AI 服务/图像生成

编辑图像

接口说明：同步编辑图像，基于参考图与指令进行编辑。

调用本接口前，请先请求「图像编辑模型」接口（GET /api/ai/models/image/edit），获取当前可用的模型列表及各模型支持的尺寸、最大输入图片数与价格，再据此填写本接口参数。

图像编辑为图生图：必须传入参考图片 image，按提示词在其基础上修改、重绘或风格化。如需仅用文字生成全新图像（文生图），请使用「生成图像」接口。

如已在使用 OpenAI SDK 或生态工具，可改用 OpenAI 兼容端点「OpenAI 图像编辑」。

POST

api

image

edit

编辑图像

curl --request POST \
  --url https://aitoearn.cn/api/ai/image/edit \
  --header 'Content-Type: application/json' \
  --header 'X-Api-Key: <api-key>' \
  --data '
{
  "model": "gpt-image-2",
  "image": "https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80",
  "prompt": "Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style."
}
'

import requests

url = "https://aitoearn.cn/api/ai/image/edit"

payload = {
    "model": "gpt-image-2",
    "image": "https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80",
    "prompt": "Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style."
}
headers = {
    "X-Api-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-Api-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-image-2',
    image: 'https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80',
    prompt: 'Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style.'
  })
};

fetch('https://aitoearn.cn/api/ai/image/edit', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://aitoearn.cn/api/ai/image/edit"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2\",\n  \"image\": \"https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80\",\n  \"prompt\": \"Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style.\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-Api-Key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{
  "code": 0,
  "message": "请求成功",
  "data": {
    "created": 1,
    "list": [
      {
        "url": "string",
        "b64_json": "string",
        "revised_prompt": "string"
      }
    ],
    "usage": {
      "input_tokens": 1,
      "output_tokens": 1,
      "total_tokens": 1
    },
    "background": "string",
    "output_format": "string",
    "quality": "string",
    "size": "string"
  }
}

授权

X-Api-Key

string

header

必填

需要从 AiToEarn 获取 API Key。点击前往「API Key 获取教程」。

请求体

application/json

model

string

必填

图像编辑模型名称。先调用「图像编辑模型」接口（GET /api/ai/models/image/edit），传入其返回的 data[n].name；各模型支持的尺寸、最大输入图片数与价格以该接口返回为准。

示例:

"gpt-image-2"

image

必填

原始图片。支持单个图片 URL、data URL 或图片 URL 数组；当前 gpt-image-2 最多支持 14 张输入图片。

示例:

"https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80"

prompt

string

必填

编辑描述

Required string length: 1 - 4000

示例:

"Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style."

mask

string

遮罩图片 URL，用于局部重绘（可选）。需为与 image 尺寸一致的 PNG 图片：完全透明（alpha 为 0）的区域表示需要按提示词重绘的部分，不透明区域保持原图不变。不传时对整张图片进行编辑。

integer

生成图片数量

必填范围: 1 <= x <= 1

示例:

1

size

string

图像尺寸。可选值随模型而不同，以「图像编辑模型」接口返回的 data[n].sizes 为准；不同尺寸的价格不同，见 data[n].pricing。当前示例使用 1024x1024，对应最低价格 1 积分。

示例:

"1024x1024"

response_format

enum<string>

返回格式

可用选项:

url,

b64_json

示例:

"url"

响应

200 - application/json

请求已被服务处理。业务是否成功以响应体 code === 0 为准。

code

integer

必填

业务状态码。0 表示成功，非 0 表示业务错误。

message

string

必填

响应消息。

data

object

Hide child attributes

data.created

number

必填

创建时间戳

data.list

object[]

必填

生成的图片列表

Hide child attributes

data.list.url

string

图片URL

data.list.b64_json

string

base64编码的图片

data.list.revised_prompt

string

修订后的提示词

data.usage

object

token使用情况

Hide child attributes

data.usage.input_tokens

number

输入token数

data.usage.output_tokens

number

输出token数

data.usage.total_tokens

number

总token数

data.background

string

背景

data.output_format

string

输出格式

data.quality

string

质量档位

data.size

string

图片尺寸

requestId

string

请求 ID。

timestamp

integer

错误响应时间戳，Unix 毫秒。

最后修改于 2026年9月29日

编辑图像

curl --request POST \
  --url https://aitoearn.cn/api/ai/image/edit \
  --header 'Content-Type: application/json' \
  --header 'X-Api-Key: <api-key>' \
  --data '
{
  "model": "gpt-image-2",
  "image": "https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80",
  "prompt": "Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style."
}
'

import requests

url = "https://aitoearn.cn/api/ai/image/edit"

payload = {
    "model": "gpt-image-2",
    "image": "https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80",
    "prompt": "Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style."
}
headers = {
    "X-Api-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-Api-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-image-2',
    image: 'https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80',
    prompt: 'Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style.'
  })
};

fetch('https://aitoearn.cn/api/ai/image/edit', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://aitoearn.cn/api/ai/image/edit"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2\",\n  \"image\": \"https://images.unsplash.com/photo-1592194996308-7b43878e84a6?auto=format&fit=crop&w=1024&q=80\",\n  \"prompt\": \"Edit the provided image into a cozy realistic scene by placing the cute orange cat beside a sunlit window. Preserve its orange fur, seated pose, and facial expression, enhance the soft natural light, add warm tones and subtle detail, and maintain a realistic photography style.\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-Api-Key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{
  "code": 0,
  "message": "请求成功",
  "data": {
    "created": 1,
    "list": [
      {
        "url": "string",
        "b64_json": "string",
        "revised_prompt": "string"
      }
    ],
    "usage": {
      "input_tokens": 1,
      "output_tokens": 1,
      "total_tokens": 1
    },
    "background": "string",
    "output_format": "string",
    "quality": "string",
    "size": "string"
  }
}