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-2.5",
"prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格",
"size": "1536x1024",
"quality": "medium",
"n": 1,
"response_format": "url"
}'
import requests
response = requests.post(
"https://xcompute.us/v1/images/generations",
headers={
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json",
},
json={
"model": "gpt-image-2.5",
"prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格",
"size": "1536x1024",
"quality": "medium",
"n": 1,
"response_format": "url",
},
timeout=300,
)
response.raise_for_status()
print(response.json()["data"][0]["url"])
{
"created": 1789097054,
"data": [
{
"url": "https://example.com/generated-image.png",
"revised_prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格"
}
]
}
图像生成
图像生成
使用 GPT Image 2.5 根据文字提示生成图片。
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-2.5",
"prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格",
"size": "1536x1024",
"quality": "medium",
"n": 1,
"response_format": "url"
}'
import requests
response = requests.post(
"https://xcompute.us/v1/images/generations",
headers={
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json",
},
json={
"model": "gpt-image-2.5",
"prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格",
"size": "1536x1024",
"quality": "medium",
"n": 1,
"response_format": "url",
},
timeout=300,
)
response.raise_for_status()
print(response.json()["data"][0]["url"])
{
"created": 1789097054,
"data": [
{
"url": "https://example.com/generated-image.png",
"revised_prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格"
}
]
}
使用
从
gpt-image-2.5 根据文字提示生成图片。同步接口会保持 HTTP 连接，直到生成完成并返回图片 URL；客户端超时建议设置为至少 300 秒。
请求
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-2.5",
"prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格",
"size": "1536x1024",
"quality": "medium",
"n": 1,
"response_format": "url"
}'
import requests
response = requests.post(
"https://xcompute.us/v1/images/generations",
headers={
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json",
},
json={
"model": "gpt-image-2.5",
"prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格",
"size": "1536x1024",
"quality": "medium",
"n": 1,
"response_format": "url",
},
timeout=300,
)
response.raise_for_status()
print(response.json()["data"][0]["url"])
参数
string
required
Bearer Token，例如
Authorization: Bearer YOUR_API_KEY。string
default:"application/json"
required
固定使用
application/json。string
default:"gpt-image-2.5"
required
固定填写
gpt-image-2.5。string
required
图片内容描述。建议说明主体、环境、构图、风格和需要避免的内容。
string
default:"auto"
图片质量，可选
auto、low、medium 或 high。integer
default:"1"
生成数量。具体上限以当前账户和模型配置为准。
string
default:"url"
返回格式。目前仅支持
url。支持尺寸
| 档位 | 支持的 size |
|---|---|
| 标准 | 1024x1024、1536x1024、1024x1536、1024x1365、1365x1024、1088x1920、1920x1088 |
| 高分辨率 | 2048x2048、1712x2560、2560x1712、2048x1536、1152x2048、2048x1152、2880x2880、2560x3840、3840x2560、3840x2880、2160x3840、3840x2160 |
成功响应
{
"created": 1789097054,
"data": [
{
"url": "https://example.com/generated-image.png",
"revised_prompt": "一只橘猫坐在窗台上看夕阳，水彩插画风格"
}
]
}
data[0].url 读取图片。返回的 URL 可能具有有效期，请及时下载并保存。