Seedream-5.0-Pro 图像生成

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 1,
    "metadata": {
      "resolution": "2K"
    }
  }'

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 1,
    "image_urls": [
      "https://example.com/panda.jpg"
    ],
    "metadata": {
      "resolution": "1K"
    }
  }'

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 4,
    "metadata": {
      "resolution": "2K",
      "sequential_image_generation": "auto",
      "sequential_image_generation_options": { "max_images": 4 },
      "watermark": false
    }
  }'

import requests

response = requests.post(
    "https://toapis.com/v1/images/generations",
    headers={
        "Authorization": "Bearer your-ToAPIs-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedream-5-0-pro",
        "prompt": "可爱的熊猫在竹林中玩耍",
        "size": "1:1",
        "n": 1,
        "metadata": {
            "resolution": "2K"
        }
    }
)

task = response.json()
print(f"任务 ID: {task['id']}")
print(f"状态: {task['status']}")

import requests

response = requests.post(
    "https://toapis.com/v1/images/generations",
    headers={
        "Authorization": "Bearer your-ToAPIs-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedream-5-0-pro",
        "prompt": "可爱的熊猫在竹林中玩耍",
        "size": "1:1",
        "n": 1,
        "image_urls": ["https://example.com/panda.jpg"],
        "metadata": {
            "resolution": "1K"
        }
    }
)

task = response.json()
print(f"任务 ID: {task['id']}")
print(f"状态: {task['status']}")

const response = await fetch('https://toapis.com/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-ToAPIs-key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'doubao-seedream-5-0-pro',
    prompt: '可爱的熊猫在竹林中玩耍',
    size: '1:1',
    n: 1,
    metadata: {
      resolution: '2K'
    }
  })
});

const task = await response.json();
console.log(`任务 ID: ${task.id}`);
console.log(`状态: ${task.status}`);

const response = await fetch('https://toapis.com/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-ToAPIs-key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'doubao-seedream-5-0-pro',
    prompt: '可爱的熊猫在竹林中玩耍',
    size: '1:1',
    n: 1,
    image_urls: ['https://example.com/panda.jpg'],
    metadata: {
      resolution: '1K'
    }
  })
});

const task = await response.json();
console.log(`任务 ID: ${task.id}`);
console.log(`状态: ${task.status}`);

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "doubao-seedream-5-0-pro",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}

POST

images

generations

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 1,
    "metadata": {
      "resolution": "2K"
    }
  }'

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 1,
    "image_urls": [
      "https://example.com/panda.jpg"
    ],
    "metadata": {
      "resolution": "1K"
    }
  }'

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 4,
    "metadata": {
      "resolution": "2K",
      "sequential_image_generation": "auto",
      "sequential_image_generation_options": { "max_images": 4 },
      "watermark": false
    }
  }'

import requests

response = requests.post(
    "https://toapis.com/v1/images/generations",
    headers={
        "Authorization": "Bearer your-ToAPIs-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedream-5-0-pro",
        "prompt": "可爱的熊猫在竹林中玩耍",
        "size": "1:1",
        "n": 1,
        "metadata": {
            "resolution": "2K"
        }
    }
)

task = response.json()
print(f"任务 ID: {task['id']}")
print(f"状态: {task['status']}")

import requests

response = requests.post(
    "https://toapis.com/v1/images/generations",
    headers={
        "Authorization": "Bearer your-ToAPIs-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedream-5-0-pro",
        "prompt": "可爱的熊猫在竹林中玩耍",
        "size": "1:1",
        "n": 1,
        "image_urls": ["https://example.com/panda.jpg"],
        "metadata": {
            "resolution": "1K"
        }
    }
)

task = response.json()
print(f"任务 ID: {task['id']}")
print(f"状态: {task['status']}")

const response = await fetch('https://toapis.com/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-ToAPIs-key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'doubao-seedream-5-0-pro',
    prompt: '可爱的熊猫在竹林中玩耍',
    size: '1:1',
    n: 1,
    metadata: {
      resolution: '2K'
    }
  })
});

const task = await response.json();
console.log(`任务 ID: ${task.id}`);
console.log(`状态: ${task.status}`);

const response = await fetch('https://toapis.com/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-ToAPIs-key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'doubao-seedream-5-0-pro',
    prompt: '可爱的熊猫在竹林中玩耍',
    size: '1:1',
    n: 1,
    image_urls: ['https://example.com/panda.jpg'],
    metadata: {
      resolution: '1K'
    }
  })
});

const task = await response.json();
console.log(`任务 ID: ${task.id}`);
console.log(`状态: ${task.status}`);

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "doubao-seedream-5-0-pro",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}

Seedream 5.0 Pro 高质量图像生成模型，由字节跳动 Seed 团队研发
通过 model 参数选择 doubao-seedream-5-0-pro 模型
参数与 Seedream-5.0 基本一致，区别在于 Pro 支持 1K 和 2K 分辨率
支持文生图、图生图、多图参考等生成模式
计费规则：首张参考图免费，从第 2 张参考图开始按正常规则计费
异步任务管理，通过任务 ID 查询结果

重要变更：为了更好的性能和成本控制，我们不再支持在 image_urls 中直接传入 base64 图片数据。请先使用上传图片接口上传图片，获取 URL 后再调用本接口。

Authorizations

Authorization

string

必填

所有接口均需要使用 Bearer Token 进行认证获取 API Key：访问 API Key 管理页面获取您的 API Key使用时在请求头中添加：

Authorization: Bearer YOUR_API_KEY

Body

model

string

默认值:"doubao-seedream-5-0-pro"

必填

图像生成模型名称示例："doubao-seedream-5-0-pro"

prompt

string

必填

图像生成的文本描述

size

string

默认值:"1:1"

图像宽高比支持的宽高比：

1:1 - 正方形（默认）
4:3 - 横向 4:3
3:4 - 竖向 3:4
16:9 - 横向宽屏
9:16 - 竖向长图
3:2 - 横向 3:2
2:3 - 竖向 2:3
21:9 - 超宽屏
9:21 - 超窄屏

integer

默认值:1

生成图像的数量范围：1-10（最少 1 张，最多 10 张）默认：1注意：

参考图像 + 生成图像总数必须 ≤ 15
必须输入纯数字（如 1），不要加引号，否则会报错

会根据生成数量和参考图数量进行预扣费，其中首张参考图免费

image_urls

string[]

参考图像 URL 列表，用于图生图或图像编辑⚠️ 仅支持 URL 格式（不再支持 base64）

公开可访问的图像 URL（http:// 或 https://）
可使用上传图片接口上传本地图片获取 URL

限制：

图片数量：1-10 张
图像格式：jpeg, png
宽高比（宽/高）范围：[1/3, 3]
宽度和高度（px）> 14
大小：不超过 10MB
总像素：不超过 6000×6000 px

计费说明：

首张参考图免费
从第 2 张参考图开始按正常规则计费

metadata

object

渠道特有参数，用于传递 Seedream 5.0 Pro 模型的高级配置

显示 metadata 属性

metadata.resolution

string

默认值:"2K"

图像分辨率支持的分辨率：

1K - 基础分辨率
2K - 标准分辨率（默认）

注意： Seedream 5.0 Pro 不支持 3K 和 4K 分辨率；非 Pro 的 Seedream 5.0 支持 2K 和 3K

metadata.sequential_image_generation

string

默认值:"disabled"

顺序图像生成模式（豆包专属功能）控制是否生成多张图像：

disabled：禁用顺序模式，即使有多张参考图像也只生成 1 张（默认）
auto：启用顺序模式，可以生成多张图像

使用说明：

✅ 设置 n: 3 或使用 sequential_image_generation: "auto" + max_images: 3
✅ 支持文生组图：仅提供文本提示词，最多生成 10 张图像
✅ 支持图生图/图生组图：提供 image_urls，基于参考图像生成多张图像
⚠️ 当 n > 1 时，会自动设置为 auto

注意：

输入的参考图数量 + 最终生成图片数量 ≤ 15 张

metadata.sequential_image_generation_options

object

顺序图像生成选项当 sequential_image_generation 设置为 auto 时可用属性：

max_images（整数）：指定生成的图像数量，范围：1-10

示例：

"sequential_image_generation_options": { "max_images": 3 }

metadata.watermark

boolean

默认值:false

是否为生成的图像添加水印

true：添加水印
false：不添加水印（默认）

Response

string

任务唯一标识符，用于查询任务状态

object

string

对象类型，固定为 generation.task

model

string

使用的模型名称

status

string

任务状态

queued - 排队等待处理
in_progress - 处理中
completed - 成功完成
failed - 失败

progress

integer

任务进度百分比（0-100）

created_at

integer

任务创建时间戳（Unix 时间戳）

metadata

object

任务元数据

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 1,
    "metadata": {
      "resolution": "2K"
    }
  }'

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 1,
    "image_urls": [
      "https://example.com/panda.jpg"
    ],
    "metadata": {
      "resolution": "1K"
    }
  }'

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "可爱的熊猫在竹林中玩耍",
    "size": "1:1",
    "n": 4,
    "metadata": {
      "resolution": "2K",
      "sequential_image_generation": "auto",
      "sequential_image_generation_options": { "max_images": 4 },
      "watermark": false
    }
  }'

import requests

response = requests.post(
    "https://toapis.com/v1/images/generations",
    headers={
        "Authorization": "Bearer your-ToAPIs-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedream-5-0-pro",
        "prompt": "可爱的熊猫在竹林中玩耍",
        "size": "1:1",
        "n": 1,
        "metadata": {
            "resolution": "2K"
        }
    }
)

task = response.json()
print(f"任务 ID: {task['id']}")
print(f"状态: {task['status']}")

import requests

response = requests.post(
    "https://toapis.com/v1/images/generations",
    headers={
        "Authorization": "Bearer your-ToAPIs-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "doubao-seedream-5-0-pro",
        "prompt": "可爱的熊猫在竹林中玩耍",
        "size": "1:1",
        "n": 1,
        "image_urls": ["https://example.com/panda.jpg"],
        "metadata": {
            "resolution": "1K"
        }
    }
)

task = response.json()
print(f"任务 ID: {task['id']}")
print(f"状态: {task['status']}")

const response = await fetch('https://toapis.com/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-ToAPIs-key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'doubao-seedream-5-0-pro',
    prompt: '可爱的熊猫在竹林中玩耍',
    size: '1:1',
    n: 1,
    metadata: {
      resolution: '2K'
    }
  })
});

const task = await response.json();
console.log(`任务 ID: ${task.id}`);
console.log(`状态: ${task.status}`);

const response = await fetch('https://toapis.com/v1/images/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer your-ToAPIs-key',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'doubao-seedream-5-0-pro',
    prompt: '可爱的熊猫在竹林中玩耍',
    size: '1:1',
    n: 1,
    image_urls: ['https://example.com/panda.jpg'],
    metadata: {
      resolution: '1K'
    }
  })
});

const task = await response.json();
console.log(`任务 ID: ${task.id}`);
console.log(`状态: ${task.status}`);

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "doubao-seedream-5-0-pro",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}

Seedream-5.0 Flux Kontext

概览

快速上手

文本对话系列

图像系列

视频系列

任务管理

文件上传

账户

常见问题

Authorizations

Body

Response

​Authorizations

​Body

​Response

Authorizations

Body

Response