Seedream 系列 - QWave API

POST

tasks

Seedream 系列

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "n": 123,
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "image_urls": [
    "<string>"
  ],
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ],
  "watermark": true,
  "optimize_prompt_options": "<string>",
  "sequential_image_generation": "<string>",
  "sequential_image_generation_options": {}
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "n": 123,
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "image_urls": ["<string>"],
    "callback_url": "<string>",
    "callback_events": ["<string>"],
    "watermark": True,
    "optimize_prompt_options": "<string>",
    "sequential_image_generation": "<string>",
    "sequential_image_generation_options": {}
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    n: 123,
    aspect_ratio: '<string>',
    resolution: '<string>',
    image_urls: ['<string>'],
    callback_url: '<string>',
    callback_events: ['<string>'],
    watermark: true,
    optimize_prompt_options: '<string>',
    sequential_image_generation: '<string>',
    sequential_image_generation_options: {}
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ],\n  \"watermark\": true,\n  \"optimize_prompt_options\": \"<string>\",\n  \"sequential_image_generation\": \"<string>\",\n  \"sequential_image_generation_options\": {}\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ],\n  \"watermark\": true,\n  \"optimize_prompt_options\": \"<string>\",\n  \"sequential_image_generation\": \"<string>\",\n  \"sequential_image_generation_options\": {}\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "doubao-seedream-5.0-lite",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

字节跳动 Seed 团队的图像生成模型系列。当前提供 doubao-seedream-5.0-lite 版本(4.0 / 4.5 因按 token 计费暂未接入)。 5.0 Lite — 视觉推理(CoT)+ 实时联网搜索,强身份保留(眼/下颌/比例/肤色跨风格不变),支持 1K/2K/4K 输出,性价比线。按张计费。

定价

模型	单价(每张)
`doubao-seedream-5.0-lite`	`$0.0315`

模式速查

模式	触发字段	action
文生图	仅 `prompt`	`generate`
图像编辑(局部重绘 / 光影修改)	`+ image_urls` + `action: "edit"`	`edit`
组图生成(主题相关一组)	`sequential_image_generation: "auto"`	`generate`

调用示例

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5.0-lite",
    "prompt": "未来主义城市夜景,霓虹灯映在湿润街面,电影感构图",
    "resolution": "2K",
    "aspect_ratio": "16:9"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5.0-lite",
    "action": "edit",
    "prompt": "把背景换成黄昏天空,人物保持不变",
    "image_urls": ["https://cdn.example.com/portrait.jpg"],
    "resolution": "2K"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5.0-lite",
    "action": "edit",
    "prompt": "把第一张图的角色放进第二张图的场景里",
    "image_urls": [
      "https://cdn.example.com/character.jpg",
      "https://cdn.example.com/scene.jpg"
    ],
    "resolution": "4K",
    "aspect_ratio": "16:9"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5.0-lite",
    "prompt": "电商主图四张:正面 / 侧面 / 细节 / 场景应用",
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": {"max_images": 4},
    "resolution": "4K",
    "aspect_ratio": "1:1"
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "doubao-seedream-5.0-lite",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

提交后用 GET /v1/tasks/{task_id} 轮询状态,详见任务系统。

可用模型

模型 ID	说明
`doubao-seedream-5.0-lite`	视觉推理 + 联网搜索,身份保留强,支持 1K/2K/4K,文生 / 编辑 / 组图统一接口

通用参数

model

string

必填

目前为 doubao-seedream-5.0-lite

action

string

默认值:"generate"

操作类型,可选值:

generate — 文生图(默认)
edit — 图像编辑 / 多图参考(需配合 image_urls)

prompt

string

必填

图像描述文本,支持中英文

integer

默认值:"1"

生成数量(单次返回多张)

aspect_ratio

string

默认值:"1:1"

画面宽高比,共 9 种:

1:1 — 正方形
4:3 / 3:4 — 横/竖版标准
16:9 / 9:16 — 横/竖版宽屏
3:2 / 2:3 — 横/竖版相机比
21:9 / 9:21 — 超宽屏 / 超长竖图

resolution

string

默认值:"2K"

输出分辨率,可选 1K / 2K / 4K

image_urls

string[]

参考图片 URL 数组,action: "edit" 时使用

callback_url

string

Webhook 回调地址,任务终态时调用。详见回调机制

callback_events

string[]

订阅的回调事件类型,详见回调机制

模型特定参数

watermark

boolean

默认值:"false"

是否加 AI 生成水印

optimize_prompt_options

string

默认值:"standard"

提示词优化模式,可选值:

standard — 标准优化(默认)
fast — 快速模式

sequential_image_generation

string

默认值:"disabled"

组图生成模式,可选值:

disabled — 单图(默认)
auto — 自动组图(主题相关多张)

sequential_image_generation_options

object

组图选项,如 {"max_images": 4}

资源限制

项目	限制
单张图片大小	≤ 30MB,支持 JPG/PNG/WEBP
输出分辨率	`1K` / `2K` / `4K`
输出文件	图片链接,24 小时有效

相关文档

任务系统详解 — 任务状态机 / 轮询节奏 / 异步推送
请求响应格式 — 通用错误码 / Headers / 限流
认证 — API Key 申请与使用

Imagen 4.0Google DeepMind 旗舰文生图 — 原生 2K 输出,写实质感,中英文字渲染准确

Seedream 系列

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "n": 123,
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "image_urls": [
    "<string>"
  ],
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ],
  "watermark": true,
  "optimize_prompt_options": "<string>",
  "sequential_image_generation": "<string>",
  "sequential_image_generation_options": {}
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "n": 123,
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "image_urls": ["<string>"],
    "callback_url": "<string>",
    "callback_events": ["<string>"],
    "watermark": True,
    "optimize_prompt_options": "<string>",
    "sequential_image_generation": "<string>",
    "sequential_image_generation_options": {}
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    n: 123,
    aspect_ratio: '<string>',
    resolution: '<string>',
    image_urls: ['<string>'],
    callback_url: '<string>',
    callback_events: ['<string>'],
    watermark: true,
    optimize_prompt_options: '<string>',
    sequential_image_generation: '<string>',
    sequential_image_generation_options: {}
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ],\n  \"watermark\": true,\n  \"optimize_prompt_options\": \"<string>\",\n  \"sequential_image_generation\": \"<string>\",\n  \"sequential_image_generation_options\": {}\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ],\n  \"watermark\": true,\n  \"optimize_prompt_options\": \"<string>\",\n  \"sequential_image_generation\": \"<string>\",\n  \"sequential_image_generation_options\": {}\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "doubao-seedream-5.0-lite",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

​定价

​模式速查

​调用示例

​可用模型

​通用参数

​模型特定参数

​资源限制

​相关文档

定价

模式速查

调用示例

可用模型

通用参数

模型特定参数

资源限制

相关文档