创建 Seedream 5.5 任务

POST

images

curl --request POST \
  --url https://sigrunai.com/v1/images \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "Minimal product still life, white background, soft light",
  "quality": "medium",
  "n": 1,
  "ratio": "1:1"
}
'

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}

创建 Seedream 5.5 异步生图任务。成功后返回 task_id，请用查询图片任务轮询，完成后从 result.image_url 取图。 GPT Image 2 见创建 GPT Image 2 任务。GPT Image 2.6 见创建 GPT Image 2.6 任务。Nano Banana 系列见创建 Nano Banana 任务。Muse Image 见创建 Muse Image 任务。

模型

`model`	说明	`resolution`	计费键
`seedream-5.5`	文生 / 参考图；每次 1 张	`1K` / `2K`（也可用 `1k` / `2k`）	`seedream-5.5-1k` / `seedream-5.5-2k`

按分辨率对应的计费模型扣费（per_task，每次 1 张）。实际单价以模型目录与创建响应中的 cost 为准。也可直接传计费键作为 model。

请求参数

字段	类型	必填	说明
`model`	string	是	`seedream-5.5`，或 `seedream-5.5-1k` / `seedream-5.5-2k`
`prompt`	string	条件	文生图必填；有参考图时可为空。最长 4000 字符
`n`	int	否	固定 1
`ratio`	string	否	画面比例；也可用 `size`。可选：`1:1` / `16:9` / `9:16` / `4:3` / `3:4` / `3:2` / `2:3` / `21:9` / `5:4` / `4:5`
`size`	string	否	`ratio` 别名
`resolution`	string	否	分辨率档位，默认 `1K`
`images`	string[]	否	参考图公网 URL，最多 8 张
`smart_queue`	bool	否	默认 `false`。为 `true` 时，近期成功率过低会先保持 `queued`，恢复后再提交（最长约 2 小时）。详见智能排队

示例

文生图（1K）

curl -X POST 'https://sigrunai.com/v1/images' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "seedream-5.5",
    "prompt": "一只蓝色杯子放在木桌上，柔和的自然光",
    "ratio": "1:1",
    "resolution": "1K"
  }'

参考图（2K）

curl -X POST 'https://sigrunai.com/v1/images' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "seedream-5.5",
    "prompt": "保持产品外观，换成摄影棚柔光背景",
    "ratio": "16:9",
    "resolution": "2K",
    "images": ["https://example.com/reference.jpg"]
  }'

成功响应示例：

{
  "code": 20000,
  "msg": "提交成功",
  "data": {
    "task_id": "img_xxxxxxxx",
    "status": "queued",
    "progress": 0,
    "model": "seedream-5.5-1k",
    "cost": 0.05,
    "result": {}
  }
}

授权

Authorization

string

header

必填

控制台创建的 API Key，格式：Bearer sk_xxx

请求体

application/json

model

string

必填

gpt-image-2 (plus low/medium/high), gpt-image-2.6-flare / gpt-image-2.6-sunburst, nano-banana-2 / nano-banana-2.1 / nano-banana-pro, seedream-5.5, or muse-image

示例:

"nano-banana-2"

prompt

string

GPT Image 2 / Seedream 5.5 / Muse Image max 4000; GPT Image 2.6 max 32000; Nano Banana max 10000. Nano Banana / Seedream prompt is optional when images are provided. Muse Image prompt is always required

Required string length: 1 - 32000

quality

enum<string>

默认值:auto

GPT Image 2: auto / low / medium / high, billed by tier. GPT Image 2.6 also accepts xhigh / max without changing the price

可用选项:

auto,

low,

medium,

high,

xhigh,

max

integer

默认值:1

GPT Image 2 accepts 1–4. GPT Image 2.6, Nano Banana, Seedream 5.5, and Muse Image accept 1 only

必填范围: 1 <= x <= 4

ratio

string

size

string

Alias of ratio. GPT Image 2.6 accepts auto or an aspect ratio, not a pixel size. Muse Image reduces a pixel size such as 1024x1024 to its ratio

resolution

string

GPT Image 2.6 accepts 1k only. Nano Banana: 0.5k/1k/2k/4k depending on the model

images

string<uri>[]

Reference image URLs. GPT Image 2 max 15; GPT Image 2.6 max 16; Nano Banana max 5; Seedream 5.5 max 8; Muse Image max 10. GPT Image 2.6 svg and gif cannot include reference images

Maximum array length: 16

output_format

enum<string>

GPT Image 2.6 only. jpg is treated as jpeg. For gif, omit size or send auto

可用选项:

png,

jpeg,

webp,

svg,

gif

style

string

Muse Image only. Free-text style such as photorealistic, anime, or cinematic

Maximum string length: 1000

negative_prompt

string

Muse Image only. What should not appear, kept apart from prompt

Maximum string length: 1000

smart_queue

boolean

默认值:false

When true, a very low recent success rate keeps the task queued until recovery (up to about 2 hours)

响应

200 - application/json

提交成功

code

integer

示例:

20000

msg

string

data

object

Show child attributes

最后修改于 2026年11月14日

curl --request POST \
  --url https://sigrunai.com/v1/images \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-image-2",
  "prompt": "Minimal product still life, white background, soft light",
  "quality": "medium",
  "n": 1,
  "ratio": "1:1"
}
'

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}