stable-diffusion(OpenAI图像格式)

POST

/chat/completions

image_size Available options: 1024x1024, 512x1024, 768x512, 768x1024, 1024x576, 576x1024
batch_size Required range: 1 < x < 4
num_inference_steps Required range: 1 < x < 100
guidance_scale Required range: 0 < x < 100
seed Required range: 0 < x < 9999999999

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Authorization

string

可选

示例值:

Bearer {{YOUR_API_KEY}}

Body 参数application/json

prompt

string

必需

所需图像的文本描述。最大长度为 1000 个字符。

integer

可选

要生成的图像数。必须介于 1 和 10 之间。

size

string

可选

生成图像的大小。必须是256x256、512x512或 1024x1024之一。

示例

{
    "model": "stable-diffusion-api",
    "messages": [
        {
            "role": "user",
            "content": "striking poses, stunning backdrop of rocky coastline and golden hour lighting, fashion-forward wardrobe, eye-catching accessories, warm and inviting color palette, sharp and detailed digital rendering, stunning high definition finish, on eye level, scenic, masterpiece"
        }
    ]
}

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://smallaapi.1273656643.workers.dev/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "stable-diffusion-api",
    "messages": [
        {
            "role": "user",
            "content": "striking poses, stunning backdrop of rocky coastline and golden hour lighting, fashion-forward wardrobe, eye-catching accessories, warm and inviting color palette, sharp and detailed digital rendering, stunning high definition finish, on eye level, scenic, masterpiece"
        }
    ]
}'

返回响应

🟢200Create image

application/json

Body

created

integer

必需

data

array [object {1}]

必需

url

string

必需

示例

{
    "created": 1589478378,
    "data": [
        {
            "url": "https://..."
        },
        {
            "url": "https://..."
        }
    ]
}

修改于 2025-06-09 18:15:13

gpt-4-all（生成图片）

GPTs对话