diff --git a/docs/development-guide/backend/docker.mdx b/docs/development-guide/backend/docker.mdx
new file mode 100644
index 000000000..cfb0fb47a
--- /dev/null
+++ b/docs/development-guide/backend/docker.mdx
@@ -0,0 +1,54 @@
+---
+sidebar_position: 2
+---
+
+# Docker 本地构建指南
+
+> 如果你想要的是使用我们提供的 docker 镜像部署 Open-LLM-VTuber 项目，可以看看 [Docker 部署](../../user-guide/backend/docker.md)
+
+## 说明
+- 项目的多架构镜像构建与推送已由 GitHub Actions 自动完成。
+- 本文档仅用于开发者本地构建调试镜像，不使用 `docker buildx`。
+
+## 本地环境要求
+- 已安装 `git`
+- 已安装 Docker（建议 Docker Engine 24+ 或 Docker Desktop 最新稳定版）
+- 可选：已安装 Docker Compose 插件（仅在你需要 `docker compose` 时）
+- 建议预留至少 `10GB` 可用磁盘空间（首次构建会下载较多依赖）
+
+可用以下命令自检：
+```
+git --version
+docker --version
+docker compose version
+```
+
+## 获取代码
+```
+git clone https://github.com/Open-LLM-VTuber/Open-LLM-VTuber.git
+cd Open-LLM-VTuber
+```
+
+## 本地构建镜像（单架构）
+在项目根目录执行：
+```
+docker build -t openllmvtuber/open-llm-vtuber:local -f dockerfile .
+```
+
+如需自定义镜像名或标签，替换 `openllmvtuber/open-llm-vtuber:local` 即可。
+
+## 可选：本地运行验证
+运行前请确认 `conf/conf.yaml` 已存在：
+```
+docker run --rm -it \
+ -p 12393:12393 \
+ -v "$(pwd)/conf:/app/conf" \
+ -v "$(pwd)/models:/app/models" \
+ openllmvtuber/open-llm-vtuber:local
+```
+
+## 清理本地 Docker 数据
+```
+docker system prune -a --volumes
+```
+
diff --git a/docs/quick-start.md b/docs/quick-start.md
index 37068354d..a34d9cb17 100644
--- a/docs/quick-start.md
+++ b/docs/quick-start.md
@@ -63,6 +63,23 @@ Groq Whisper API、OpenAI API 等国外大模型/推理平台 API 一般无法
对于本快速开始文档选择的组件，你需要一个速度正常的 CPU (ASR)，一个 Ollama 支持的 GPU (LLM)，以及网路链接 (TTS)。
+## Docker 快速启动
+
+:::info 说明
+Docker是**最适合小白**的部署方式，它可以一键部署所有组件，无需手动配置。
+:::
+
+如果你对 Docker 感兴趣，请移步[Docker 部署指南](./user-guide/backend/docker.md)。
+
+如果不感兴趣，您也可以跳转到常规配置方法，从下一步，也就是[环境准备](#环境准备)步骤开始。
+
+:::note 目前的docker镜像对平台支持情况如下表
+| 平台 | CPU 支持 | NVIDIA GPU 支持 | AMD/Intel GPU 支持 |
+|----------|----------|-----------------|--------------------|
+| Linux | ✅ | ✅ | ❌ |
+| Windows | ✅ | ✅[(需安装Nvidia驱动）](#nvidia-gpu-支持) | ❌ |
+| macOS | ✅ | ❌ | ❌ |
+:::
## 环境准备
@@ -377,9 +394,6 @@ source ~/.zshrc # 如果使用 zsh
-
-
-
### 2. 安装项目依赖
:::info
diff --git a/docs/user-guide/backend/agent.md b/docs/user-guide/backend/agent.md
index dcc73a191..6220c4934 100644
--- a/docs/user-guide/backend/agent.md
+++ b/docs/user-guide/backend/agent.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 5
+sidebar_position: 6
---
# 智能体 (Agent)
diff --git a/docs/user-guide/backend/asr.md b/docs/user-guide/backend/asr.md
index 373770359..a51a5d3f6 100644
--- a/docs/user-guide/backend/asr.md
+++ b/docs/user-guide/backend/asr.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 3
+sidebar_position: 4
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
diff --git a/docs/user-guide/backend/docker.md b/docs/user-guide/backend/docker.md
index ac8e49ba2..a133300b2 100644
--- a/docs/user-guide/backend/docker.md
+++ b/docs/user-guide/backend/docker.md
@@ -1,56 +1,258 @@
---
-sidebar_position: 8
+sidebar_position: 3
---
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
# Docker 部署
-:::danger
-由于重构幅度较大，Docker 镜像暂时还没有更新到 `v1.0.0` 版本，但是很快会更新。
+> 关于本地构建 docker 镜像，参考 [Docker 本地构建指南](../../development-guide/backend/docker.mdx)
+
+## 关于我们的docker团队
+我们在 docker hub 成立了[openllmvtuber团队](https://hub.docker.com/orgs/openllmvtuber/members)，目前docker镜像由[@Harry_Y](https://github.com/Harry-Yu-Shuhang)维护。
+
+## 下载配置文件
+
+### git下载（适合有git基础的用户）
+先[按照Quick Start安装 git](../../quick-start.md#安装-git)
+, 然后下载docker用户配置文件:
+
+```bash
+git clone https://github.com/Open-LLM-VTuber/OLV-Docker-Config
+```
+
+### zip下载（适合没有代码基础的用户）
+:::warning
+这样下载的话,配置文件`conf.yaml`只能[手动更新](#手动更新)。
+:::
+首先，[点击这里前往用户配置代码仓库](https://github.com/Open-LLM-VTuber/OLV-Docker-Config)
+
+然后，在网页右上角，点击 `Code` -> `Download ZIP` 下载 docker 用户配置, 如下图。
+
+
+
+## 修改配置文件
+如果自己有想修改的配置，就修改配置文件`conf.yaml`。
+
+:::info 默认的 `conf.yaml` 是英文的，如果想替换成中文，请到 `config_templates` 文件夹下复制 `conf.ZH.default.yaml`, 然后回到上一级, 替换掉原来的 `conf.yaml`
+:::
+
+如果你是小白，建议直接用默认的配置文件，可以一键启动。
+
+如果你想改一些配置，比如人设、模型、asr、tts等，请修改`conf.yaml`的对应字段。
+
+关于配置文件里各个字段的作用，可以参考配置文件里的注释。
+
+## 安装 Docker
+
+:::tip 关于安装方式
+目前支持两种方式。
+- 如果您是小白，推荐您[使用 Docker DeskTop](#使用-docker-desktop-安装-docker) 。
+- 如果您对 Docker 比较熟悉，也可以[使用终端命令](#使用终端命令安装-docker)。
+:::
+
+:::caution 关于GPU支持
+目前**仅支持CPU和Nvidia GPU**, 且GPU需要配置好Nvidia驱动, 如果还没配置好, 请[**点击这里前往Quick Start查看配置攻略**](../../quick-start.md#nvidia-gpu-支持)。
+
+如果您不打算使用GPU，而是**调用api**（这也是**绝大多数用户体验最好的方式**），或者使用CPU，可以忽略此步。
+:::
+
+:::note 关于我们`Docker`团队
+我们在 docker hub 成立了[openllmvtuber团队](https://hub.docker.com/orgs/openllmvtuber/members)，目前Docker镜像由[@Harry_Y](https://github.com/Harry-Yu-Shuhang)维护。
+:::
+
+## 使用 Docker Desktop 安装 Docker
+
+:::warning 由于 `Docker Desktop` 退出重启经常卡死，建议尽量避免重启，如果重启很久以后没有反应，可以在任务管理器 (`Windows`) 或者 活动监视器 (`macOS`) 里杀掉 `Docker Desktop` 的后台进程，然后再次启动。
+:::
+
+### 下载 Docker Desktop
+
+访问 [Docker Desktop 下载页面](https://www.docker.com/products/docker-desktop)。
+
+点击 "Download Docker Desktop"
+
+
+
+根据电脑类型选择对应版本
+
+:::tip 如何选择适用于自己电脑的版本
+- **Mac Apple Silicon** → 新款 Mac (M1/M2/M3 芯片)
+- **Mac Intel Chip** → 老款 Mac (Intel 处理器)
+- **Windows AMD64** → 大部分 Windows 电脑 (Intel/AMD 64 位)
+- **Windows ARM64** → 少见，仅 ARM 架构 Windows (如 Surface Pro X)
+:::
+
+如果您还不确定，可以按如下方法查看系统设置：
+
+
+
+
+1. 右键 **此电脑 → 属性**
+2. 在 **系统类型** 一栏查看：
+ - “基于 x64 的处理器” → 选择 **Windows AMD64**
+ - “基于 ARM 的处理器” → 选择 **Windows ARM64**
+
+
+
+
+1. 点击屏幕左上角苹果图标 → **关于本机**
+2. 在“芯片”一栏查看：
+ - 显示 **Apple M1/M2/M3** → 选择 **Mac Apple Silicon**
+ - 显示 **Intel** → 选择 **Mac Intel Chip**
+
+
+
+
+### 启动 Docker Desktop
+
+双击下载好的安装包，按照提示完成安装。
+
+安装完成后，点击 Docker Desktop 图标启动 Docker。
+
+首次启动时，Docker Desktop 会要求您登录 Docker Hub 账号。如果您没有账号，需要先注册一个。
+
+### 获取 Docker 镜像
+
+点击顶部菜单的 **Search** 图标（或使用快捷键 `Ctrl + K`(Windows)或者`Cmd + K`(MacOS)）。
+
+
+
+在搜索框中输入以下内容，搜索到以后点击右侧的**Pull**按钮。
+
+```
+openllmvtuber/open-llm-vtuber:latest
+```
+
+
+
+### 配置 LLM
+:::info 关于调用LLM的方式
+如果您使用本地模型，比如默认配置的 `Ollama`， 这一步必须做。
+
+如果你选择api调用，可以跳过这一步。
:::
-:::warning
-⚠️ 请注意：此功能目前处于实验阶段，但在大多数情况下可以正常工作。
+:::info 如果您是没有代码基础的小白
+建议按照以下步骤，直接使用默认的 `Ollama` 模型调用方式，省去配置麻烦。
+
+
+ 1. 从 [Ollama 官网](https://ollama.com/) 下载并安装 Ollama 客户端。
+
+ 2. 终端输入以下指令，验证Ollama是否安装成功:
+ ```bash
+ ollama --version
+ ```
+
+ 3. 下载并运行模型（以默认配置文件的 `qwen2.5:latest` 为例）：
+ ```bash
+ ollama run qwen2.5:latest
+ ```
+
+ 4. 查看已安装的模型。
+ ```bash
+ ollama list
+ ```
+
:::
-您可以选择自行构建 Docker 镜像，或者直接从 Docker Hub 拉取已构建的镜像：[](https://hub.docker.com/r/openllmvtuber/open-llm-vtuber)
-## 使用须知
+更多注意事项，可以参考 [Quick Start 里的配置 LLM 部分](../../quick-start.md#3-配置-llm)。
+
+
+### 运行 Docker 容器
+
+点击**Images**, 找到**openllmvtuber/open-llm-vtuber**, 点击右侧的运行按钮。
+
+
+点开"Optional settings", 按照下图配置，
+
+
+
+### 在浏览器打开web界面
+等到出现这几行字，如下图，就说明启动成功了。第一次拉取会比较慢，因为要安装一些必要工具，请耐心等待。
+
-- Docker 镜像体积较大（约 13GB），且某些可选模型在使用时需要额外下载，会占用更多存储空间
-- 仅支持 NVIDIA GPU 的设备
-- 需要安装并配置 [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) 以支持 GPU 直通
-- 目前存在的问题：容器停止后部分模型需要重新下载（该问题将在后续版本修复）
-- 不建议在 ARM 架构的设备上构建镜像，因为依赖项 gRPC 可能会出现构建失败的情况（[相关 issue](https://github.com/grpc/grpc/issues/34998)）
-- 如需在远程服务器上运行，必须配置 HTTPS。这是因为前端网页的麦克风/摄像头/屏幕录制功能只能在安全上下文（localhost 或 HTTPS 环境）中使用
+点击左上角的 `12393:12393`，如下图，或者在浏览器输入 `http://localhost:12393`
+
-## 预装模型说明
+**恭喜你，成功了**，和你的虚拟伴侣对话吧！
-默认镜像已预装大部分语音识别（ASR）和文本转语音（TTS）模型。但考虑到体积因素（约 8GB，会使总体积增加到 25GB）和性能表现，默认构建不包含以下模型：
-- Bark TTS
-- 原版 OpenAI Whisper（注意：这里指的是 Whisper，而非 WhisperCPP）
+## 使用终端命令安装 Docker
+1. 安装 Docker Desktop。
+
+
-如需在镜像中包含这些模型，请在构建时添加参数：
```bash
---build-arg INSTALL_ORIGINAL_WHISPER=true --build-arg INSTALL_BARK=true
+winget install -e --id Docker.DockerDesktop
```
-## 部署步骤
+
+
-1. 在构建镜像前，请先检查并调整 `conf.yaml` 配置文件（当前配置会被构建进镜像）
+```bash
+brew install --cask docker
+```
+
+
+
+
+2. 拉取最新镜像。
-2. 构建 Docker 镜像：
```bash
-docker build -t open-llm-vtuber .
+docker pull openllmvtuber/open-llm-vtuber:latest
+```
+
+3. 打包容器。可以更改 `docker-compose.yml`，默认的也可以直接一键启动。
+```bash
+cd OLV-Docker-Config
+```
+
+```bash
+docker-compose up -d
+```
+
+4. 查看容器的日志。
+```bash
+docker logs -f open-llm-vtuber-latest
```
- > 提示：构建过程可能需要较长时间
-3. 准备 `conf.yaml` 配置文件
- 您可以从项目仓库获取，或直接通过此[链接](https://raw.githubusercontent.com/Open-LLM-VTuber/Open-LLM-VTuber/main/conf.yaml)下载
+5. 在浏览器打开web界面。
-4. 运行容器：
+等到日志里出现 `Uvicorn running on http://0.0.0.0:12393` 以后，在浏览器输入 `http://localhost:12393` 打开web界面。
+
+至此，你就成功部署了 Open LLM VTuber！
+
+## 更新
+### 更新配置文件
+有 git 更新和手动更新两种方式。
+#### git 更新
+在 `OLV-Docker-Config` 目录下运行以下命令：
+```bash
+git stash
+git pull
+git stash pop
+```
+如有冲突请手动处理。
+
+#### 手动更新
+手动对比新版 `conf.yaml` 与旧版 `conf.yaml`的不同，将需要更新的部分复制到旧的 `conf.yaml` 中。
+
+ChatGPT推荐这个网站 [DiffCheck.ai — YAML Diff Checker](https://diffcheck.ai/yaml)，你也可以自己找合适的网站。
+
+### 拉取最新镜像
+如果用 `Docker Desktop`, 点击 `Image` 旁边的 `Pull` 即可。
+
+如果用终端，运行以下命令：
```bash
-docker run -it --net=host --rm -v $(pwd)/conf.yaml:/app/conf.yaml -p 12393:12393 open-llm-vtuber
+docker pull openllmvtuber/open-llm-vtuber:latest
```
- 注意：请将 `$(pwd)/conf.yaml` 替换为您的配置文件实际路径
-5. 访问 `localhost:12393` 进行测试
+### 重启容器
+如果用 `Docker Desktop`, 点击 `Containers` 的 `Restart` 即可。
+
+如果用终端，运行以下命令：
+```bash
+docker-compose up -d
+```
\ No newline at end of file
diff --git a/docs/user-guide/backend/llm.md b/docs/user-guide/backend/llm.md
index 56074a43d..bb5dbf5ac 100644
--- a/docs/user-guide/backend/llm.md
+++ b/docs/user-guide/backend/llm.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 4
+sidebar_position: 5
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
diff --git a/docs/user-guide/backend/translate.md b/docs/user-guide/backend/translate.md
index 6b0083636..c115162d8 100644
--- a/docs/user-guide/backend/translate.md
+++ b/docs/user-guide/backend/translate.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 7
+sidebar_position: 8
---
# 翻译 (Translate)
diff --git a/docs/user-guide/backend/tts.md b/docs/user-guide/backend/tts.md
index 98ef6b0bd..0b9066714 100644
--- a/docs/user-guide/backend/tts.md
+++ b/docs/user-guide/backend/tts.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 6
+sidebar_position: 7
---
# 语音合成 (TTS)
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/development-guide/backend/docker.mdx b/i18n/en/docusaurus-plugin-content-docs/current/development-guide/backend/docker.mdx
new file mode 100644
index 000000000..6120c1cf8
--- /dev/null
+++ b/i18n/en/docusaurus-plugin-content-docs/current/development-guide/backend/docker.mdx
@@ -0,0 +1,54 @@
+---
+sidebar_position: 2
+---
+
+# Docker Local Build Guide
+
+> If you want to deploy Open-LLM-VTuber using our pre-built Docker images, see [Docker Deployment](../../user-guide/backend/docker.md)
+
+## Notes
+- Multi-architecture image builds and pushes are automatically handled by GitHub Actions.
+- This document is only for developers who want to build debug images locally, without using `docker buildx`.
+
+## Local Environment Requirements
+- `git` installed
+- Docker installed (Docker Engine 24+ or the latest stable Docker Desktop recommended)
+- Optional: Docker Compose plugin installed (only if you need `docker compose`)
+- At least `10GB` of free disk space recommended (first build downloads many dependencies)
+
+You can verify your environment with these commands:
+```
+git --version
+docker --version
+docker compose version
+```
+
+## Get the Code
+```
+git clone https://github.com/Open-LLM-VTuber/Open-LLM-VTuber.git
+cd Open-LLM-VTuber
+```
+
+## Build Image Locally (Single Architecture)
+Run in the project root directory:
+```
+docker build -t openllmvtuber/open-llm-vtuber:local -f dockerfile .
+```
+
+To customize the image name or tag, replace `openllmvtuber/open-llm-vtuber:local` as needed.
+
+## Optional: Local Run Verification
+Before running, ensure `conf/conf.yaml` exists:
+```
+docker run --rm -it \
+ -p 12393:12393 \
+ -v "$(pwd)/conf:/app/conf" \
+ -v "$(pwd)/models:/app/models" \
+ openllmvtuber/open-llm-vtuber:local
+```
+
+## Clean Up Local Docker Data
+```
+docker system prune -a --volumes
+```
+
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/quick-start.md b/i18n/en/docusaurus-plugin-content-docs/current/quick-start.md
index d013b1efd..9f23b7deb 100644
--- a/i18n/en/docusaurus-plugin-content-docs/current/quick-start.md
+++ b/i18n/en/docusaurus-plugin-content-docs/current/quick-start.md
@@ -55,6 +55,24 @@ This project supports various backends for speech recognition (ASR), large langu
For the components selected in this quick start guide, you will need a CPU with normal speed (for ASR), a GPU supported by Ollama (for LLM), and an internet connection (for TTS).
+## Docker Quick Start
+
+:::info Note
+Docker is the easiest deployment method for beginners. It can deploy all components with one click and requires no manual configuration.
+:::
+
+If you're interested in Docker, please refer to the [Docker Deployment Guide](./user-guide/backend/docker.md).
+
+If you're not interested, you can skip ahead to the general setup and start from the next step: [Environment Preparation](#environment-preparation).
+
+:::note Current Docker image platform support is as follows
+| Platform | CPU Support | NVIDIA GPU Support | AMD/Intel GPU Support |
+|----------|-------------|--------------------|-----------------------|
+| Linux | ✅ | ✅ | ❌ |
+| Windows | ✅ | ✅ [(requires Nvidia driver installation)](#nvidia-gpu-support) | ❌ |
+| macOS | ✅ | ❌ | ❌ |
+:::
+
## Environment Preparation
### Install Git
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/agent.md b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/agent.md
index 7cfb62dc1..1b9484b88 100644
--- a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/agent.md
+++ b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/agent.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 5
+sidebar_position: 6
---
# Agent
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/asr.md b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/asr.md
index 5a378f67b..0aa58910a 100644
--- a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/asr.md
+++ b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/asr.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 3
+sidebar_position: 4
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/docker.md b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/docker.md
index 8c0745436..5c679b53d 100644
--- a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/docker.md
+++ b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/docker.md
@@ -1,56 +1,260 @@
---
-sidebar_position: 8
+sidebar_position: 3
---
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
# Docker Deployment
-:::danger
-Due to significant refactoring, the Docker image has not yet been updated to version `v1.0.0`, but it will be updated soon.
+> For building Docker images locally, refer to the [Docker Local Build Guide](../../development-guide/backend/docker.mdx)
+
+## About Our Docker Team
+We have established the [openllmvtuber team](https://hub.docker.com/orgs/openllmvtuber/members) on Docker Hub.
+The Docker images are currently maintained by [@Harry_Y](https://github.com/Harry-Yu-Shuhang).
+
+## Download configuration files
+
+### Git clone (for users familiar with git)
+First, [install git following the Quick Start](../../quick-start.md#install-git), then download the Docker user configuration:
+
+```bash
+git clone https://github.com/Open-LLM-VTuber/OLV-Docker-Config
+```
+
+### Download ZIP (for users without coding experience)
+:::warning
+If you download it this way, the configuration file `conf.yaml` can only be [updated manually](#manual-update).
+:::
+First, [click here to go to the user configuration repository](https://github.com/Open-LLM-Vtuber/OLV-Docker-Config)
+
+Then, on the repository page, click `Code` -> `Download ZIP` to download the Docker user configuration, as shown below.
+
+
+
+## Edit configuration files
+If you want to change any settings, edit the `conf.yaml` file.
+
+:::info
+The default `conf.yaml` is in English. If you want to replace it with Chinese, copy `conf.ZH.default.yaml` from the `config_templates` folder, go back one level, and replace the original `conf.yaml`.
+:::
+
+If you're a beginner, it's recommended to use the default configuration file for one-click startup.
+
+If you want to change settings like character profile, model, ASR, TTS, etc., modify the corresponding fields in `conf.yaml`.
+
+For information about each field in the config file, refer to the comments inside the configuration file.
+
+## Install Docker
+
+:::tip About installation methods
+Two installation methods are supported currently:
+- If you're a beginner, we recommend [using Docker Desktop](#install-docker-using-docker-desktop).
+- If you're familiar with Docker, you can [use terminal commands](#install-docker-using-terminal-commands).
+:::
+
+:::caution About GPU support
+Currently **only CPU and Nvidia GPU** are supported. Nvidia GPUs require proper Nvidia driver configuration. If you haven't set it up yet, please [**click here to view the setup guide in Quick Start**](../../quick-start.md#nvidia-gpu-support).
+
+If you don't plan to use a GPU and will instead **use API calls** (this is **the best experience for most users**) or use CPU only, you can skip this step.
:::
-:::warning
-⚠️ Please note: This feature is currently in an experimental stage but works normally in most cases.
+:::note About our Docker team
+We created an [openllmvtuber team on Docker Hub](https://hub.docker.com/orgs/openllmvtuber/members). Docker images are currently maintained by [@Harry_Y](https://github.com/Harry-Yu-Shuhang).
:::
-You can choose to build the Docker image yourself or pull the pre-built image directly from Docker Hub: [](https://hub.docker.com/r/openllmvtuber/open-llm-vtuber)
+## Install Docker using Docker Desktop
-## Usage Notes
+:::warning
+Docker Desktop may hang during restart; try to avoid restarting when possible. If it becomes unresponsive for a long time, kill the Docker Desktop background process in Task Manager (Windows) or Activity Monitor (macOS) and then start it again.
+:::
+
+### Download Docker Desktop
+
+Visit the [Docker Desktop download page](https://www.docker.com/products/docker-desktop).
+
+Click "Download Docker Desktop"
+
+
+
+Choose the version that matches your computer.
+
+:::tip How to choose the right version for your computer
+- **Mac Apple Silicon** → Newer Macs (M1/M2/M3 chips)
+- **Mac Intel Chip** → Older Macs (Intel processors)
+- **Windows AMD64** → Most Windows PCs (Intel/AMD 64-bit)
+- **Windows ARM64** → Rare, for ARM-based Windows (e.g., Surface Pro X)
+:::
+
+If you are not sure, check your system settings as follows:
+
+
+
+
+1. Right-click "This PC" → Properties
+2. Under "System type" check:
+ - "x64-based processor" → Choose **Windows AMD64**
+ - "ARM-based processor" → Choose **Windows ARM64**
-- The Docker image is large (about 13GB), and some optional models require additional downloads when used, occupying more storage space
-- Only supports devices with NVIDIA GPUs
-- Requires installation and configuration of [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) to support GPU passthrough
-- Current issue: Some models need to be re-downloaded after the container stops (this will be fixed in future versions)
-- Building the image on ARM architecture devices is not recommended due to potential build failures with the gRPC dependency ([related issue](https://github.com/grpc/grpc/issues/34998))
-- If running on a remote server, HTTPS must be configured. This is because the frontend webpage's microphone/camera/screen recording features can only be used in a secure context (localhost or HTTPS environment)
+
+
-## Pre-installed Model Information
+1. Click the Apple icon at the top-left → "About This Mac"
+2. Check the "Chip" (or "Processor") field:
+ - Shows **Apple M1/M2/M3** → Choose **Mac Apple Silicon**
+ - Shows **Intel** → Choose **Mac Intel Chip**
-The default image comes with most Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) models pre-installed. However, considering size factors (about 8GB, which would increase the total size to 25GB) and performance, the default build does not include the following models:
-- Bark TTS
-- Original OpenAI Whisper (Note: This refers to Whisper, not WhisperCPP)
+
+
+
+### Start Docker Desktop
+
+Double-click the downloaded installer and follow the prompts to install.
+
+After installation, click the Docker Desktop icon to start Docker.
+
+On first start, Docker Desktop will ask you to sign in to a Docker Hub account. If you don't have one, register first.
+
+### Pull the Docker image
+
+Click the top menu "Search" icon (or use the shortcut `Ctrl + K` on Windows or `Cmd + K` on macOS).
+
+
+
+Enter the following in the search box. When you find it, click the "Pull" button on the right.
+
+```
+openllmvtuber/open-llm-vtuber:latest
+```
+
+
+
+### Configure LLM
+:::info About how to use LLM
+If you use a local model (for example the default `Ollama`), this step is required.
+
+If you choose API calls, you can skip this step.
+:::
+
+:::info
+If you are a beginner with no coding background
+We recommend following these steps to use the default `Ollama` model and avoid extra configuration.
+
+
+ 1. Download and install the Ollama client from the [Ollama official site](https://ollama.com/).
+
+ 2. Verify Ollama installation:
+ ```bash
+ ollama --version
+ ```
+
+ 3. Download and run a model (the default config uses `qwen2.5:latest` as an example):
+ ```bash
+ ollama run qwen2.5:latest
+ ```
+
+ 4. List installed models:
+ ```bash
+ ollama list
+ ```
+
+:::
+
+For more details, refer to the LLM configuration section in [Quick Start](/docs/quick-start.md#3-configure-llm).
+
+### Run the Docker container
+
+Click "Images", find **openllmvtuber/open-llm-vtuber**, and click the run button on the right.
+
+
+Open "Optional settings" and configure as shown below:
+
+
+### Open the web interface in your browser
+When you see lines like the ones below, the service has started successfully. The first pull may be slow because it installs necessary tools—please be patient.
+
+
+Click the `12393:12393` link in the top-left as shown below, or open `http://localhost:12393` in your browser.
+
+
+**Congratulations — it's working!** Chat with your virtual companion!
+
+## Install Docker using terminal commands
+1. Install Docker Desktop.
+
+
+
+```bash
+winget install -e --id Docker.DockerDesktop
+```
+
+
+
-To include these models in the image, add the following parameters when building:
```bash
---build-arg INSTALL_ORIGINAL_WHISPER=true --build-arg INSTALL_BARK=true
+brew install --cask docker
```
-## Deployment Steps
+
+
-1. Before building the image, check and adjust the `conf.yaml` configuration file (the current configuration will be built into the image)
+2. Pull the latest image.
-2. Build the Docker image:
```bash
-docker build -t open-llm-vtuber .
+docker pull openllmvtuber/open-llm-vtuber:latest
```
- > Note: The build process may take a considerable amount of time
-3. Prepare the `conf.yaml` configuration file
- You can obtain it from the project repository or download it directly via this [link](https://raw.githubusercontent.com/Open-LLM-VTuber/Open-LLM-VTuber/main/conf.yaml)
+3. Start the container. You can modify `docker-compose.yml` if needed; the default can also be started with one command.
+```bash
+cd OLV-Docker-Config
+```
+
+```bash
+docker-compose up -d
+```
-4. Run the container:
+4. View container logs.
```bash
-docker run -it --net=host --rm -v $(pwd)/conf.yaml:/app/conf.yaml -p 12393:12393 open-llm-vtuber
+docker logs -f open-llm-vtuber-latest
```
- Note: Replace `$(pwd)/conf.yaml` with the actual path to your configuration file
-5. Access `localhost:12393` for testing
\ No newline at end of file
+5. Open the web interface in your browser.
+
+After the logs show `Uvicorn running on http://0.0.0.0:12393`, open `http://localhost:12393` in your browser to access the web interface.
+
+That's it — you have successfully deployed Open LLM VTuber!
+
+## Update
+
+### Update configuration file
+There are two ways to update: via git or manually.
+
+#### Git update
+Run the following commands in the `OLV-Docker-Config` directory:
+```bash
+git stash
+git pull
+git stash pop
+```
+If there are conflicts, please resolve them manually.
+
+#### Manual update
+Manually compare the new `conf.yaml` with the old `conf.yaml` and copy the parts that need updating into the old `conf.yaml`.
+
+ChatGPT recommends this website: [DiffCheck.ai — YAML Diff Checker](https://diffcheck.ai/yaml), but you can also use any other suitable site.
+
+### Pull the latest image
+If you're using Docker Desktop, click the `Pull` button next to `Image`.
+
+If you're using the terminal, run:
+```bash
+docker pull openllmvtuber/open-llm-vtuber:latest
+```
+
+### Restart the container
+If you're using Docker Desktop, click `Restart` under `Containers`.
+
+If you're using the terminal, run:
+```bash
+docker-compose up -d
+```
\ No newline at end of file
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/llm.md b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/llm.md
index 6ef73a2ad..cfbeb44e4 100644
--- a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/llm.md
+++ b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/llm.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 4
+sidebar_position: 5
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/translate.md b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/translate.md
index 27168c723..eace054e4 100644
--- a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/translate.md
+++ b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/translate.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 7
+sidebar_position: 8
---
# Translation
diff --git a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/tts.md b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/tts.md
index 708fd70e6..10cf657ec 100644
--- a/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/tts.md
+++ b/i18n/en/docusaurus-plugin-content-docs/current/user-guide/backend/tts.md
@@ -1,5 +1,5 @@
---
-sidebar_position: 6
+sidebar_position: 7
---
# Speech Synthesis (TTS)
diff --git a/static/docker_img/click_12393.png b/static/docker_img/click_12393.png
new file mode 100644
index 000000000..ce87e6842
Binary files /dev/null and b/static/docker_img/click_12393.png differ
diff --git a/static/docker_img/click_search.png b/static/docker_img/click_search.png
new file mode 100644
index 000000000..eec095b40
Binary files /dev/null and b/static/docker_img/click_search.png differ
diff --git a/static/docker_img/container_config_cn.png b/static/docker_img/container_config_cn.png
new file mode 100644
index 000000000..220377367
Binary files /dev/null and b/static/docker_img/container_config_cn.png differ
diff --git a/static/docker_img/container_config_en.png b/static/docker_img/container_config_en.png
new file mode 100644
index 000000000..5994c4237
Binary files /dev/null and b/static/docker_img/container_config_en.png differ
diff --git a/static/docker_img/container_config_raw.png b/static/docker_img/container_config_raw.png
new file mode 100644
index 000000000..98b0afd8d
Binary files /dev/null and b/static/docker_img/container_config_raw.png differ
diff --git a/static/docker_img/docker_run_success.png b/static/docker_img/docker_run_success.png
new file mode 100644
index 000000000..13892891e
Binary files /dev/null and b/static/docker_img/docker_run_success.png differ
diff --git a/static/docker_img/download_docker_conf_repo.png b/static/docker_img/download_docker_conf_repo.png
new file mode 100644
index 000000000..076a6e53b
Binary files /dev/null and b/static/docker_img/download_docker_conf_repo.png differ
diff --git a/static/docker_img/download_docker_desktop.png b/static/docker_img/download_docker_desktop.png
new file mode 100644
index 000000000..23c501e5c
Binary files /dev/null and b/static/docker_img/download_docker_desktop.png differ
diff --git a/static/docker_img/openllmvtuber_image.png b/static/docker_img/openllmvtuber_image.png
new file mode 100644
index 000000000..d2bf657d3
Binary files /dev/null and b/static/docker_img/openllmvtuber_image.png differ
diff --git a/static/docker_img/run_image.png b/static/docker_img/run_image.png
new file mode 100644
index 000000000..6fa2cccad
Binary files /dev/null and b/static/docker_img/run_image.png differ