豆包图片生成 API

支持的模型

doubao-seedream-4-0-250828

基础版图片生成模型

doubao-seedream-4-5-251128

增强版图片生成模型

doubao-seedream-5-0-260128

最新图像创作模型,精准解析复杂指令

文生图

通过文本描述生成图片。

配置说明：

将 api.xxx.com 替换为您的实际 API 域名
将 sk-xxx 替换为您的 API 密钥（可在控制台获取）

curl -X POST https://api.xxx.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "doubao-seedream-4-0-250828",
    "prompt": "星际穿越,黑洞,黑洞里冲出一辆快支离破碎的复古列车,抢视觉冲击力,电影大片,末日既视感,动感,对比色,oc渲染,光线追踪,动态模糊,景深,超现实主义,深蓝,画面通过细腻的丰富的色彩层次塑造主体与场景,质感真实,暗黑风背景的光影效果营造出氛围,整体兼具艺术幻想感,夸张的广角透视效果,耀光,反射,极致的光影,强引力,吞噬",
    "size": "2K",
    "sequential_image_generation": "disabled",
    "stream": false,
    "response_format": "url",
    "watermark": false
  }'

import requests
import json

url = "https://api.xxx.com/v1/images/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer sk-xxx"
}

data = {
    "model": "doubao-seedream-4-0-250828",
    "prompt": "星际穿越,黑洞,黑洞里冲出一辆快支离破碎的复古列车,抢视觉冲击力,电影大片,末日既视感,动感,对比色,oc渲染,光线追踪,动态模糊,景深,超现实主义,深蓝,画面通过细腻的丰富的色彩层次塑造主体与场景,质感真实,暗黑风背景的光影效果营造出氛围,整体兼具艺术幻想感,夸张的广角透视效果,耀光,反射,极致的光影,强引力,吞噬",
    "size": "2K",
    "sequential_image_generation": "disabled",
    "stream": False,
    "response_format": "url",
    "watermark": False
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print(json.dumps(result, indent=2, ensure_ascii=False))

{
  "model": "doubao-seedream-4-0-250828",
  "created": 1765250822,
  "data": [
    {
      "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/...",
      "size": "3136x1344"
    }
  ],
  "usage": {
    "generated_images": 1,
    "output_tokens": 16464,
    "total_tokens": 16464
  }
}

参数说明

常用参数

参数名	类型	必填	说明	默认值/可选值
`model`	string	✅	模型名称	`doubao-seedream-4-0-250828`, `doubao-seedream-4-5-251128`, `doubao-seedream-5-0-260128`
`prompt`	string	✅	文本提示词	支持中英文,建议≤300汉字或600英文单词
`image`	string/array	❌	输入图片URL	图生图/多图融合时使用,支持URL或Base64
`size`	string	✅	图片尺寸	`2K`, `4K`, 或指定宽高如`2048x2048`
`sequential_image_generation`	string	❌	序列图片生成模式	`disabled`(关闭), `auto`(自动), 默认`disabled`
`sequential_image_generation_options`	object	❌	组图配置	`max_images`: 最多图片数(1-15), 默认15
`stream`	boolean	❌	是否流式返回	`true`, `false`, 默认`false`
`response_format`	string	❌	响应格式	`url`(链接), `b64_json`(Base64), 默认`url`
`watermark`	boolean	❌	是否添加水印	`true`, `false`, 默认`false`

宽高比	宽高像素值
1:1	2048x2048
4:3	2304x1728
3:4	1728x2304
16:9	2560x1440
9:16	1440x2560
3:2	2496x1664
2:3	1664x2496
21:9	3024x1296

图生图

基于输入图片生成新图片。

curl -X POST https://api.xxx.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "doubao-seedream-4-0-250828",
    "prompt": "生成狗狗趴在草地上的近景画面",
    "image": "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imageToimage.png",
    "size": "2K",
    "sequential_image_generation": "disabled",
    "stream": false,
    "response_format": "url",
    "watermark": false
  }'

import requests
import json

url = "https://api.xxx.com/v1/images/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer sk-xxx"
}

data = {
    "model": "doubao-seedream-4-0-250828",
    "prompt": "生成狗狗趴在草地上的近景画面",
    "image": "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imageToimage.png",
    "size": "2K",
    "sequential_image_generation": "disabled",
    "stream": False,
    "response_format": "url",
    "watermark": False
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print(json.dumps(result, indent=2, ensure_ascii=False))

{
  "model": "doubao-seedream-4-0-250828",
  "created": 1765250879,
  "data": [
    {
      "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/...",
      "size": "1696x2272"
    }
  ],
  "usage": {
    "generated_images": 1,
    "output_tokens": 15052,
    "total_tokens": 15052
  }
}

图生组图

基于输入图片生成一组连续的图片。

curl -X POST https://api.xxx.com/v1/images/generations \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-xxx" \
   -d '{
     "model": "doubao-seedream-4-0-250828",
     "prompt": "生成3张女孩和奶牛玩偶在游乐园开心地坐过山车的图片,涵盖早晨、中午、晚上",
     "image": ["https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimages_1.png", "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimages_2.png"],
     "sequential_image_generation": "auto",
     "sequential_image_generation_options": {
         "max_images": 3
     },
     "size": "2K"
   }'

import requests
import json

url = "https://api.xxx.com/v1/images/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer sk-xxx"
}

data = {
    "model": "doubao-seedream-4-0-250828",
    "prompt": "生成3张女孩和奶牛玩偶在游乐园开心地坐过山车的图片,涵盖早晨、中午、晚上",
    "image": [
        "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimages_1.png",
        "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimages_2.png"
    ],
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": {
        "max_images": 3
    },
    "size": "2K"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print(json.dumps(result, indent=2, ensure_ascii=False))

{
  "model": "doubao-seedream-4-0-250828",
  "created": 1765251003,
  "data": [
    {
      "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/..._0.jpeg",
      "size": "2848x1600"
    },
    {
      "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/..._1.jpeg",
      "size": "2848x1600"
    },
    {
      "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/..._2.jpeg",
      "size": "2848x1600"
    }
  ],
  "usage": {
    "generated_images": 3,
    "output_tokens": 53400,
    "total_tokens": 53400
  }
}

多图融合

融合多张图片的特征生成新图片。

curl -X POST https://api.xxx.com/v1/images/generations \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer sk-xxx" \
  -d '{
    "model": "doubao-seedream-4-0-250828",
    "prompt": "将图1的服装换为图2的服装",
    "image": ["https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_1.png", "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_2.png"],
    "sequential_image_generation": "disabled",
    "size": "2K"
  }'

import requests
import json

url = "https://api.xxx.com/v1/images/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer sk-xxx"
}

data = {
    "model": "doubao-seedream-4-0-250828",
    "prompt": "将图1的服装换为图2的服装",
    "image": [
        "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_1.png",
        "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_2.png"
    ],
    "sequential_image_generation": "disabled",
    "size": "2K"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()
print(json.dumps(result, indent=2, ensure_ascii=False))

返回的图片URL通常有24小时的有效期，请及时下载保存。

Getting Started

API 文档

ComfyUI 插件

OpenClaw 配置

支持的模型

doubao-seedream-4-0-250828

doubao-seedream-4-5-251128

doubao-seedream-5-0-260128

文生图

参数说明

常用参数

推荐宽高比

图生图

图生组图

多图融合

​支持的模型

doubao-seedream-4-0-250828

doubao-seedream-4-5-251128

doubao-seedream-5-0-260128

​文生图

​参数说明

​常用参数

​推荐宽高比

​图生图

​图生组图

​多图融合

支持的模型

文生图

参数说明

常用参数

推荐宽高比

图生图

图生组图

多图融合