update readme and doc

README.md

@@ -13,6 +13,16 @@
 
 --------------------------------------------------------------------------------
 
+LightX2V is a lightweight video generation inference framework designed to provide an inference tool that leverages multiple advanced video generation inference techniques. As a unified inference platform, this framework supports various generation tasks such as text-to-video (T2V) and image-to-video (I2V) across different models. X2V means transforming any input modality (such as text or images) to video output.
+
+
+## How to Start
+
+Please refer to our documentation:
+
+[English Docs](https://lightx2v-en.readthedocs.io/en/latest/) | [中文文档](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/)
+
+
 ## Supported Model List
 
 ✅ [HunyuanVideo-T2V](https://huggingface.co/tencent/HunyuanVideo)
@@ -31,11 +41,6 @@
 
 ✅ [CogVideoX1.5-5B-T2V](https://huggingface.co/THUDM/CogVideoX1.5-5B)
 
-## How to Run
-
-Please refer to our documentation:
-
-[English Docs](https://lightx2v-en.readthedocs.io/en/latest/) | [中文文档](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/)
 
 ## Contributing Guidelines
 

docs/EN/source/index.rst

@@ -14,6 +14,8 @@ Welcome to Lightx2v!
    </strong>
 
 
+LightX2V is a lightweight video generation inference framework designed to provide an inference tool that leverages multiple advanced video generation inference techniques. As a unified inference platform, this framework supports various generation tasks such as text-to-video (T2V) and image-to-video (I2V) across different models. X2V means transforming any input modality (such as text or images) to video output.
+
 Documentation
 -------------
 

docs/ZH_CN/source/index.rst

@@ -14,6 +14,8 @@
    </strong>
 
 
+LightX2V 是一个轻量级的视频生成推理框架，旨在提供一个利用多种先进的视频生成推理技术的推理工具。该框架作为统一的推理平台，支持不同模型的文本到视频（T2V）和图像到视频（I2V）等生成任务。X2V 表示将任何输入模态（X，如文本或图像）转换（to）为视频输出（V）。
+
 文档列表
 -------------