编辑图像

在给定原图与提示词的情况下编辑或扩展图像。兼容 /v1/images/edits。

兼容 OpenAI Image Edits API。请求以 multipart/form-data 上传，base_url 设为 https://api.covanexus.com/v1。

POST /v1/images/edits https://api.covanexus.com

Authorization

Body

Authorization

Authorization BearerAuth

Authorization Bearer <token>

使用 Bearer Token 认证。格式：Authorization: Bearer $COVA_NEXUS_API_KEY

in: header

Request Body

multipart/form-data

image* file

待编辑的图像。需为.png 文件，小于 4MB 且为正方形

prompt* string

期望图像的文本描述，最长 1000 个字符

mask? file

遮罩.png，透明区域表示需要编辑的部位。尺寸须与 image 一致

model? string

用于图像编辑的模型

n? integer

生成图像数量，必须介于 1 到 10 之间

size? string

生成图像的大小：256x256、512x512 或 1024x1024

response_format? string

返回格式

Value in "url" | "b64_json"

user? string

用户标识

Response Body

状态码	类型
200	application/json

curl -X POST "https://api.covanexus.com/v1/images/edits" \
  -H "Authorization: Bearer $COVA_NEXUS_API_KEY" \
  -F image="@sunlit_lounge.png" \
  -F mask="@mask.png" \
  -F prompt="A sunlit indoor lounge area with a pool" \
  -F n=1 \
  -F size="1024x1024"

import fs from "fs";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "$COVA_NEXUS_API_KEY",
  baseURL: "https://api.covanexus.com/v1"
});

const response = await client.images.edit({
  image: fs.createReadStream("sunlit_lounge.png"),
  mask: fs.createReadStream("mask.png"),
  prompt: "A sunlit indoor lounge area with a pool",
  n: 1,
  size: "1024x1024"
});

from openai import OpenAI

client = OpenAI(
    api_key="$COVA_NEXUS_API_KEY",
    base_url="https://api.covanexus.com/v1"
)
response = client.images.edit(
    image=open("sunlit_lounge.png", "rb"),
    mask=open("mask.png", "rb"),
    prompt="A sunlit indoor lounge area with a pool",
    n=1,
    size="1024x1024"
)

200

{
  "created": 0,
  "data": [
    {
      "b64_json": "string",
      "url": "string"
    }
  ]
}

BearerAuth