Add windows docs

docs/EN/source/deploy_guides/deploy_local_windows.md

-# 本地windows电脑部署
+# Local Windows Deployment Guide
 
-xxx
+This document provides detailed instructions for deploying LightX2V locally on Windows environments.
+
+## System Requirements
+
+Before getting started, please ensure your system meets the following requirements:
+
+- **Operating System**: Windows 10/11
+- **Graphics Card**: NVIDIA GPU (with CUDA support)
+- **VRAM**: At least 8GB VRAM
+- **Memory**: At least 16GB RAM
+- **Storage**: 20GB+ available disk space
+- **Environment Manager**: Anaconda or Miniconda installed
+- **Network Tools**: Git (for cloning repositories)
+
+## Deployment Steps
+
+### Step 1: Check CUDA Version
+
+First, verify your GPU driver and CUDA version by running the following command in Command Prompt:
+
+```bash
+nvidia-smi
+```
+
+Note the **CUDA Version** displayed in the output, as you'll need to match this version during subsequent installations.
+
+### Step 2: Create Python Environment
+
+Create an isolated conda environment, we recommend using Python 3.12:
+
+```bash
+# Create new environment (using Python 3.12 as example)
+conda create -n lightx2v python=3.12 -y
+
+# Activate environment
+conda activate lightx2v
+```
+
+> 💡 **Tip**: Python 3.10 or higher is recommended for optimal compatibility.
+
+### Step 3: Install PyTorch Framework
+
+#### Method 1: Download Official Wheel Packages (Recommended)
+
+1. Visit the [PyTorch Official Wheel Download Page](https://download.pytorch.org/whl/torch/)
+2. Select the appropriate wheel package, ensuring you match:
+   - **Python Version**: Must match your environment (cp312 means Python 3.12)
+   - **CUDA Version**: Must match your GPU driver
+   - **Platform**: Choose Windows version (win_amd64)
+
+**Example for Python 3.12 + PyTorch 2.6 + CUDA 12.4:**
+
+```
+torch-2.6.0+cu124-cp312-cp312-win_amd64.whl
+```
+
+After downloading, install the packages:
+
+```bash
+# Install PyTorch (replace with actual file path)
+pip install torch-2.6.0+cu124-cp312-cp312-win_amd64.whl
+
+# Install accompanying vision and audio packages
+pip install torchvision==0.21.0 torchaudio==2.6.0
+```
+
+#### Method 2: Direct pip Installation
+
+If you prefer direct installation, use the following command:
+
+```bash
+# Example: CUDA 12.4 version
+pip install torch==2.6.0+cu124 torchvision==0.21.0+cu124 torchaudio==2.6.0+cu124 --index-url https://download.pytorch.org/whl/cu124
+```
+
+### Step 4: Install Windows Version vLLM
+
+Download the corresponding wheel package from the [vllm-windows releases page](https://github.com/SystemPanic/vllm-windows/releases).
+
+**Version Matching Requirements:**
+- Python version must match (e.g., cp312)
+- PyTorch version must match
+- CUDA version must match
+
+**Recommended v0.9.1 Installation:**
+
+```bash
+pip install vllm-0.9.1+cu124-cp312-cp312-win_amd64.whl
+```
+
+> ⚠️ **Note**: Please select the appropriate wheel package filename based on your specific environment.
+
+### Step 5: Install Attention Mechanism Operators
+
+You can choose to install either Flash Attention 2 or SageAttention 2. **SageAttention 2 is strongly recommended**.
+
+#### Option A: Flash Attention 2
+
+```bash
+pip install flash-attn==2.7.2.post1
+```
+
+#### Option B: SageAttention 2 (Recommended)
+
+**Download Sources:**
+- [Windows Version 1](https://github.com/woct0rdho/SageAttention/releases)
+- [Windows Version 2](https://github.com/sdbds/SageAttention-for-windows/releases)
+
+**Version Selection Guidelines:**
+- Python version must match
+- PyTorch version must match
+- **CUDA version can be flexible** (SageAttention doesn't use breaking APIs yet)
+
+**Recommended Installation Version:**
+
+```bash
+pip install sageattention-2.1.1+cu126torch2.6.0-cp312-cp312-win_amd64.whl
+```
+
+**Verify SageAttention Installation:**
+
+After installation, we recommend running a verification script to ensure proper functionality:
+
+```bash
+# Download and run test script
+python -c "
+import torch
+import sageattention
+print('✅ SageAttention installed successfully!')
+print(f'Version: {sageattention.__version__ if hasattr(sageattention, \"__version__\") else \"Unknown\"}')
+"
+```
+
+> 📝 **Extended Testing**: You can also run the [test script](https://github.com/woct0rdho/SageAttention/blob/main/tests/test_sageattn.py) for more detailed functionality verification.
+
+### Step 6: Get LightX2V Project Code
+
+Clone the LightX2V project from GitHub and install Windows-specific dependencies:
+
+```bash
+# Clone project code
+git clone https://github.com/ModelTC/LightX2V.git
+
+# Enter project directory
+cd LightX2V
+
+# Install Windows-specific dependencies
+pip install -r requirements_win.txt
+```
+
+> 🔍 **Note**: We use `requirements_win.txt` instead of the standard `requirements.txt` because Windows environments may require specific package versions or additional dependencies.
+
+
+## Troubleshooting
+
+### 1. CUDA Version Mismatch
+
+**Symptoms**: CUDA-related errors occur
+
+**Solutions**:
+- Verify GPU driver supports required CUDA version
+- Re-download matching wheel packages
+- Use `nvidia-smi` to check maximum supported CUDA version
+
+### 2. Dependency Conflicts
+
+**Symptoms**: Package version conflicts or import errors
+
+**Solutions**:
+- Remove existing environment: `conda env remove -n lightx2v`
+- Recreate environment and install dependencies strictly by version requirements
+- Use virtual environments to isolate dependencies for different projects
+
+### 3. Wheel Package Download Issues
+
+**Symptoms**: Slow download speeds or connection failures
+
+**Solutions**:
+- Use download tools or browser for direct downloads
+- Look for domestic mirror sources
+- Check network connections and firewall settings
+
+## Next Steps
+
+After completing the environment setup, you can:
+
+- 📚 Check the [Quick Start Guide](../getting_started/quickstart.md) (skip environment installation steps)
+- 🌐 Use the [Gradio Web Interface](./deploy_gradio.md) for visual operations
+
+## Version Compatibility Reference
+
+| Component | Recommended Version |
+|-----------|-------------------|
+| Python | 3.12 |
+| PyTorch | 2.6.0+cu124 |
+| vLLM | 0.9.1+cu124 |
+| SageAttention | 2.1.1+cu126torch2.6.0 |
+| CUDA | 12.4+ |
+
+---
+
+💡 **Pro Tip**: If you encounter other issues, we recommend first checking whether all component versions match properly, as most problems stem from version incompatibilities.

docs/ZH_CN/source/deploy_guides/deploy_local_windows.md

-# 本地windows电脑部署
+# 本地Windows电脑部署指南
 
-xxx
+本文档将详细指导您在Windows环境下完成LightX2V的本地部署配置。
+
+## 系统要求
+
+在开始之前，请确保您的系统满足以下要求：
+
+- **操作系统**: Windows 10/11
+- **显卡**: NVIDIA GPU（支持CUDA）
+- **显存**: 至少8GB显存
+- **内存**: 至少16GB内存
+- **存储空间**: 20GB以上可用硬盘空间
+- **环境管理**: 已安装Anaconda或Miniconda
+- **网络工具**: Git（用于克隆代码仓库）
+
+## 部署步骤
+
+### 步骤1：检查CUDA版本
+
+首先确认您的GPU驱动和CUDA版本，在命令提示符中运行：
+
+```bash
+nvidia-smi
+```
+
+记录输出中显示的**CUDA Version**信息，后续安装时需要保持版本一致。
+
+### 步骤2：创建Python环境
+
+创建一个独立的conda环境，推荐使用Python 3.12：
+
+```bash
+# 创建新环境（以Python 3.12为例）
+conda create -n lightx2v python=3.12 -y
+
+# 激活环境
+conda activate lightx2v
+```
+
+> 💡 **提示**: 建议使用Python 3.10或更高版本以获得最佳兼容性。
+
+### 步骤3：安装PyTorch框架
+
+#### 方法一：下载官方wheel包安装（推荐）
+
+1. 访问 [PyTorch官方wheel包下载页面](https://download.pytorch.org/whl/torch/)
+2. 选择对应版本的wheel包，注意匹配：
+   - **Python版本**: 与您的环境一致（cp312表示Python 3.12）
+   - **CUDA版本**: 与您的GPU驱动匹配
+   - **平台**: 选择Windows版本（win_amd64）
+
+**以Python 3.12 + PyTorch 2.6 + CUDA 12.4为例：**
+
+```
+torch-2.6.0+cu124-cp312-cp312-win_amd64.whl
+```
+
+下载完成后进行安装：
+
+```bash
+# 安装PyTorch（请替换为实际的文件路径）
+pip install torch-2.6.0+cu124-cp312-cp312-win_amd64.whl
+
+# 安装配套的vision和audio包
+pip install torchvision==0.21.0 torchaudio==2.6.0
+```
+
+#### 方法二：使用pip直接安装
+
+如果您偏好直接安装，可以使用以下命令：
+
+```bash
+# 示例：CUDA 12.4版本
+pip install torch==2.6.0+cu124 torchvision==0.21.0+cu124 torchaudio==2.6.0+cu124 --index-url https://download.pytorch.org/whl/cu124
+```
+
+### 步骤4：安装Windows版vLLM
+
+从 [vllm-windows releases页面](https://github.com/SystemPanic/vllm-windows/releases) 下载对应的wheel包。
+
+**版本匹配要求：**
+- Python版本匹配（如cp312）
+- PyTorch版本匹配
+- CUDA版本匹配
+
+**推荐安装v0.9.1版本：**
+
+```bash
+pip install vllm-0.9.1+cu124-cp312-cp312-win_amd64.whl
+```
+
+> ⚠️ **注意**: 请根据您的具体环境选择对应的wheel包文件名。
+
+### 步骤5：安装注意力机制算子
+
+您可以选择安装Flash Attention 2或SageAttention 2，**强烈推荐SageAttention 2**。
+
+#### 选项A：Flash Attention 2
+
+```bash
+pip install flash-attn==2.7.2.post1
+```
+
+#### 选项B：SageAttention 2（推荐）
+
+**下载源选择：**
+- [Windows专用版本1](https://github.com/woct0rdho/SageAttention/releases)
+- [Windows专用版本2](https://github.com/sdbds/SageAttention-for-windows/releases)
+
+**版本选择要点：**
+- Python版本必须匹配
+- PyTorch版本必须匹配
+- **CUDA版本可以不严格对齐**（SageAttention暂未使用破坏性API）
+
+**推荐安装版本：**
+
+```bash
+pip install sageattention-2.1.1+cu126torch2.6.0-cp312-cp312-win_amd64.whl
+```
+
+**验证SageAttention安装：**
+
+安装完成后，建议运行测试脚本验证功能是否正常：
+
+```bash
+# 下载并运行测试脚本
+python -c "
+import torch
+import sageattention
+print('✅ SageAttention安装成功!')
+print(f'版本: {sageattention.__version__ if hasattr(sageattention, \"__version__\") else \"未知\"}')
+"
+```
+
+> 📝 **扩展测试**: 您也可以运行[测试脚本](https://github.com/woct0rdho/SageAttention/blob/main/tests/test_sageattn.py)进行更详细的功能验证。
+
+### 步骤6：获取LightX2V项目代码
+
+从GitHub克隆LightX2V项目并安装Windows专用依赖：
+
+```bash
+# 克隆项目代码
+git clone https://github.com/ModelTC/LightX2V.git
+
+# 进入项目目录
+cd LightX2V
+
+# 安装Windows专用依赖包
+pip install -r requirements_win.txt
+```
+
+> 🔍 **说明**: 这里使用`requirements_win.txt`而不是标准的`requirements.txt`，因为Windows环境可能需要特定的包版本或额外的依赖。
+
+
+## 故障排除
+
+### 1. CUDA版本不匹配
+
+**问题现象**: 出现CUDA相关错误
+
+**解决方案**:
+- 确认GPU驱动支持所需CUDA版本
+- 重新下载匹配的wheel包
+- 可以通过`nvidia-smi`查看支持的最高CUDA版本
+
+### 2. 依赖冲突
+
+**问题现象**: 包版本冲突或导入错误
+
+**解决方案**:
+- 删除现有环境: `conda env remove -n lightx2v`
+- 重新创建环境并严格按版本要求安装
+- 使用虚拟环境隔离不同项目的依赖
+
+### 3. wheel包下载问题
+
+**问题现象**: 下载速度慢或失败
+
+**解决方案**:
+- 使用下载工具或浏览器直接下载
+- 寻找国内镜像源
+- 检查网络连接和防火墙设置
+
+
+## 下一步操作
+
+环境配置完成后，您可以：
+
+- 📚 查看[快速开始指南](../getting_started/quickstart.md)（跳过环境安装步骤）
+- 🌐 使用[Gradio Web界面](./deploy_gradio.md)进行可视化操作
+
+## 版本兼容性参考
+
+| 组件 | 推荐版本 |
+|------|----------|
+| Python | 3.12 |
+| PyTorch | 2.6.0+cu124 |
+| vLLM | 0.9.1+cu124 |
+| SageAttention | 2.1.1+cu126torch2.6.0 |
+| CUDA | 12.4+ |
+
+---
+
+💡 **小贴士**: 如果遇到其他问题，建议先检查各组件版本是否匹配，大部分问题都源于版本不兼容。

requirements.txt

@@ -18,3 +18,6 @@ sgl-kernel
 qtorch
 ftfy
 easydict
+gradio
+aiohttp
+pydantic

requirements_win.txt

+packaging
+ninja
+diffusers
+transformers
+tokenizers
+accelerate
+safetensors
+opencv-python
+numpy
+imageio
+imageio-ffmpeg
+einops
+loguru
+qtorch
+ftfy
+easydict
+gradio
+aiohttp
+pydantic