深度解析 Gemini 2.5 Flash Image Preview：API Key 获取、核心能力与多模态调用实践

import os
import google.generativeai as genai
from PIL import Image
from io import BytesIO

# 填入在“uiuiapi.com”获取的秘钥
# SDK 会自动从环境变量 `GEMINI_API_KEY` 读取密钥
genai.configure(api_key=os.environ["GEMINI_API_KEY"])

# 初始化模型
model = genai.GenerativeModel('gemini-2.5-flash-image-preview')

# 编写一个有趣的提示
prompt = "一张关于'纳米香蕉'菜肴的照片，在一家以Gemini为主题的高档餐厅里，照片风格要非常逼真。"

print("正在生成图像，请稍候...")
# 生成内容
response = model.generate_content(prompt)

# 健壮地处理响应并保存图像
try:
    # 假设响应中只有一个图像部分
    image_part = response.parts[0]
    image_data = image_part.inline_data.data
    image = Image.open(BytesIO(image_data))
    image.save("generated_image.png")
    print("图像已成功保存为 generated_image.png")
except (IndexError, AttributeError) as e:
    print(f"解析图像失败: {e}")
    print(f"完整响应内容: {response.text}")

import os
import google.generativeai as genai
from PIL import Image
from io import BytesIO

genai.configure(api_key=os.environ["GEMINI_API_KEY"])
model = genai.GenerativeModel('gemini-2.5-flash-image-preview')

# 定义图片路径
image_path = 'path/to/your/cat_image.png'

# 检查文件是否存在
try:
    cat_image = Image.open(image_path)
except FileNotFoundError:
    print(f"错误: 找不到图片文件 '{image_path}'。请更新路径。")
    exit()

# 定义编辑指令和图像内容
prompt = "使用这张我猫咪的图片，请在它的头上加一顶小小的、针织的巫师帽。"
contents = [prompt, cat_image]

print("正在编辑图像...")
response = model.generate_content(contents)

# 处理并保存结果
try:
    edited_image_part = response.parts[0]
    edited_image_data = edited_image_part.inline_data.data
    edited_image = Image.open(BytesIO(edited_image_data))
    edited_image.save("edited_image.png")
    print("编辑后的图像已保存为 edited_image.png")
except (IndexError, AttributeError) as e:
    print(f"解析编辑后的图像失败: {e}")
    print(f"完整响应内容: {response.text}")

# ...（接续前面的代码）...
def process_response(response, save_prefix="output"):
    """
    处理API响应，保存所有图像并打印所有文本。
    """
    image_count = 0
    text_parts = []
    
    if not response.candidates:
        print("响应中没有有效内容。")
        return

    for part in response.candidates[0].content.parts:
        if part.text:
            text_parts.append(part.text)
        elif part.inline_data:
            image_data = part.inline_data.data
            image = Image.open(BytesIO(image_data))
            file_name = f"{save_prefix}_image_{image_count}.png"
            image.save(file_name)
            print(f"图像已保存为 {file_name}")
            image_count += 1
            
    if text_parts:
        print("\n收到的文本信息：")
        print("\n".join(text_parts))

# 使用方法：
# response = model.generate_content(...)
# process_response(response)

const { GoogleGenerativeAI } = require("@google/generative-ai");
const fs = require("fs");
// SDK 会自动从环境变量 `GEMINI_API_KEY` 读取密钥
const genAI = new GoogleGenerativeAI(process.env.GEMINI_API_KEY);

async function run() {
  const model = genAI.getGenerativeModel({ model: "gemini-2.5-flash-image-preview" });
  const prompt = "一张卡哇伊风格的贴纸，内容是一只快乐的小熊猫戴着一顶小小的竹编帽子，白色背景。";

  console.log("正在生成贴纸...");
  const result = await model.generateContent(prompt);
  const response = await result.response;

  // 查找并保存图像数据
  const imagePart = response.candidates[0]?.content?.parts.find(part => part.inlineData);
  if (imagePart) {
    const imageData = imagePart.inlineData.data;
    const buffer = Buffer.from(imageData, "base64");
    fs.writeFileSync("generated_sticker.png", buffer);
    console.log("贴纸已保存为 generated_sticker.png");
  } else {
    console.log("响应中未找到图像数据。");
    console.log("文本响应:", response.text());
  }
}

run();

const { GoogleGenerativeAI } = require("@google/generative-ai");
const fs = require("fs");

const genAI = new GoogleGenerativeAI(process.env.GEMINI_API_KEY);

// 辅助函数：将本地文件转为API需要的格式
function fileToGenerativePart(path, mimeType) {
  return {
    inlineData: {
      data: Buffer.from(fs.readFileSync(path)).toString("base64"),
      mimeType
    },
  };
}

async function run() {
  const model = genAI.getGenerativeModel({ model: "gemini-2.5-flash-image-preview" });

  const imagePath = "path/to/your/car_image.jpg";
  if (!fs.existsSync(imagePath)) {
      console.error(`错误: 找不到图片文件 '${imagePath}'。请更新路径。`);
      return;
  }
  
  const imageParts = [
    fileToGenerativePart(imagePath, "image/jpeg"),
  ];

  const prompt = "根据这张图片，把汽车的颜色改成明亮的黄色。";

  console.log("正在编辑汽车颜色...");
  const result = await model.generateContent([prompt, ...imageParts]);
  const response = await result.response;
  
  // 处理并保存结果
  const editedImagePart = response.candidates[0]?.content?.parts.find(part => part.inlineData);
  if (editedImagePart) {
    const imageData = editedImagePart.inlineData.data;
    const buffer = Buffer.from(imageData, "base64");
    fs.writeFileSync("edited_car.png", buffer);
    console.log("编辑后的汽车图片已保存为 edited_car.png");
  } else {
    console.log("未找到编辑后的图像数据。");
    console.log("文本响应:", response.text());
  }
}

run();

# 填入在“uiuiapi.com”获取的秘钥
# 确保你已经设置了 GEMINI_API_KEY 环境变量
curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image-preview:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "contents": [{
    "parts": [{
      "text": "A close-up, highly detailed photograph of a futuristic robotic bee pollinating a glowing, biomechanical flower."
    }]
  }]
}' > response.json

echo "响应已保存至 response.json。你可以解析它来提取 Base64 编码的图像数据。"