
                    description: Array of generated images
                    items:
                      type: object
                      properties:
                        url:
                          type: string
                          format: uri
                          description: >-
                            URL to access the generated image (when
                            response_format is 'url')
                          example: >-
                            http://localhost:5173/uploads/secureai_image_api_68c5c6d2d57c85b102eb05e2_90d3756f_0.png
                        b64_json:
                          type: string
                          description: >-
                            Base64-encoded image data (when response_format is
                            'b64_json')
                          example: iVBORw0KGgoAAAANSUhEUgAA...
                        revised_prompt:
                          type: string
                          description: >-
                            The prompt that was actually used for generation
                            (may differ from input)
                          example: >-
                            A beautiful sunset over the ocean with mountains in
                            the background, digital art style
                  metadata:
                    type: object
                    properties:
                      model:
                        type: string
                        example: google/gemini-2.5-flash-image-preview
                      provider:
                        type: string
                        example: Google
                      total_images:
                        type: integer
                        example: 1
                      is_image_to_image:
                        type: boolean
                        description: Whether this was an image-to-image generation
                        example: false
                      text_response:
                        type: string
                        nullable: true
                        description: Optional text response from the model
                        example: null
                      smltp_trace_id:
                        type: string
                        description: SMLTP trace ID for audit tracking
                        example: trx-220eca66-5e3a-4a72-886b-e6ba8cde18a6
                      smltp_bundle_id:
                        type: string
                        description: SMLTP bundle ID for audit tracking
                        example: jti-bb850e61-fbfe-412a-8b0d-d180d4a36d22
                      smltp_policy:
                        type: string
                        description: SMLTP policy that was applied
                        example: internal
              example:
                success: true
                id: 90d3756f-41c3-4f86-a18d-e257bfbc33a3
                object: image.generation
                created: 1705312200
                data:
                  - url: >-
                      http://localhost:5173/uploads/secureai_image_api_68c5c6d2d57c85b102eb05e2_90d3756f_0.png
                    revised_prompt: >-
                      A beautiful sunset over the ocean with mountains in the
                      background, digital art style
                metadata:
                  model: google/gemini-2.5-flash-image-preview
                  provider: Google
                  total_images: 1
                  is_image_to_image: false
                  text_response: null
                  smltp_trace_id: trx-220eca66-5e3a-4a72-886b-e6ba8cde18a6
                  smltp_bundle_id: jti-bb850e61-fbfe-412a-8b0d-d180d4a36d22
                  smltp_policy: internal
        '400':
          description: >-
            Invalid request parameters (missing prompt, invalid image format,
            etc.)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                success: false
                error: Invalid prompt
                message: Prompt is required and must be a non-empty string
                request_id: 90d3756f-41c3-4f86-a18d-e257bfbc33a3
        '401':
          description: Invalid API key
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Access denied (SMLTP policy not allowed)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '413':
          description: Image file too large (maximum 10MB)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                success: false
                error: File too large
                message: Maximum image size is 10MB
                request_id: 90d3756f-41c3-4f86-a18d-e257bfbc33a3
        '500':
          description: Internal server error or image generation failed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '503':
          description: Image generation service unavailable (Gemini service not configured)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              example:
                success: false
                error: Service unavailable
                message: Image generation service is not configured
                request_id: 90d3756f-41c3-4f86-a18d-e257bfbc33a3
      security:
        - ApiKeyAuth: []
components:
  schemas:
    ErrorResponse:
      type: object
      properties:
        success:
          type: boolean
          example: false
        error:
          type: string
          example: Invalid API key
        message:
          type: string
          example: The provided API key is invalid or has been revoked
        request_id:
          type: string
          example: req-abc123
          description: Request ID for tracking (if available)
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
      description: |
        API key authentication using Bearer token format.
        Example: `Authorization: Bearer sk-your-api-key-here`

````