gpt-image-2 API

本文介绍 gpt-image-2 模型调用 API 的输入输出参数，供您使用接口时查阅字段含义。

请求参数

请求体

响应参数

示例

OPENAI 兼容接口

POST https://api.modelverse.cn/v1/images/generations

同步请求

curl

curl --location 'https://api.modelverse.cn/v1/images/generations' \
  --header "Authorization: Bearer $MODELVAULTS_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-image-2",
    "prompt": "a beautiful flower",
    "size": "1024x1024",
    "quality": "high",
    "output_format": "png",
    "output_compression": 100
  }'

python

import os, base64
from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.modelverse.cn/v1",
    api_key=os.getenv("MODELVAULTS_API_KEY", "YOUR_API_KEY")
)
 
res = client.images.generate(
    model="gpt-image-2",
    prompt="a beautiful flower",
    size="1024x1024",
    quality="high",
)
 
# gpt-image-2 返回 base64 数据
image_b64 = res.data[0].b64_json
raw = image_b64.split(",")[-1] if image_b64.startswith("data:") else image_b64
with open("image.png", "wb") as f:
    f.write(base64.b64decode(raw))
print("Saved to image.png")

图片编辑

POST https://api.modelverse.cn/v1/images/edits

gpt-image-2 支持局部编辑功能，能够针对特定区域进行修改，同时保持其他区域的构图、色调和人物外观一致，避免整体重绘。

使用 multipart/form-data 传参，至少包含待编辑图片 image（可选 mask）、以及 model、prompt 等字段；其余参数如 size、quality、output_format、output_compression 与生成接口一致。

curl

curl --location 'https://api.modelverse.cn/v1/images/edits' \
  --header "Authorization: Bearer $MODELVAULTS_API_KEY" \
  -F "image=@/path/to/your/image.png" \
  -F "mask=@/path/to/your/mask.png" \
  -F "model=gpt-image-2" \
  -F "prompt=Add a beach ball in the center" \
  -F "size=1024x1024" \
  -F "n=1" \
  -F "quality=low" \
  -F "output_format=png" \
  -F "output_compression=100"

python

import os, base64, requests
 
url = "https://api.modelverse.cn/v1/images/edits"
headers = {"Authorization": f"Bearer {os.getenv('MODELVAULTS_API_KEY', '$MODELVAULTS_API_KEY')}"}
 
files = {
    "image": ("beach.png", open("beach.png", "rb"), "image/png"),
    # 可选：提供 mask 来限定编辑区域
    # "mask": ("mask.png", open("mask.png", "rb"), "image/png"),
}
 
data = {
    "model": "gpt-image-2",
    "prompt": "Add a beach ball in the center",
    "size": "1024x1024",
    "n": "1",
    "quality": "high",
    "output_format": "png",
    "output_compression": "100",
}
 
r = requests.post(url, headers=headers, files=files, data=data)
r.raise_for_status()
resp = r.json()
 
image_b64 = resp["data"][0]["b64_json"]
raw = image_b64.split(",")[-1] if image_b64.startswith("data:") else image_b64
with open("edit.png", "wb") as f:
    f.write(base64.b64decode(raw))
print("Saved to edit.png")

响应

{
  "created": 1750667997,
  "data":
  [
    {
      "b64_json": "{image_base64_string}"
    }
  ],
  "usage":
  {
    "total_tokens": 4169,
    "input_tokens": 9,
    "output_tokens": 4160,
    "input_tokens_details":
    {
      "text_tokens": 9
    }
  }
}

{
  "error": {
    "message": "error_message",
    "type": "error_type",
    "param": "request_id",
    "code": "error_code"
  }
}