Midjourney Imagine API 接入指南与实战

图像放大与变换

生成 2x2 预览图后，我们可以对特定区域进行微调。比如觉得右上角第二张不错，想进一步变换，可以将 action 设为 variation2，并传入上一步的 image_id。

若需精细化放大，选择第四张则传入 upscale4。注意，upscale 操作通常比 variation 耗时更短。

放大后的图片会提供新的 actions，例如 upscale_2x、zoom_out_2x（缩小）、pan_left/right/up/down（平移）等，支持连续迭代处理。

图像改写（垫图）

API 支持 Image Prompt，即输入一张图片 URL 加文字描述，基于原图风格进行改写。

注意：输入的图片 URL 必须是纯图片链接，建议使用图床。权重参数可通过 --iw 调整。

示例 Prompt 格式：

https://cdn.example.com/image.png an illustration of a car parked on the beach --iw2

将图片链接放在开头，空格分隔后接描述文字，整体传给 prompt 字段即可。

图像融合

支持多张图片融合，最多 5 张。将多个图片 URL 以空格分隔放在 Prompt 开头，最后跟上文字描述。

例如让熊拿着电锯：

https://img1.png https://img2.png The bear is holding the chainsaw --iw2

局部重绘 (Inpainting)

这是高阶用法，支持指定区域重绘。需要传入掩码（Mask）的 Base64 编码。

获取掩码

我们需要先绘制掩码，白色区域代表重绘范围。以下是一个简单的 Python 工具示例，用于生成灰度掩码：

import sys
import os
from PySide6.QtWidgets import *
from PySide6.QtGui import QPainter, QMouseEvent, QPen, QColor, QImage
from PySide6.QtCore import Qt, QPoint

class DrawingWidget(QWidget):
    def __init__(self, imagePath):
        super().__init__()
        self.setAttribute(Qt.WA_StaticContents)
        self.background_image = QImage(imagePath)
        imageSize = self.background_image.size() * 0.8
        self.setFixedSize(imageSize)
        self.foreground_image = QImage(self.size(), QImage.Format_ARGB32)
        self.foreground_image.fill(Qt.transparent)
        self.drawing = False
        self.lastPoint = QPoint()
        self.pen_color = QColor(255, 255, 255, 255)
        self.pen_size = 50

    def set_pen_size(self, size):
        self.pen_size = size

    def mousePressEvent(self, event: QMouseEvent):
        if event.button() == Qt.LeftButton:
            self.drawing = True
            self.lastPoint = event.pos()

    def mouseMoveEvent(self, event: QMouseEvent):
        if event.buttons() & Qt.LeftButton and self.drawing:
            painter = QPainter(self.foreground_image)
            painter.setRenderHint(QPainter.Antialiasing, True)
            pen = QPen(self.pen_color, self.pen_size, Qt.SolidLine, Qt.RoundCap, Qt.RoundJoin)
            painter.setPen(pen)
            painter.drawLine(self.lastPoint, event.pos())
            self.lastPoint = event.pos()
            self.update()

    def mouseReleaseEvent(self, event: QMouseEvent):
        if event.button() == Qt.LeftButton and self.drawing:
            self.drawing = False

    def paintEvent(self, event):
        canvasPainter = QPainter(self)
        canvasPainter.drawImage(self.rect(), self.background_image, self.background_image.rect())
        canvasPainter.drawImage(self.rect(), self.foreground_image, self.foreground_image.rect())

    def save_image(self, path):
        self.foreground_image.save(path)

class MainWindow(QDialog):
    def __init__(self, imagePath):
        super().__init__()
        self.setWindowTitle("mask tool")
        self.drawing_widget = DrawingWidget(imagePath)
        self.currentPath = os.getcwd().replace("\\", "/")
        self.tempPath = self.currentPath + "/temp.jpg"
        self.setDone = False

    def init_ui(self):
        layout = QVBoxLayout()
        layout.addWidget(self.drawing_widget)
        controls_layout = QHBoxLayout()
        size_label = QLabel("pen size:")
        controls_layout.addWidget(size_label)
        self.size_slider = QSlider(Qt.Horizontal)
        self.size_slider.setMinimum(100)
        self.size_slider.setMaximum(400)
        self.size_slider.setValue(400)
        self.size_slider.valueChanged.connect(self.update_pen_size)
        controls_layout.addWidget(self.size_slider)
        self.lineEdit_addPromp = QLineEdit()
        layout.addWidget(self.lineEdit_addPromp)
        save_button = QPushButton("Start partial redrawing")
        save_button.clicked.connect(self.save_image)
        controls_layout.addWidget(save_button)
        dont_button = QPushButton("Cancel partial redraw")
        dont_button.clicked.connect(lambda: setattr(self, 'setDone', False))
        controls_layout.addWidget(dont_button)
        layout.addLayout(controls_layout)
        self.setLayout(layout)

    def update_pen_size(self):
        size = self.size_slider.value()
        self.drawing_widget.set_pen_size(size)

    def closeEvent(self, event):
        if not self.setDone:
            self.setDone = False
        event.accept()

if __name__ == '__main__':
    app = QApplication(sys.argv)
    mainWindow = MainWindow("test.png")
    mainWindow.init_ui()
    mainWindow.exec()

获得掩码图片后，需将其转换为 Base64 编码：

import cv2
import base64

image_path = 'temp.jpg'
gray_image = cv2.imread(image_path)
_, buffer = cv2.imencode('.jpg', gray_image)
base64_encoded = base64.b64encode(buffer).decode('utf-8')
with open('grayscale_image_base64.txt', 'w') as f:
    f.write(base64_encoded)
print("success!")

调用局部重绘

设置 action 为 variation_region，传入 image_id 和 mask（Base64 字符串）：

{
  "prompt": "A cute cat",
  "action": "variation_region",
  "image_id": "1265875488702726144",
  "mask": "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..."
}

异步回调

由于生图耗时较长，API 支持 Webhook 回调。设置 callback_url 后，当任务完成时，服务器会收到 HTTP 请求。

如果生成成功，回调体包含 success: true 及图片信息；失败则包含 error.code 和 error.message。这有助于避免长轮询带来的资源浪费。

流式输出

为了提升用户体验，API 支持流式返回。只需将请求头 accept 设置为 application/x-ndjson，并在代码中开启流式读取。

Python 示例：

import requests
url = 'https://api.acedata.cloud/midjourney/imagine'
headers = {
    'content-type': 'application/json',
    'accept': 'application/x-ndjson',
    'authorization': 'Bearer {token}'
}
body = {"prompt": "a beautiful cat --v 6"}
r = requests.post(url, headers=headers, json=body, stream=True)
for line in r.iter_lines():
    print(line.decode())

Node.js 示例：

const axios = require("axios");
const url = "https://api.acedata.cloud/midjourney/imagine";
const headers = {
    "content-type": "application/json",
    "accept": "application/x-ndjson",
    "authorization": "Bearer {token}"
};
const body = {
    prompt: "a beautiful cat --v 6",
    action: "generate"
};

axios.post(url, body, { headers: headers, responseType: "stream" })
    .then((response) => {
        console.log(response.status);
        response.data.on("data", (chunk) => {
            console.log(chunk.toString());
        });
    })
    .catch((error) => {
        console.error(error);
    });

流式输出中包含 progress 字段（0-100），可用于前端进度条展示。注意未完全完成时 actions 为空，无法进行后续操作。