update readme

README.md

@@ -6,11 +6,14 @@ license: bsd-3-clause
 
 This project provides a complete implementation for deploying the Z-Image-Turbo diffusion model on AXERA AX650N NPU hardware. Z-Image-Turbo is a high-performance text-to-image generation model that leverages advanced diffusion techniques to produce high-quality images with fast inference speed.
 
+**Note:** This implementation is optimized for AXERA AX650N hardware. Performance and compatibility may vary on other platforms.
+
 ## Table of Contents
 
 - [Overview](#overview)
 - [Requirements](#requirements)
 - [Project Structure](#project-structure)
+- [Quick Start](#quick-start)
 - [Model Components](#model-components)
   - [1. Transformer Module](#1-transformer-module)
   - [2. VAE Decoder Module](#2-vae-decoder-module)
@@ -79,6 +82,17 @@ Z-Image-Turbo/
 └── README.md                   # This documentation
 ```
 
+## Quick Start
+
+Clone the entire repository and navigate to the `VideoX-Fun` directory:
+
+```sh
+git clone https://huggingface.co/AXERA-TECH/Z-Image-Turbo
+cd Z-Image-Turbo/VideoX-Fun
+```
+
+This repository contains pre-compiled models ready for deployment on AXERA AX650N hardware. If you want to export and compile models from scratch, please refer to the [Model Components](#model-components) section below.
+
 ## Model Components
 
 ### 1. Transformer Module
@@ -98,6 +112,8 @@ python scripts/z_image/export_transformer_body_onnx.py \
         --skip-slim
 ```
 
+> **Important:** Before exporting to ONNX format, you need to download the complete Z-Image-Turbo model from [Tongyi-MAI/Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo) and place it in the `models/Diffusion_Transformer/` directory. This repository only provides pre-compiled models and inference code for deployment on AXERA hardware.
+
 **Parameters:**
 - `--output`: Output path for the ONNX model
 - `--height`, `--width`: Target image dimensions (512x512)
@@ -395,9 +411,4 @@ If you encounter any issues or have questions about the implementation:
 
 ## License
 
-This project is licensed under the BSD-3-Clause License. See the LICENSE file for details.
-
----
-
-**Note:** This implementation is optimized for AXERA AX650N hardware. Performance and compatibility may vary on other platforms.
-
+This project is licensed under the BSD-3-Clause License. See the LICENSE file for details.