高级自动去水印/图片修复接口（V1）- 高级图像修复 API 文档

1.接口说明

高级自动去水印 / 图片修复 API：在无需手动绘制蒙版的情况下，对输入图片进行自动检测和修复，可用于去除水印、文字、马赛克、遮挡物、电商图违规词或其他损坏区域，输出修复完成后的图片。

1.1 主要功能

高级自动修复：: 自动检测需要清理的区域并填补缺损内容，生成自然连贯的纹理和背景。
同步/异步处理：: 支持 sync 同步返回结果，也支持 async_submit 提交任务后通过 async_fetch 轮询结果。
提示词控制：: 可通过 prompt 描述需要去除或修复的内容，例如水印、文字、遮挡物或电商图违规词。
任务状态查询：: 异步任务会返回 image_id，可用于查询 added、processing、done、error 等状态。

1.2 接入场景

商品图违规词清理、营销素材去水印、图片文字清理、老照片修复、图片瑕疵修补、内容编辑等。

2.请求信息

2.1 请求地址(URL)

POST http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1

2.2 请求方式

POST

2.3 请求头(header)

参数	类型	说明
Content-Type	string	application/json
APIKEY	string	您的 API KEY 获取

2.4 请求体(body)

参数	是否必填	类型	说明
mode	否	string	任务提交模式，`sync` 表示同步，`async_submit` 表示异步提交任务，默认为同步
image_base64	必填其中之一	string	base64 编码的图片文件，图片文件小于 20M
image_url	必填其中之一	string	图片文件 url，图片文件小于 20M
prompt	否	string	图片去水印/图片修复提示词
异步获取结果
mode	是	string	填 `async_fetch`
image_id	是	string	异步提交任务返回的 `image_id`

2.5 请求示例

// 同步请求
{
  "image_base64": "图片base64编码",
  "mode": "sync",
  "prompt": "去除图片中的水印和遮挡文字"
}

// 异步提交任务
{
  "image_url": "https://example.com/demo.jpg",
  "mode": "async_submit",
  "prompt": "去除图片中的水印"
}

// 异步获取结果
{
  "mode": "async_fetch",
  "image_id": "异步提交任务返回的image_id"
}

3.返回信息

3.1 返回类型

JSON

3.2 返回字段说明

参数	类型	说明
code	int	错误码
msg	string	错误信息（英文）
msg_cn	string	错误信息（中文）
image_id	string	图片id
同步模式
result_base64	string	结果的base64编码，当code==0时会有该返回值
异步模式
status	string	任务状态，`added`：已加入，`processing`：正在处理，`done`：处理完成，`error`：错误
wait_time	float	大概还需等待时间（秒）, ex: `12.3`
result_base64	string	结果的base64编码，当status为 `done` 时有该返回值

3.3 返回示例

// 同步成功示例
{
  "code": 0,
  "msg": "OK",
  "msg_cn": "成功",
  "image_id": "b6a0f7d0b2f54d0ea3...",
  "result_base64": "/9j/4AAQSkZJRgABAQAAAQABAAD..."
}

// 异步提交成功示例
{
  "code": 0,
  "msg": "OK",
  "msg_cn": "成功",
  "image_id": "b6a0f7d0b2f54d0ea3...",
  "status": "added",
  "wait_time": 12.3
}

// 异步获取结果成功示例
{
  "code": 0,
  "msg": "OK",
  "msg_cn": "成功",
  "image_id": "b6a0f7d0b2f54d0ea3...",
  "status": "done",
  "result_base64": "/9j/4AAQSkZJRgABAQAAAQABAAD..."
}

// 失败示例
{
  "code": 4,
  "msg": "Invalid parameter",
  "msg_cn": "参数错误"
}

3.4 错误码说明

错误码	说明
0	成功
1	图片错误
2	处理错误
3	服务器繁忙
4	参数错误，具体错误请查看 `msg` 或 `msg_cn`
5	未知错误
101	API-KEY 不正确
102	未知用户
103	积分已用完
104	扣除积分失败

4.示例代码

4.1 Python 示例

# -*- coding: utf-8 -*-
import requests
import base64
import cv2
import json
import numpy as np

api_key = '******'  # 你的API KEY
image_path = '...'  # 图片路径

"""
同步请求：mode 为 sync，直接返回 result_base64。
"""
with open(image_path, 'rb') as fp:
    image_base64 = base64.b64encode(fp.read()).decode('utf8')

url = 'http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1'
headers = {'APIKEY': api_key, "Content-Type": "application/json"}
data = {
    "image_base64": image_base64,
    "mode": "sync",
    "prompt": "去除图片中的水印和遮挡文字"
}

response = requests.post(url=url, headers=headers, json=data)
response = json.loads(response.content)
"""
成功：{'code': 0, 'msg': 'OK', 'msg_cn': '成功', 'result_base64': result_base64, 'image_id': image_id}
or
失败：{'code': error_code, 'msg': error_msg, 'msg_cn': 错误信息}
"""
image_id = response['image_id']
result_base64 = response['result_base64']
file_bytes = base64.b64decode(result_base64)
f = open('result.jpg', 'wb')
f.write(file_bytes)
f.close()

image = np.asarray(bytearray(file_bytes), dtype=np.uint8)
image = cv2.imdecode(image, cv2.IMREAD_UNCHANGED)
cv2.imshow('result', image)
cv2.waitKey(0)

"""
异步请求：先 async_submit 提交任务，再用 async_fetch 获取结果。
"""
submit_data = {
    "image_base64": image_base64,
    "mode": "async_submit",
    "prompt": "去除图片中的水印"
}
submit_resp = requests.post(url=url, headers=headers, json=submit_data)
submit_resp = json.loads(submit_resp.content)
image_id = submit_resp["image_id"]

fetch_data = {
    "mode": "async_fetch",
    "image_id": image_id
}
fetch_resp = requests.post(url=url, headers=headers, json=fetch_data)
fetch_resp = json.loads(fetch_resp.content)
print(fetch_resp)

4.2 PHP 示例

$url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1";
$method = "POST";
$apikey = "******";
$header = array();
array_push($header, "APIKEY:" . $apikey);
array_push($header, "Content-Type:application/json");

$image_path = "...";
$handle = fopen($image_path, "r");
$image = fread($handle, filesize($image_path));
fclose($handle);
$image_base64 = base64_encode($image);

$data = array(
  "image_base64"=> $image_base64,
  "mode"=> "sync",
  "prompt"=> "去除图片中的水印和遮挡文字"
);
$post_data = json_encode($data);

$curl = curl_init();
curl_setopt($curl, CURLOPT_CUSTOMREQUEST, $method);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
curl_setopt($curl, CURLOPT_POSTFIELDS, $post_data);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, false);

$response = curl_exec($curl);
var_dump($response);

4.3 Java

import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.nio.file.Files;
import java.util.Base64;
import org.json.JSONObject;

public class AutoInpaintApiExample {
    public static void main(String[] args) {
        String apiKey = "******";
        String filePath = "...";
        String apiUrl = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1";

        try {
            String imageBase64 = Base64.getEncoder().encodeToString(Files.readAllBytes(new File(filePath).toPath()));
            JSONObject requestData = new JSONObject();
            requestData.put("image_base64", imageBase64);
            requestData.put("mode", "sync");
            requestData.put("prompt", "去除图片中的水印和遮挡文字");

            JSONObject response = sendPost(apiUrl, apiKey, requestData);
            if (response.getInt("code") == 0) {
                byte[] resultBytes = Base64.getDecoder().decode(response.getString("result_base64"));
                Files.write(new File("result.jpg").toPath(), resultBytes);
                System.out.println("自动去水印成功，已保存 result.jpg");
            } else {
                System.out.println("请求失败: " + response.optString("msg_cn", response.optString("msg")));
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    private static JSONObject sendPost(String apiUrl, String apiKey, JSONObject body) throws Exception {
        HttpURLConnection conn = (HttpURLConnection) new URL(apiUrl).openConnection();
        conn.setRequestMethod("POST");
        conn.setRequestProperty("APIKEY", apiKey);
        conn.setRequestProperty("Content-Type", "application/json");
        conn.setDoOutput(true);
        try (OutputStream os = conn.getOutputStream()) {
            os.write(body.toString().getBytes("utf-8"));
        }
        StringBuilder sb = new StringBuilder();
        try (BufferedReader br = new BufferedReader(new InputStreamReader(conn.getInputStream(), "utf-8"))) {
            String line;
            while ((line = br.readLine()) != null) sb.append(line.trim());
        }
        return new JSONObject(sb.toString());
    }
}

4.4 JavaScript 示例

const fs = require('fs');

const apiKey = '******';
const imagePath = '...';
const apiUrl = 'http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1';

async function main() {
  const imageBase64 = fs.readFileSync(imagePath).toString('base64');

  let res = await fetch(apiUrl, {
    method: 'POST',
    headers: {
      APIKEY: apiKey,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      image_base64: imageBase64,
      mode: 'sync',
      prompt: '去除图片中的水印和遮挡文字'
    })
  });

  let data = await res.json();
  if (data.code !== 0) {
    console.error('请求失败:', data.msg_cn || data.msg);
    return;
  }

  fs.writeFileSync('result.jpg', Buffer.from(data.result_base64, 'base64'));
  console.log('自动去水印成功，已保存 result.jpg');

  res = await fetch(apiUrl, {
    method: 'POST',
    headers: {
      APIKEY: apiKey,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      mode: 'async_submit',
      image_base64: imageBase64,
      prompt: '去除图片中的水印'
    })
  });

  const submitData = await res.json();
  const fetchRes = await fetch(apiUrl, {
    method: 'POST',
    headers: {
      APIKEY: apiKey,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      mode: 'async_fetch',
      image_id: submitData.image_id
    })
  });
  const fetchData = await fetchRes.json();
  console.log('异步获取结果:', fetchData);
}

main().catch(console.error);

4.5 NodeJs

const request = require("request");
const fs = require("fs");

const apiKey = '******';
const imagePath = '...';
const apiUrl = 'http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1';

function post(body, callback) {
  request({
    method: "POST",
    url: apiUrl,
    headers: {
      APIKEY: apiKey,
      "Content-Type": "application/json",
    },
    body: JSON.stringify(body),
  }, callback);
}

function main() {
  const imageBase64 = fs.readFileSync(imagePath).toString('base64');

  post({
    image_base64: imageBase64,
    mode: "sync",
    prompt: "去除图片中的水印和遮挡文字"
  }, function (error, response, body) {
    if (error) {
      console.error(error);
      return;
    }
    let data = body;
    try {
      if (typeof body === 'string') data = JSON.parse(body);
    } catch (e) {}
    if (data.code !== 0) {
      console.error('请求失败:', data.msg_cn || data.msg);
      return;
    }

    fs.writeFileSync('result.jpg', Buffer.from(data.result_base64, 'base64'));
    console.log('自动去水印成功，已保存 result.jpg');

    post({
      image_base64: imageBase64,
      mode: "async_submit",
      prompt: "去除图片中的水印"
    }, function (error2, response2, body2) {
      if (error2) {
        console.error(error2);
        return;
      }
      let data2 = body2;
      try {
        if (typeof body2 === 'string') data2 = JSON.parse(body2);
      } catch (e) {}
      post({ mode: "async_fetch", image_id: data2.image_id }, function (error3, response3, body3) {
        if (error3) {
          console.error(error3);
          return;
        }
        let data3 = body3;
        try {
          if (typeof body3 === 'string') data3 = JSON.parse(body3);
        } catch (e) {}
        console.log('异步获取结果:', data3);
      });
    });
  });
}

main();

4.6 cURL

# 同步请求
curl -k 'http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1' \
  -H 'APIKEY: 你的APIKEY' \
  -H 'Content-Type: application/json' \
  -d '{"image_base64":"图片base64编码","mode":"sync","prompt":"去除图片中的水印和遮挡文字"}'

# 异步提交任务
curl -k 'http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1' \
  -H 'APIKEY: 你的APIKEY' \
  -H 'Content-Type: application/json' \
  -d '{"image_url":"https://example.com/demo.jpg","mode":"async_submit","prompt":"去除图片中的水印"}'

# 异步获取结果
curl -k 'http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1' \
  -H 'APIKEY: 你的APIKEY' \
  -H 'Content-Type: application/json' \
  -d '{"mode":"async_fetch","image_id":"异步提交任务返回的image_id"}'

4.7 C# 示例

using System;
using System.IO;
using System.Net.Http;
using System.Text;
using System.Text.Json;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        string apiKey = "******"; // 你的API KEY
        string filePath = "...";  // 图片路径
        string url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1";

        // 将图片编码为Base64
        string photoBase64;
        using (var imageStream = File.OpenRead(filePath))
        {
            byte[] imageBytes = new byte[imageStream.Length];
            await imageStream.ReadAsync(imageBytes, 0, (int)imageStream.Length);
            photoBase64 = Convert.ToBase64String(imageBytes);
        }

        // 构造请求数据
        var requestData = new
        {
            image_base64 = photoBase64
        };
        string jsonData = JsonSerializer.Serialize(requestData);

        using (HttpClient client = new HttpClient())
        {
            client.DefaultRequestHeaders.Add("APIKEY", apiKey);

            try
            {
                // 发送POST请求
                var response = await client.PostAsync(url, new StringContent(jsonData, Encoding.UTF8, "application/json"));
                string responseString = await response.Content.ReadAsStringAsync();

                // 解析响应
                var responseObject = JsonSerializer.Deserialize<JsonElement>(responseString);

                int code = responseObject.GetProperty("code").GetInt32();
                if (code == 0)
                {
                    string resultBase64 = responseObject.GetProperty("result_base64").GetString();
                    
                    // 将Base64转换为图片并保存
                    byte[] fileBytes = Convert.FromBase64String(resultBase64);
                    File.WriteAllBytes("result.jpg", fileBytes);
                    Console.WriteLine("Image processing succeeded, saved as result.jpg");
                }
                else
                {
                    string errorMsg = responseObject.GetProperty("msg_cn").GetString();
                    Console.WriteLine($"Error: {errorMsg}");
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine($"Exception: {ex.Message}");
            }
        }
    }
}

4.8 易语言

版本 2
.支持库 spec
.支持库 dp1

.子程序 图片_API_示例
.局部变量 局_网址, 文本型
.局部变量 局_方式, 整数型
.局部变量 局_提交数据, 文本型
.局部变量 局_提交协议头, 文本型
.局部变量 局_结果, 字节集
.局部变量 局_返回, 文本型
.局部变量 图片数据, 字节集
.局部变量 base64图片, 文本型

图片数据 ＝ 读入文件 ("你的图片路径.jpg")
base64图片 ＝ 编码_BASE64编码 (图片数据)
局_提交数据 ＝ "{" ＋ #引号 ＋ "image_base64" ＋ #引号 ＋ ":" ＋ #引号 ＋ base64图片 ＋ #引号 ＋ "}"
局_网址 ＝ "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1"
局_方式 ＝ 1
局_提交协议头 ＝ "APIKEY: 你的APIKEY" ＋ #换行符 ＋ "Content-Type: application/json"
局_结果 ＝ 网页_访问_对象 (局_网址, 局_方式, 局_提交数据, , , 局_提交协议头, , , , , , , , , , , , , )
局_返回 ＝ 到文本 (编码_编码转换对象 (局_结果, , , ))
返回 (局_返回)

4.9 天诺

public static string Api_Image64(Image image, string apiKey)
{
    string url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1";
    var headers = new Dictionary
    {
        {"Authorization", "APPCODE " + appcode},
        {"Content-Type", "application/json"}
    };
    string body = "{\"image_base64\":\"" + CustomHelp.ImageTobase64(image) + "\"}";
    return CustomHelp.HttpPost(url, body, headers);
}

4.10 按键精灵-电脑版

Import "Encrypt.dll"
VBSBegin
Function Base64Encode(filePath)
    Set inStream = CreateObject("ADODB.Stream")
    inStream.Type = 1
    inStream.Open
    inStream.LoadFromFile filePath
    inStream.Position = 0
    Set dom = CreateObject("MSXML2.DOMDocument")
    Set elem = dom.createElement("tmp")
    elem.dataType = "bin.base64"
    elem.nodeTypedValue = inStream.Read
    Base64Encode = elem.Text
    inStream.Close
End Function

Function api_image64(apiKey, imgPath)
    url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1"
    jsonBody = "{""image_base64"":""" & Base64Encode(imgPath) & """}"
    Set http = CreateObject("MSXML2.XMLHTTP")
    http.Open "POST", url, False
    http.setRequestHeader "APIKEY", apiKey
    http.setRequestHeader "Content-Type", "application/json"
    http.send jsonBody
    api_image64 = http.responseText
End Function
VBSEnd

apiKey = "你的APIKEY"
res = api_image64(apiKey, "你的图片路径.jpg")
TracePrint res

4.11 按键精灵-手机版

Import "yd.luae"
Import "zm.luae"

Dim imagePath = "/sdcard/Pictures/test.png"
SnapShotEx imagePath

Function api_image64(apiKey, imagePath)
    Dim url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1"
    Dim body = "{""image_base64"":""" & yd.Base64EncodeFile(imagePath) & """}"
    Dim headers = {null}
    headers["APIKEY"] = apiKey
    headers["Content-Type"] = "application/json"
    Dim res = yd.HttpPost(url, body, headers)
    api_image64 = yd.JsonDecode(res)
End Function

Dim apiKey = "你的APIKEY"
Dim res = api_image64(apiKey, imagePath)
TracePrint res["code"]

4.12 触动精灵

require("tsnet")
require "TSLib"
local ts = require("ts")
local json = ts.json

function readFileBase64(path)
    local f = io.open(path,"rb")
    if not f then return nil end
    local bytes = f:read("*all")
    f:close()
    return bytes:base64_encode()
end

function api_image64(apiKey, imagePath)
    local url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1"
    local body = json.encode({ image_base64 = readFileBase64(imagePath) })
    local headers = {}
    headers["APIKEY"] = apiKey
    headers["Content-Type"] = "application/json"
    local resp = httpPost(url, body, { headers = headers })
    return json.decode(resp)
end

4.13 懒人精灵

function api_image64(apiKey, imagePath)
    local url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1"
    local body = jsonLib.encode({ image_base64 = getFileBase64(imagePath) })
    local headers = {}
    headers["APIKEY"] = apiKey
    headers["Content-Type"] = "application/json"
    local resp = httpPost(url, body, { headers = headers })
    return jsonLib.decode(resp)
end

4.14 EasyClick

function main()
    local request = image.requestScreenCapture(10000, 0)
    if not request then
        request = image.requestScreenCapture(10000, 0)
    end
    local apiKey = "你的APIKEY"
    local img = image.captureFullScreenEx()
    console.time("t")
    local res = api_image64(apiKey, img)
    logd(console.timeEnd("t"))
    logd(res.code)
end

function api_image64(apiKey, img)
    local url = "http(s)://api.shiliuai.com/api/auto_inpaint_advanced/v1"
    local imgBase64 = image.toBase64Format(img, "jpg", 100)
    image.recycle(img)
    local body = JSON.stringify({ image_base64 = imgBase64 })
    local params = {
        url = url,
        method = "POST",
        headers = {
            ["APIKEY"] = apiKey,
            ["Content-Type"] = "application/json"
        },
        requestBody = body
    }
    local res = http.request(params)
    return JSON.parse(res.body)
end

高级自动去水印 / 图片修复接口

1.接口说明

1.1 主要功能

1.2 接入场景

2.请求信息

2.1 请求地址(URL)

2.2 请求方式

2.3 请求头(header)

2.4 请求体(body)

2.5 请求示例

3.返回信息

3.1 返回类型

3.2 返回字段说明

3.3 返回示例

3.4 错误码说明

4.示例代码

4.1 Python 示例

4.2 PHP 示例

4.3 Java

4.4 JavaScript 示例

4.5 NodeJs

4.6 cURL

4.7 C# 示例

4.8 易语言

4.9 天诺

4.10 按键精灵-电脑版

4.11 按键精灵-手机版

4.12 触动精灵

4.13 懒人精灵

4.14 EasyClick