nano-banana

Nano Banana — 图像生成器

使用 Google Gemini 的图像生成模型生成图像。

用户请求： $ARGUMENTS

前置条件

• Python 3.10+
• google-genai 软件包（pip install google-genai）
• .env 文件中的 GEMINI_API_KEY（在 aistudio.google.com 获取免费密钥）

生成方法

编写并运行此 Python 脚本：

import os
import sys
from pathlib import Path
from datetime import datetime

# Load .env
env_file = Path(".env")
if env_file.exists():
    for line in env_file.read_text().splitlines():
        line = line.strip()
        if line and not line.startswith('#') and '=' in line:
            key, value = line.split('=', 1)
            os.environ[key] = value

from google import genai
from google.genai import types

api_key = os.environ.get("GEMINI_API_KEY")
if not api_key:
    print("❌ GEMINI_API_KEY not found. Add it to .env file.")
    sys.exit(1)

client = genai.Client(api_key=api_key)

prompt = "<USER'S IMAGE DESCRIPTION HERE>"

try:
    response = client.models.generate_content(
        model="gemini-3.1-flash-image-preview",
        contents=prompt,
        config=types.GenerateContentConfig(
            response_modalities=['IMAGE', 'TEXT']
        )
    )

    if not response.candidates:
        print("❌ No response — image may have been blocked by safety filter")
        sys.exit(1)

    candidate = response.candidates[0]
    if not candidate.content or not candidate.content.parts:
        print("❌ No content in response — try a different prompt")
        sys.exit(1)

    for part in candidate.content.parts:
        if part.inline_data is not None:
            ext = "png" if "png" in part.inline_data.mime_type else "jpg"
            timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
            filepath = f"images/{timestamp}.{ext}"
            Path("images").mkdir(exist_ok=True)
            Path(filepath).write_bytes(part.inline_data.data)
            print(f"✅ Image saved: {filepath}")
            break
    else:
        print("❌ No image in response — model returned text only")
        sys.exit(1)

except Exception as e:
    print(f"❌ Error: {e}")
    sys.exit(1)

重要事项

1. 根据用户的请求，将 <USER'S IMAGE DESCRIPTION HERE> 替换为实际提示词
2. 提示词必须使用与用户相同的语言
3. 如果未安装 google-genai，请先安装：pip install google-genai
4. 生成图像后，使用 Read 工具向用户展示图像