Initial commit: AI Image Generator project

Author: AI Assistant

.gitignore

@@ -0,0 +1,21 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+
+# 配置文件
+config.py
+
+# 输出目录
+output/
+
+# 日志文件
+*.log
+
+# 虚拟环境
+venv/
+.env/
+
+# IDE配置
+.vscode/
+.idea/

README.md

@@ -0,0 +1,139 @@
+# AI Image Generator
+
+基于阿里云灵积模型的批量图片生成工具
+
+[English](README_EN.md) | 简体中文
+
+## 功能特点
+
+- 支持批量生成AI图片
+- 自定义存储路径和文件夹结构
+- 自动保存生成提示词
+- 断点续传功能
+- 智能请求限制处理
+- 详细的错误日志记录
+
+## 环境要求
+
+- Python 3.7+
+- aiohttp
+- Pillow
+- 阿里云灵积API密钥（注册即送500万tokens免费额度）
+
+## 安装
+
+1. 克隆项目到本地：
+
+```bash
+git clone https://github.com/yourusername/ai-image-generator.git
+cd ai-image-generator
+```
+
+2. 安装依赖：
+
+```bash
+pip install -r requirements.txt
+```
+
+## 配置
+
+1. 复制配置文件模板：
+
+```bash
+cp config.example.py config.py
+```
+
+2. 在config.py中设置你的API密钥和其他配置：
+
+```python
+API_KEY = "your-api-key-here"  # 在阿里云百炼平台获取API密钥：https://bailian.console.aliyun.com
+API_URL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis"
+
+# 输出配置
+OUTPUT_DIR = "output"  # 输出目录
+IMAGE_FORMAT = "jpg"   # 图片格式
+```
+
+## 使用方法
+
+1. 准备提示词文件
+
+在`prompts.txt`中每行写入一个图片生成提示词：
+
+```text
+一个苹果被切开后，果肉内部长出一朵鲜花
+一个风扇旋转时，风向扇叶内部吹去
+...
+```
+
+2. 运行程序
+
+```bash
+python generate_images.py
+```
+
+程序会自动：
+- 创建输出目录
+- 读取提示词文件
+- 批量生成图片
+- 保存图片和提示词
+- 记录错误日志
+
+## 输出结构
+
+```
+output/
+  ├── 1/
+  │   ├── image.jpg
+  │   └── info.txt
+  ├── 2/
+  │   ├── image.jpg
+  │   └── info.txt
+  └── ...
+```
+
+## 高级配置
+
+在`config.py`中可以自定义更多参数：
+
+```python
+# 批处理配置
+BATCH_SIZE = 10        # 每批处理数量
+BATCH_DELAY = 60       # 批次间延迟(秒)
+REQUEST_DELAY = 15     # 请求间延迟(秒)
+
+# 重试配置
+MAX_RETRIES = 3        # 最大重试次数
+RETRY_DELAY = 5        # 重试延迟(秒)
+
+# 图片配置
+IMAGE_SIZE = "1024*1024"  # 图片尺寸
+IMAGE_COUNT = 1           # 每个提示词生成图片数
+```
+
+## 错误处理
+
+- 程序会自动处理API限流
+- 失败的生成会记录到error.log
+- 支持断点续传，可以从上次中断处继续
+
+## 开发计划
+
+- [ ] 支持更多图片格式
+- [ ] 添加Web界面
+- [ ] 支持更多AI模型
+- [ ] 优化并发处理
+
+## 贡献指南
+
+欢迎提交Issue和Pull Request！
+
+## 许可证
+
+MIT License
+
+## 致谢
+
+- [阿里云灵积平台](https://bailian.console.aliyun.com) - 注册即送500万tokens免费额度
+- [Python aiohttp](https://docs.aiohttp.org)
+- [Pillow](https://python-pillow.org)

README_EN.md

@@ -0,0 +1,139 @@
+# AI Image Generator
+
+A batch image generation tool based on Alibaba Cloud Tongyi Model
+
+English | [简体中文](README.md)
+
+## Features
+
+- Batch AI image generation
+- Customizable storage paths and folder structures
+- Automatic prompt text saving
+- Resume from breakpoint
+- Smart request rate limiting
+- Detailed error logging
+
+## Requirements
+
+- Python 3.7+
+- aiohttp
+- Pillow
+- Alibaba Cloud Tongyi API Key
+
+## Installation
+
+1. Clone the repository:
+
+```bash
+git clone https://github.com/yourusername/ai-image-generator.git
+cd ai-image-generator
+```
+
+2. Install dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+## Configuration
+
+1. Copy the configuration template:
+
+```bash
+cp config.example.py config.py
+```
+
+2. Set your API key and other configurations in config.py:
+
+```python
+API_KEY = "your-api-key-here"
+API_URL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis"
+
+# Output settings
+OUTPUT_DIR = "output"  # Output directory
+IMAGE_FORMAT = "jpg"   # Image format
+```
+
+## Usage
+
+1. Prepare the prompts file
+
+Add one prompt per line in `prompts.txt`:
+
+```text
+An apple cut open with a flower growing inside
+A fan spinning with wind blowing inward
+...
+```
+
+2. Run the program
+
+```bash
+python generate_images.py
+```
+
+The program will automatically:
+- Create output directory
+- Read prompts file
+- Generate images in batch
+- Save images and prompts
+- Log errors
+
+## Output Structure
+
+```
+output/
+  ├── 1/
+  │   ├── image.jpg
+  │   └── info.txt
+  ├── 2/
+  │   ├── image.jpg
+  │   └── info.txt
+  └── ...
+```
+
+## Advanced Configuration
+
+Customize more parameters in `config.py`:
+
+```python
+# Batch processing settings
+BATCH_SIZE = 10        # Number of items per batch
+BATCH_DELAY = 60       # Delay between batches (seconds)
+REQUEST_DELAY = 15     # Delay between requests (seconds)
+
+# Retry settings
+MAX_RETRIES = 3        # Maximum retry attempts
+RETRY_DELAY = 5        # Delay between retries (seconds)
+
+# Image settings
+IMAGE_SIZE = "1024*1024"  # Image dimensions
+IMAGE_COUNT = 1           # Images per prompt
+```
+
+## Error Handling
+
+- Automatic API rate limit handling
+- Failed generations are logged to error.log
+- Supports resuming from last successful generation
+
+## Roadmap
+
+- [ ] Support for more image formats
+- [ ] Add Web interface
+- [ ] Support for more AI models
+- [ ] Optimize concurrent processing
+
+## Contributing
+
+Issues and Pull Requests are welcome!
+
+## License
+
+MIT License
+
+## Acknowledgments
+
+- [Alibaba Cloud Tongyi Platform](https://dashscope.aliyun.com)
+- [Python aiohttp](https://docs.aiohttp.org)
+- [Pillow](https://python-pillow.org)

config.example.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+
+# API配置
+API_KEY = "your-api-key-here"  # 在阿里云百炼平台获取API密钥：https://bailian.console.aliyun.com
+API_URL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis"
+
+# 模型配置
+MODEL = "wanx2.1-t2i-turbo"  # 使用的模型名称
+
+# 输出配置
+OUTPUT_DIR = "ai"  # 输出目录
+IMAGE_FORMAT = "jpg"  # 图片格式
+IMAGE_SIZE = "1024*1024"  # 图片尺寸
+IMAGE_COUNT = 1  # 每个提示词生成的图片数量
+
+# 批处理配置
+BATCH_SIZE = 10  # 每批处理的提示词数量
+BATCH_DELAY = 60  # 批次间延迟(秒)
+REQUEST_DELAY = 15  # 请求间延迟(秒)
+
+# 重试配置
+MAX_RETRIES = 3  # 最大重试次数
+RETRY_DELAY = 5  # 重试延迟(秒)
+
+# 日志配置
+ERROR_LOG = "error.log"  # 错误日志文件
+PROMPTS_FILE = "prompts.txt"  # 提示词文件