Update docs (#332)

689e69b6 · Yang Yong (雍洋) · GitHub · 749f8c64 · 689e69b6 · 689e69b6
Unverified Commit 689e69b6 authored Sep 25, 2025 by Yang Yong (雍洋) Committed by GitHub Sep 25, 2025
8 changed files
--- a/docs/EN/source/getting_started/quickstart.md
+++ b/docs/EN/source/getting_started/quickstart.md
@@ -36,7 +36,7 @@ docker pull lightx2v/lightx2v:25092201-cu128
 We recommend using the `cuda128` environment for faster inference speed. If you need to use the `cuda124` environment, you can use image versions with the `-cu124` suffix:

 ```bash
-docker pull lightx2v/lightx2v:25091903-cu124
+docker pull lightx2v/lightx2v:25092201-cu124
 ```

 #### 2. Run Container
@@ -54,7 +54,7 @@ For mainland China, if the network is unstable when pulling images, you can pull
 docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/lightx2v:25092201-cu128

 # cuda124
-docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/lightx2v:25091903-cu124
+docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/lightx2v:25092201-cu124
 ```

 ### 🐍 Conda Environment Setup

--- a/docs/PAPERS_ZH_CN/source/index.rst
+++ b/docs/PAPERS_ZH_CN/source/index.rst
@@ -47,4 +47,7 @@ HuggingFace: https://huggingface.co/lightx2v
   并行推理 <papers/parallel.md>
   变分辨率推理 <papers/changing_resolution.md>
   步数蒸馏 <papers/step_distill.md>
-   自回归蒸馏 <papers/autoregressive_distill.md>
+   自回归模型 <papers/autoregressive.md>
+   vae加速 <papers/vae.md>
+   prompt增强 <papers/prompt_enhance.md>
+   强化学习 <papers/RL.md>
--- a/docs/PAPERS_ZH_CN/source/papers/RL.md
+++ b/docs/PAPERS_ZH_CN/source/papers/RL.md
+# 强化学习
+
+xxx
--- a/docs/PAPERS_ZH_CN/source/papers/autoregressive.md
+++ b/docs/PAPERS_ZH_CN/source/papers/autoregressive.md
+# 自回归模型
+
+xxx
--- a/docs/PAPERS_ZH_CN/source/papers/autoregressive_distill.md
+++ b/docs/PAPERS_ZH_CN/source/papers/autoregressive_distill.md
-# 自回归蒸馏
-
-xxx
--- a/docs/PAPERS_ZH_CN/source/papers/prompt_enhance.md
+++ b/docs/PAPERS_ZH_CN/source/papers/prompt_enhance.md
+# prompt增强
+
+xxx
--- a/docs/PAPERS_ZH_CN/source/papers/vae.md
+++ b/docs/PAPERS_ZH_CN/source/papers/vae.md
+# vae加速
+
+xxx
--- a/docs/ZH_CN/source/getting_started/quickstart.md
+++ b/docs/ZH_CN/source/getting_started/quickstart.md
@@ -36,7 +36,7 @@ docker pull lightx2v/lightx2v:25092201-cu128
 我们推荐使用`cuda128`环境，以获得更快的推理速度，若需要使用`cuda124`环境，可以使用带`-cu124`后缀的镜像版本：

 ```bash
-docker pull lightx2v/lightx2v:25091903-cu124
+docker pull lightx2v/lightx2v:25092201-cu124
 ```

 #### 2. 运行容器
@@ -54,7 +54,7 @@ docker run --gpus all -itd --ipc=host --name [容器名] -v [挂载设置] --ent
 docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/lightx2v:25092201-cu128

 # cuda124
-docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/lightx2v:25091903-cu124
+docker pull registry.cn-hangzhou.aliyuncs.com/yongyang/lightx2v:25092201-cu124
 ```

 ### 🐍 Conda 环境搭建