curl --request POST \
--url https://xcompute.us/v1/images/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-image-2",
"prompt": "一只橘猫坐在窗台上看夕阳,水彩画风格",
"n": 1,
"size": "1024x1024"
}'
import requests
response = requests.post(
"https://xcompute.us/v1/images/generations",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "gpt-image-2",
"prompt": "一只橘猫坐在窗台上看夕阳,水彩画风格",
"n": 1,
"size": "1024x1024",
},
timeout=300,
)
response.raise_for_status()
print(response.json())
const response = await fetch('https://xcompute.us/v1/images/generations', {
method: 'POST',
headers: {
Authorization: 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'gpt-image-2',
prompt: '一只橘猫坐在窗台上看夕阳,水彩画风格',
n: 1,
size: '1024x1024',
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());
{
"created": 1784039704,
"data": [
{
"b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
}
]
}
{
"created": 1784039704,
"data": [
{
"url": "https://example.com/generated-image.png"
}
]
}
{
"error": {
"message": "prompt is required",
"type": "invalid_request_error"
}
}
图像生成与编辑
图像生成
使用 GPT Image 2 根据文本提示词生成图片
POST
https://xcompute.us
/
v1
/
images
/
generations
curl --request POST \
--url https://xcompute.us/v1/images/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-image-2",
"prompt": "一只橘猫坐在窗台上看夕阳,水彩画风格",
"n": 1,
"size": "1024x1024"
}'
import requests
response = requests.post(
"https://xcompute.us/v1/images/generations",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "gpt-image-2",
"prompt": "一只橘猫坐在窗台上看夕阳,水彩画风格",
"n": 1,
"size": "1024x1024",
},
timeout=300,
)
response.raise_for_status()
print(response.json())
const response = await fetch('https://xcompute.us/v1/images/generations', {
method: 'POST',
headers: {
Authorization: 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'gpt-image-2',
prompt: '一只橘猫坐在窗台上看夕阳,水彩画风格',
n: 1,
size: '1024x1024',
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());
{
"created": 1784039704,
"data": [
{
"b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
}
]
}
{
"created": 1784039704,
"data": [
{
"url": "https://example.com/generated-image.png"
}
]
}
{
"error": {
"message": "prompt is required",
"type": "invalid_request_error"
}
}
使用
需要基于参考图像生成内容时,请使用图像编辑接口。
gpt-image-2 根据文本提示词生成图片。接口兼容 OpenAI Images API,并在图片生成完成后同步返回结果。
图片生成通常需要几十秒到数分钟。建议将客户端请求超时时间设置为至少
300 秒。请求示例
curl --request POST \
--url https://xcompute.us/v1/images/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-image-2",
"prompt": "一只橘猫坐在窗台上看夕阳,水彩画风格",
"n": 1,
"size": "1024x1024"
}'
import requests
response = requests.post(
"https://xcompute.us/v1/images/generations",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "gpt-image-2",
"prompt": "一只橘猫坐在窗台上看夕阳,水彩画风格",
"n": 1,
"size": "1024x1024",
},
timeout=300,
)
response.raise_for_status()
print(response.json())
const response = await fetch('https://xcompute.us/v1/images/generations', {
method: 'POST',
headers: {
Authorization: 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'gpt-image-2',
prompt: '一只橘猫坐在窗台上看夕阳,水彩画风格',
n: 1,
size: '1024x1024',
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());
请求参数
string
required
Bearer API Key,例如
Bearer sk-xxxxxxxx。string
default:"gpt-image-2"
required
固定填写
gpt-image-2。string
required
图片生成提示词。支持中文和英文。
integer
default:"1"
生成图片数量。建议使用
1;实际可用范围取决于当前渠道。string
default:"1024x1024"
输出尺寸,例如
1024x1024。实际支持的尺寸取决于当前渠道。string
图片质量,例如
auto、standard、high。该参数可能因渠道不同而被忽略。string
期望的返回格式,可传
url 或 b64_json。客户端应同时兼容这两种实际返回形式。成功响应
图片通常通过b64_json 或 url 返回。
{
"created": 1784039704,
"data": [
{
"b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
}
]
}
{
"created": 1784039704,
"data": [
{
"url": "https://example.com/generated-image.png"
}
]
}
{
"error": {
"message": "prompt is required",
"type": "invalid_request_error"
}
}
保存 Base64 图片
jq -r '.data[0].b64_json' response.json | base64 --decode > result.png
⌘I