Update README.md

README.md

@@ -17,11 +17,56 @@ library_name: diffusers
 ---
 # 🎬 Wan-NVFP4-4Steps Models
 
-### ⚡ NVFP4 Quantization-Aware Step Distillation
+> **NVFP4 Quantization-Aware Step Distillation for Blackwell Architecture**
+
+[![GitHub](https://img.shields.io/badge/GitHub-ModelTC/LightX2V-blue)](https://github.com/ModelTC/LightX2V)
+[![HuggingFace](https://img.shields.io/badge/HuggingFace-lightx2v-yellow)](https://huggingface.co/lightx2v/)
+
+## 📋 Table of Contents
+
+- [✨ Features](#-features)
+- [🚀 Quick Start](#-quick-start)
+- [🎬 Generation Results](#-generation-results)
+- [⚡ Performance Comparison](#-performance-comparison)
+- [📦 Installation](#-installation)
+- [🛠️ Usage](#-usage)
+- [🧭 Project Structure](#-project-structure)
+- [⚠️ Notes](#️-notes)
+- [🤝 Community](#-community)
 
 ## ✨ Features
-- 4-Step Inference + NVFP4 Quantization: Reduced memory and bandwidth usage, optimized for Blackwell architecture, significantly accelerated end-to-end generation approaching real-time performance (tested on RTX 5090 single GPU)
-- LightX2V Integration: Optimal performance and stability on the official framework.
+
+- **⚡ 4-Step Inference**: Dramatically accelerated end-to-end generation approaching real-time performance (tested on RTX 5090 single GPU)
+- **🎯 NVFP4 Quantization**: Reduced memory and bandwidth usage, optimized for Blackwell architecture
+- **🔧 LightX2V Integration**: Optimal performance and stability on the official framework
+- **🚀 High-Quality Generation**: Maintains Wan2.1's superior video quality while achieving unprecedented speed
+
+## 🚀 Quick Start
+
+```bash
+# 1. Install LightX2V
+git clone https://github.com/ModelTC/LightX2V.git
+cd LightX2V
+uv pip install -v .
+
+# 2. Install NVFP4 Kernel
+pip install scikit_build_core uv
+git clone https://github.com/NVIDIA/cutlass.git
+cd lightx2v_kernel
+
+MAX_JOBS=$(nproc) CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) \
+uv build --wheel \
+  -Cbuild-dir=build . \
+  -Ccmake.define.CUTLASS_PATH=/path/to/cutlass \
+  --verbose --color=always --no-build-isolation
+
+pip install dist/*whl --force-reinstall --no-deps
+
+# 3. Run inference
+cd examples/wan
+python wan_i2v_nvfp4.py   # Image-to-Video
+python wan_t2v_nvfp4.py   # Text-to-Video
+```
 
 ## 🎬 Generation Results
 
@@ -88,45 +133,28 @@ library_name: diffusers
 </tr>
 </table>
 
+## ⚠️ Notes
 
+### System Requirements
+- **Required Hardware**: NVIDIA RTX 50-series GPUs (RTX 5090/5080/5070/5060) or other Blackwell architecture GPUs
 
-## 🚀 Usage Guide
-1) Install LightX2V
-```bash
-git clone https://github.com/ModelTC/LightX2V.git
-cd LightX2V
-uv pip install -v .  # or pip install -v .
-```
-2) Install lightx2v-kernel (NVFP4 operators)
-```bash
-pip install scikit_build_core uv
-git clone https://github.com/NVIDIA/cutlass.git
-cd LightX2V/lightx2v_kernel
-MAX_JOBS=$(nproc) CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) \
-uv build --wheel \
-  -Cbuild-dir=build . \
-  -Ccmake.define.CUTLASS_PATH=/path/to/cutlass \  # Fill in the absolute path to your local cutlass repository here
-  --verbose --color=always --no-build-isolation
-pip install dist/*whl --force-reinstall --no-deps
-```
-3) Run inference (modify model paths in scripts)
-```bash
-cd LightX2V/examples/wan
-python wan_i2v_nvfp4.py   # I2V
-python wan_t2v_nvfp4.py   # T2V
-```
-
-## 🧭 Directory Structure Guide
-- `examples/wan/`: Example inference scripts (choose 480P / 1.3B / 14B based on memory).
-- `lightx2v_kernel/`: Self-compiled NVFP4 operators.
+### Dependencies
+- Prepare T5 / CLIP / VAE components yourself (same as Wan2.x structure)
 
-## ⚠️ Notes
-- Prepare T5 / CLIP / VAE and other dependent components yourself (same as Wan2.x structure).
-- For GPUs with lower memory, CPU offload can be used; however, Blackwell + NVFP4 is recommended for optimal performance.
+### Performance Tips
+- Use Blackwell + NVFP4 for best performance
+- Enable CPU offload for GPUs with limited memory
 
 ## 🤝 Community
 
-- **GitHub Issues**: https://github.com/ModelTC/LightX2V/issues
-- **HuggingFace**: https://huggingface.co/lightx2v/
+- **🐛 Issues**: [GitHub Issues](https://github.com/ModelTC/LightX2V/issues)
+- **🤗 Models**: [HuggingFace Hub](https://huggingface.co/lightx2v/)
+- **📖 Documentation**: [LightX2V Docs](https://github.com/ModelTC/LightX2V)
+
+---
+
+<div align="center">
+
+**If you find this project helpful, please give us a ⭐ on [GitHub](https://github.com/ModelTC/LightX2V)**
 
-If you find this project helpful, please give us a ⭐ on [GitHub](https://github.com/ModelTC/LightX2V)
+</div>