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

# Seedream 4.5 图像编辑

> Seedream 4.5 图像编辑 API 通过文本提示词和 1-10 张参考图编辑图像，每次请求生成 1-15 张编辑后的图像。

> [!TIP]
>
> 1. 提交后会返回 `task_id`。如果提供了 `callback_url`，当任务状态变为 `finished` 或 `failed` 时，系统会向 `callback_url` 发送 POST 请求。
> 2. 无论是否提供 `callback_url`，都可以通过统一的[查询任务状态](https://docs.vidgo.ai/zh/api-manual/task-management/status.md)接口获取结果。

使用 Seedream 4.5，通过文本提示词和 1-10 张参考图编辑图像，每次请求生成 1-15 张编辑后的图像。

## 模型

* **bytedance/seedream/v4.5/edit** - 使用提示词和参考图编辑图像。

## 功能

* 使用提示词和参考图编辑图像。
* `image_urls` 接受 1-10 张图像。
* 通过 `n` 控制输出图像数量。

## 输出选项

### 图像尺寸

* `size`：可选。默认：`1:1`。
* 预设：`2K`、`4K`、`1:1`、`4:3`、`3:4`、`16:9`、`9:16`、`3:2`、`2:3`、`21:9`。
* 自定义尺寸时，提供包含整数 `width` 和 `height` 的对象，两者都必须为正数。
* 自定义尺寸也可以使用 `WIDTHxHEIGHT` 字符串，两个正数之间用 `x` 或 `X` 分隔。

### 图像数量

* `n`：可选。要生成的图像数量。`1` 到 `15` 的整数。默认：`1`。

## 高级参数

`model` 和可选的 `callback_url` 放在请求根级。所有工作流参数（包括输出选项）都放在 `input` 内。

输入图像 URL 使用 HTTP(S)，并指向公开可访问的 JPEG 或 PNG 文件。

### 提示词

* `prompt`：必填。描述要做的修改。长度：**1-3,000 个字符**。
* 至少包含一个非空白字符。

### 图像 URL

* `image_urls`：必填。提供公开可访问的图像 URL。1-10 项。每项都必须是指向 JPEG 或 PNG 图像的 HTTP(S) URL。

### 安全检查

* `enable_safety_checker`：可选。设为 `true` 开启内容安全检查，设为 `false` 关闭。默认：`true`。

## 已验证示例

此示例通过 Vidgo 测试 API、使用 API Playground 中的 `basic` 请求生成。它按顺序组合了三张参考图：孩子、玩具帆船和湖岸。源图和结果图托管在 Vidgo CDN 上。

![参考图 1：孩子](https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-01.png)

![参考图 2：玩具帆船](https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-02.png)

![参考图 3：湖岸](https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-03.png)

![放飞玩具船](https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/output.jpg)

```json theme={null}
{
  "code": 200,
  "data": {
    "task_id": "GAPP1TYEWHR5CQVS",
    "status": "finished",
    "files": [
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/output.jpg",
        "file_type": "image"
      }
    ],
    "created_time": "2026-09-25T16:16:53",
    "error_message": null,
    "progress": 100
  }
}
```


## OpenAPI

````yaml zh/api-manual/image-series/bytedance-seedream-v4-5-edit.json POST /api/generate/submit
openapi: 3.0.0
info:
  title: Vidgo API - Seedream 4.5 图像编辑
  description: 使用 Seedream 4.5，通过文本提示词和 1-10 张参考图编辑图像，每次请求生成 1-15 张编辑后的图像。
  version: 1.0.0
servers:
  - url: https://api.vidgo.ai
security:
  - BearerAuth: []
paths:
  /api/generate/submit:
    post:
      tags:
        - Image Series
      summary: Seedream 4.5 图像编辑
      description: 提交异步图像编辑任务。prompt 为 1–3,000 个字符。自定义尺寸的宽和高均为正整数。
      operationId: submit_bytedance_seedream_v4_5_edit
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
              additionalProperties: true
              properties:
                model:
                  type: string
                  example: bytedance/seedream/v4.5/edit
                  enum:
                    - bytedance/seedream/v4.5/edit
                input:
                  type: object
                  required:
                    - image_urls
                    - prompt
                  properties:
                    prompt:
                      type: string
                      maxLength: 3000
                      minLength: 1
                      description: 描述要做的修改，1–3,000 个字符，且至少包含一个非空白字符。
                    image_urls:
                      type: array
                      items:
                        type: string
                        format: uri
                        description: JPEG 或 PNG 图像的公开 HTTP(S) URL。
                      minItems: 1
                      maxItems: 10
                      description: 1–10 个按顺序排列的 HTTP(S) 参考图 URL。格式：JPEG、PNG。
                    size:
                      oneOf:
                        - type: string
                          description: >-
                            使用预设（`2K`、`4K`、`1:1`、`4:3`、`3:4`、`16:9`、`9:16`、`3:2`、`2:3`、`21:9`）或自定义
                            `WIDTHxHEIGHT` 尺寸。


                            宽和高之间用 `x` 或 `X` 分隔。
                          title: 尺寸字符串
                        - type: object
                          required:
                            - width
                            - height
                          properties:
                            width:
                              type: integer
                              description: 输出宽度（像素），正整数。
                              minimum: 1
                            height:
                              type: integer
                              description: 输出高度（像素），正整数。
                              minimum: 1
                          additionalProperties: false
                          description: 以对象表示的自定义尺寸，宽和高均为正整数。
                          title: 宽和高
                      default: '1:1'
                      description: 输出尺寸：2K、4K、比例预设、WIDTHxHEIGHT 字符串，或宽高为正整数的对象。默认：1:1。
                    'n':
                      type: integer
                      minimum: 1
                      maximum: 15
                      default: 1
                      description: 要生成的图像数量，1 到 15。默认：1。
                    enable_safety_checker:
                      type: boolean
                      default: true
                      description: 设为 true 开启安全检查，设为 false 关闭。默认：true。
                  additionalProperties: false
                callback_url:
                  type: string
                  nullable: true
                  description: 可选的公开 HTTP(S) URL，用于接收任务完成通知。
              description: model 和可选的 callback_url 放在请求根级，生成参数放在 input 内。
            examples:
              basic:
                summary: 已验证的默认示例：放飞玩具船
                value:
                  model: bytedance/seedream/v4.5/edit
                  input:
                    prompt: >-
                      Combine the three reference images into one natural
                      photograph. Use the boy from image 1 with the same face,
                      curly dark hair, freckles, red hooded raincoat with wooden
                      toggles, navy trousers and yellow rubber boots. Use the
                      exact toy sailboat from image 2: teal wooden hull with a
                      white stripe, cream canvas sail with the stitched patch
                      and dark blue painted star, red string at the bow. Place
                      them on the misty loch shoreline from image 3. The boy
                      crouches on the flat rocks at the water's edge, seen in
                      three-quarter side view, gently setting the sailboat onto
                      the calm water with both hands while holding the red
                      string; small ripples spread around the hull. Keep the
                      pebbles, rust bracken hills and misty pines of the
                      location. Soft overcast morning light, consistent scale
                      and shadows, realistic reflections in the water, a quiet
                      tender moment, no text, no watermark.
                    image_urls:
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-01.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-02.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-03.png
                    size: '3:2'
                    'n': 1
                    enable_safety_checker: true
              verified-2:
                summary: 已验证示例：重新雕刻的峡谷步道路牌
                value:
                  model: bytedance/seedream/v4.5/edit
                  input:
                    prompt: >-
                      Edit only the carved text on the two wooden arrow boards.
                      Change the upper board text to exactly "HIDDEN SPRING 2
                      MI" and the lower board text to exactly "RANGER CABIN 5
                      MI". Keep the same arrow directions, the same deeply
                      carved cream-painted capital letters, the same font style,
                      letter depth, wood grain, weathering and perspective of
                      each board. Keep everything else unchanged: the post,
                      sagebrush, boulders, red canyon cliffs, sky, lighting and
                      shadows. No other text, no watermark.
                    image_urls:
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/02/input-01.png
                    size: '4:3'
                    'n': 1
                    enable_safety_checker: true
              verified-3:
                summary: 已验证示例：蜡笔野餐立体模型
                value:
                  model: bytedance/seedream/v4.5/edit
                  input:
                    prompt: >-
                      Turn this child's crayon drawing into a photograph of a
                      handcrafted miniature diorama built on a tabletop, keeping
                      the exact same composition and layout. The big tree with
                      the round green crown and the wooden treehouse with its
                      rope ladder stays on the left; the family of four sits on
                      the red and white checkered picnic blanket on the right
                      with the basket and watermelon slice; the spotty
                      black-and-white dog runs in the same place; the yellow sun
                      sits in the top right corner with the blue clouds on a
                      painted backdrop; green grass and two red flowers along
                      the bottom. Make everything tangible: sculpted clay
                      figures with simple friendly faces, a real twig tree trunk
                      with felt leaves, a tiny balsa-wood treehouse, fabric
                      blanket, flocked grass. Macro photography with shallow
                      depth of field, soft warm window light, tilt-shift
                      miniature feeling, no text, no watermark.
                    image_urls:
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/03/input-01.png
                    size: '4:3'
                    'n': 1
                    enable_safety_checker: true
              callback:
                summary: 接收完成回调
                value:
                  model: bytedance/seedream/v4.5/edit
                  input:
                    prompt: >-
                      Combine the three reference images into one natural
                      photograph. Use the boy from image 1 with the same face,
                      curly dark hair, freckles, red hooded raincoat with wooden
                      toggles, navy trousers and yellow rubber boots. Use the
                      exact toy sailboat from image 2: teal wooden hull with a
                      white stripe, cream canvas sail with the stitched patch
                      and dark blue painted star, red string at the bow. Place
                      them on the misty loch shoreline from image 3. The boy
                      crouches on the flat rocks at the water's edge, seen in
                      three-quarter side view, gently setting the sailboat onto
                      the calm water with both hands while holding the red
                      string; small ripples spread around the hull. Keep the
                      pebbles, rust bracken hills and misty pines of the
                      location. Soft overcast morning light, consistent scale
                      and shadows, realistic reflections in the water, a quiet
                      tender moment, no text, no watermark.
                    image_urls:
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-01.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-02.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-03.png
                    size: '3:2'
                    'n': 1
                    enable_safety_checker: true
                  callback_url: https://your-domain.com/callback
              custom-string:
                summary: 自定义尺寸字符串
                value:
                  model: bytedance/seedream/v4.5/edit
                  input:
                    prompt: >-
                      Combine the three reference images into one natural
                      photograph. Use the boy from image 1 with the same face,
                      curly dark hair, freckles, red hooded raincoat with wooden
                      toggles, navy trousers and yellow rubber boots. Use the
                      exact toy sailboat from image 2: teal wooden hull with a
                      white stripe, cream canvas sail with the stitched patch
                      and dark blue painted star, red string at the bow. Place
                      them on the misty loch shoreline from image 3. The boy
                      crouches on the flat rocks at the water's edge, seen in
                      three-quarter side view, gently setting the sailboat onto
                      the calm water with both hands while holding the red
                      string; small ripples spread around the hull. Keep the
                      pebbles, rust bracken hills and misty pines of the
                      location. Soft overcast morning light, consistent scale
                      and shadows, realistic reflections in the water, a quiet
                      tender moment, no text, no watermark.
                    image_urls:
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-01.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-02.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-03.png
                    size: 1920x4096
                    'n': 1
                    enable_safety_checker: true
              custom-object:
                summary: 自定义尺寸对象
                value:
                  model: bytedance/seedream/v4.5/edit
                  input:
                    prompt: >-
                      Combine the three reference images into one natural
                      photograph. Use the boy from image 1 with the same face,
                      curly dark hair, freckles, red hooded raincoat with wooden
                      toggles, navy trousers and yellow rubber boots. Use the
                      exact toy sailboat from image 2: teal wooden hull with a
                      white stripe, cream canvas sail with the stitched patch
                      and dark blue painted star, red string at the bow. Place
                      them on the misty loch shoreline from image 3. The boy
                      crouches on the flat rocks at the water's edge, seen in
                      three-quarter side view, gently setting the sailboat onto
                      the calm water with both hands while holding the red
                      string; small ripples spread around the hull. Keep the
                      pebbles, rust bracken hills and misty pines of the
                      location. Soft overcast morning light, consistent scale
                      and shadows, realistic reflections in the water, a quiet
                      tender moment, no text, no watermark.
                    image_urls:
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-01.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-02.png
                      - >-
                        https://cdn.vidgo.ai/apis/models/bytedance/seedream/v4.5/edit/v1/01/input-03.png
                    size:
                      width: 2304
                      height: 3072
                    'n': 1
                    enable_safety_checker: true
      responses:
        '200':
          description: 任务已提交
          content:
            application/json:
              schema:
                type: object
                required:
                  - code
                  - data
                properties:
                  code:
                    type: integer
                    enum:
                      - 200
                  data:
                    type: object
                    required:
                      - task_id
                      - status
                      - created_time
                    properties:
                      task_id:
                        type: string
                      status:
                        type: string
                        enum:
                          - not_started
                          - running
                          - finished
                          - failed
                      created_time:
                        type: string
                        format: date-time
              example:
                code: 200
                data:
                  task_id: GAPP1TYEWHR5CQVS
                  status: running
                  created_time: '2026-09-25T16:16:53'
        '400':
          description: 请求校验错误或账户余额不足
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '401':
          description: 认证错误
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '403':
          description: 拒绝访问
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '404':
          description: 模型未知或已停用
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '408':
          description: 请求超时
          content:
            text/plain:
              schema:
                type: string
              example: Request timeout
        '422':
          description: JSON 无效或请求体不是对象
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '429':
          description: 达到请求速率或账户限额
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '500':
          description: 服务器内部错误
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '502':
          description: 任务创建错误
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
        '503':
          description: 服务暂时不可用
          content:
            application/json:
              schema:
                type: object
                required:
                  - detail
                properties:
                  detail:
                    oneOf:
                      - type: string
                      - type: object
                        additionalProperties: true
                      - type: array
                        items: {}
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: 使用 VIDGO_API_KEY。

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.