diff --git a/.vitepress/config.js b/.vitepress/config.js
index 7f4a56a..0a2674c 100644
--- a/.vitepress/config.js
+++ b/.vitepress/config.js
@@ -17,61 +17,111 @@ export default defineConfig({
     /^http:\/\/localhost/
   ],
 
-  themeConfig: {
-    nav: [
-      { text: '首页', link: '/' },
-      { text: '入门指南', link: '/guide/requirements' },
-      { text: 'API 参考', link: '/api/overview' }
-    ],
-
-    sidebar: [
-      {
-        text: '入门指南',
-        items: [
-          { text: '项目介绍', link: '/guide/introduction' },
-          { text: '环境要求', link: '/guide/requirements' },
-          { text: '快速部署', link: '/guide/deployment' },
-          { text: '首次使用', link: '/guide/first-use' }
-        ]
-      },
-      {
-        text: '配置说明',
-        items: [
-          { text: '配置概览', link: '/config/overview' },
-          { text: '实例配置', link: '/config/instances' },
-          { text: '代理设置', link: '/config/proxy' }
-        ]
-      },
-      {
-        text: 'API 参考',
-        items: [
-          { text: '接口概览', link: '/api/overview' },
-          { text: 'Chat Completions', link: '/api/chat' },
-          { text: 'Models', link: '/api/models' },
-          { text: 'Cookies', link: '/api/cookies' }
-        ]
-      },
-      {
-        text: '运维管理',
-        items: [
-          { text: 'Web 管理界面', link: '/admin/webui' },
-          { text: 'Linux 部署', link: '/admin/linux' },
-          { text: '故障排查', link: '/admin/troubleshooting' }
-        ]
+  locales: {
+    root: {
+      label: '简体中文',
+      lang: 'zh-CN',
+      themeConfig: {
+        nav: [
+          { text: '首页', link: '/' },
+          { text: '入门指南', link: '/guide/requirements' },
+          { text: 'API 参考', link: '/api/overview' }
+        ],
+        sidebar: [
+          {
+            text: '入门指南',
+            items: [
+              { text: '项目介绍', link: '/guide/introduction' },
+              { text: '环境要求', link: '/guide/requirements' },
+              { text: '快速部署', link: '/guide/deployment' },
+              { text: '首次使用', link: '/guide/first-use' }
+            ]
+          },
+          {
+            text: '配置说明',
+            items: [
+              { text: '配置概览', link: '/config/overview' },
+              { text: '实例配置', link: '/config/instances' },
+              { text: '代理设置', link: '/config/proxy' }
+            ]
+          },
+          {
+            text: 'API 参考',
+            items: [
+              { text: '接口概览', link: '/api/overview' },
+              { text: 'Chat Completions', link: '/api/chat' },
+              { text: 'Models', link: '/api/models' },
+              { text: 'Cookies', link: '/api/cookies' }
+            ]
+          },
+          {
+            text: '运维管理',
+            items: [
+              { text: 'Web 管理界面', link: '/admin/webui' },
+              { text: 'Linux 部署', link: '/admin/linux' },
+              { text: '故障排查', link: '/admin/troubleshooting' }
+            ]
+          }
+        ],
+        outline: { label: '页面导航' },
+        docFooter: { prev: '上一页', next: '下一页' }
       }
-    ],
+    },
+    en: {
+      label: 'English',
+      lang: 'en-US',
+      link: '/en/',
+      themeConfig: {
+        nav: [
+          { text: 'Home', link: '/en/' },
+          { text: 'Guide', link: '/en/guide/requirements' },
+          { text: 'API Reference', link: '/en/api/overview' }
+        ],
+        sidebar: [
+          {
+            text: 'Guide',
+            items: [
+              { text: 'Introduction', link: '/en/guide/introduction' },
+              { text: 'Requirements', link: '/en/guide/requirements' },
+              { text: 'Deployment', link: '/en/guide/deployment' },
+              { text: 'First Use', link: '/en/guide/first-use' }
+            ]
+          },
+          {
+            text: 'Configuration',
+            items: [
+              { text: 'Overview', link: '/en/config/overview' },
+              { text: 'Instances', link: '/en/config/instances' },
+              { text: 'Proxy Settings', link: '/en/config/proxy' }
+            ]
+          },
+          {
+            text: 'API Reference',
+            items: [
+              { text: 'API Overview', link: '/en/api/overview' },
+              { text: 'Chat Completions', link: '/en/api/chat' },
+              { text: 'Models', link: '/en/api/models' },
+              { text: 'Cookies', link: '/en/api/cookies' }
+            ]
+          },
+          {
+            text: 'Operation',
+            items: [
+              { text: 'Web UI', link: '/en/admin/webui' },
+              { text: 'Linux Deployment', link: '/en/admin/linux' },
+              { text: 'Troubleshooting', link: '/en/admin/troubleshooting' }
+            ]
+          }
+        ],
+        outline: { label: 'On this page' },
+        docFooter: { prev: 'Previous page', next: 'Next page' }
+      }
+    }
+  },
 
+  themeConfig: {
     socialLinks: [
       { icon: 'github', link: 'https://github.com/foxhui/WebAI2API' }
-    ],
-
-    outline: {
-      label: '页面导航'
-    },
-
-    docFooter: {
-      prev: '上一页',
-      next: '下一页'
-    }
+    ]
   }
 })
diff --git a/docs/en/admin/linux.md b/docs/en/admin/linux.md
new file mode 100644
index 0000000..bce81f5
--- /dev/null
+++ b/docs/en/admin/linux.md
@@ -0,0 +1,88 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Linux Deployment
+
+[Docker users can ignore this] Special configuration instructions for running WebAI2API on Linux servers.
+
+## 1. Install Necessary Dependencies
+
+Essential dependencies for Linux command-line mode that allow you to run graphical applications in a Linux environment without a desktop environment.
+
+### Ubuntu/Debian
+
+```bash
+sudo apt-get update
+sudo apt-get install xvfb x11vnc
+```
+
+### CentOS/RHEL
+
+```bash
+sudo yum install xorg-x11-server-Xvfb x11vnc
+```
+
+### Arch Linux
+
+```bash
+sudo pacman -S xorg-server-xvfb x11vnc
+```
+
+## 2. Run the Program
+
+Run the program using a virtual display and view it remotely via VNC. (The program will handle all the setup for you.)
+
+```bash
+npm start -- -xvfb -vnc
+```
+
+This will automatically:
+- Start the Xvfb virtual display.
+- Start the x11vnc server.
+- Allow you to view the VNC screen directly through the WebUI.
+
+## 3. Connecting to the Program
+
+### Via WebUI (Recommended)
+
+Once the service is started, visit the "VNC Display" page in the WebUI to view it directly.
+
+### Via SSH Tunnel
+
+::: tip Tip
+The port might not always be 5900; the program will automatically search for an available VNC port in the range 5900-5999.
+:::
+
+```bash
+# In your local terminal
+ssh -L 5900:127.0.0.1:5900 root@Server_IP
+```
+
+Then use a VNC client to connect to `127.0.0.1:5900`.
+
+## Alternative Method: Terminal X11 Forwarding
+
+This method is not recommended unless you prefer to configure your own environment.
+
+1. Install an X Server locally (e.g., VcXsrv, Xming).
+2. Use a terminal that supports X11 forwarding (e.g., WindTerm).
+3. Enable X11 forwarding in your SSH session.
+
+```bash
+ssh -X user@server
+```
+
+## FAQ
+
+### Port Already Occupied
+
+If port 5900 is already in use, the VNC server will automatically look for an available port in the 5901-5999 range.
+
+### Display Number Conflict
+
+Xvfb will automatically search for an available display number starting from 50 to avoid conflicts with existing X servers.
+
+### Unable to Connect to VNC
+
+Please check if the dependencies were installed successfully.
diff --git a/docs/en/admin/troubleshooting.md b/docs/en/admin/troubleshooting.md
new file mode 100644
index 0000000..a858556
--- /dev/null
+++ b/docs/en/admin/troubleshooting.md
@@ -0,0 +1,148 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Troubleshooting
+
+Diagnosis and solutions for common problems.
+
+## Operational Issues
+
+### Window Forcing Itself to Foreground
+
+**Problem**: The browser window actively brings itself to the foreground during a task.
+
+**Solution**:
+- On Windows and macOS, you can use a separate virtual desktop (Win + Tab) specifically for the program.
+- On Linux, use Xvfb mode.
+
+## Request Issues
+
+### Request Rejected (429 Too Many Requests)
+
+**Problem**: Too many concurrent requests; the queue is full.
+
+**Solution**:
+- Enable streaming mode (`stream: true`), which allows for unlimited queuing.
+- Reduce the number of concurrent requests.
+- Increase the `queue.queueBuffer` value in your configuration.
+
+### Request Timeout
+
+**Problem**: The task did not complete within 120 seconds.
+
+**Solution**:
+- Enable streaming mode and use the heartbeat mechanism to keep the connection alive.
+- Check if your network connection is stable.
+- Some complex prompts may simply require more time.
+
+## Verification Issues
+
+### reCAPTCHA Failure
+
+**Problem**: Returns `recaptcha validation failed`.
+
+**Solution**:
+- Reduce the frequency of requests.
+- Enter Login Mode to complete the verification manually.
+- Use a stable and clean IP address.
+- Check IP cleanliness using tools like [ping0.cc](https://ping0.cc).
+
+### Cloudflare Challenge
+
+**Problem**: The browser is stuck on the Cloudflare verification page.
+
+**Solution**:
+- Use VNC to complete the verification manually.
+- Change your IP address.
+- Avoid using datacenter IPs.
+
+## Login Issues
+
+### Login State Lost
+
+**Problem**: You are asked to log in again after a service restart.
+
+**Solution**:
+- Ensure the `data` directory is persistent.
+- Verify that the `userDataMark` configuration is correct.
+- Avoid deleting browser data directories.
+
+### OAuth Login Failure
+
+**Problem**: Login redirects via Google or other OAuth providers fail.
+
+**Solution**:
+- Ensure `accounts.google.com` is accessible.
+- Check if your proxy configuration is correct.
+- Try changing your IP address.
+
+## Browser Issues
+
+### Browser Fails to Start
+
+**Problem**: Camoufox cannot start.
+
+**Solution**:
+```bash
+# Re-initialize Camoufox
+npm run init
+```
+
+### Out of Memory
+
+**Problem**: The browser crashes due to insufficient memory.
+
+**Solution**:
+- Increase server RAM (2GB+ recommended).
+- Reduce the number of simultaneously running browser instances.
+- Ensure `--shm-size=2gb` is set in Docker environments.
+
+## Network Issues
+
+### Proxy Connection Failed
+
+**Problem**: Unable to connect to the proxy server.
+
+**Solution**:
+- Check the proxy server address and port.
+- Verify proxy authentication credentials.
+- Test if the proxy server is working correctly.
+
+### Target Website Inaccessible
+
+**Problem**: Unable to access sites like LMArena or Gemini.
+
+**Solution**:
+- Check your network connectivity.
+- Try using a proxy.
+- Confirm the target website is not blocked.
+
+## Log Diagnosis
+
+### View Detailed Logs
+
+Set the log level in `config.yaml`:
+
+```yaml
+logLevel: debug
+```
+
+### Common Log Messages
+
+| Log Content | Description |
+| --- | --- |
+| `Worker pool initialization failed` | Check configuration and network. |
+| `Worker does not support model` | Verify if the model name is correct. |
+| `Verification timeout` | Manual verification is required. |
+| `Page closed` | The browser may have crashed. |
+
+## Getting Help
+
+If the above methods do not resolve your issue:
+
+1. Check [GitHub Issues](https://github.com/foxhui/WebAI2API/issues).
+2. Submit an Issue including:
+   - Log output (with `logLevel: debug`).
+   - Your configuration file (hide sensitive information).
+   - Your OS and Node.js version.
diff --git a/docs/en/admin/webui.md b/docs/en/admin/webui.md
new file mode 100644
index 0000000..f6682dc
--- /dev/null
+++ b/docs/en/admin/webui.md
@@ -0,0 +1,87 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Web Management Interface
+
+WebAI2API provides a built-in Web Management Interface (WebUI) for monitoring and managing the service.
+
+::: warning Note
+The WebUI and management interfaces only use the API Token for authentication during the handshake phase. Transmissions are not encrypted. If you are using this on a public network, please use a professional web server like Caddy or Nginx to provide HTTPS encryption!
+:::
+
+## Access URL
+
+```
+http://localhost:3000
+```
+
+On your first visit, you will need to enter the API Token set in your configuration file (`auth` field) for authentication.
+
+## Functional Modules
+
+### Dashboard
+
+The dashboard displays the system's operational status:
+
+- **System Status**: Version, uptime, and running mode.
+- **Business Statistics**: Number of windows and instances.
+- **Queue Status**: Lists of tasks currently being processed or waiting in the queue.
+
+### System Management
+
+The system management page provides:
+
+- **Service Control**
+  - Normal Restart
+  - Restart in Login Mode
+  - Specific Worker Login
+  - Stop Service
+  - Adapter Settings (descriptions, model management, feature toggles)
+
+- **Cache Management**
+  - View temporary files.
+  - Clear cache.
+
+- **Data Management**
+  - View browser data directories.
+  - Delete unused data directories.
+
+### VNC Display
+
+When starting with `-xvfb -vnc` in a Linux environment, you can view and operate the virtual display directly through the WebUI:
+
+- Connect/Disconnect VNC.
+- Full-screen mode.
+- View VNC status information.
+
+::: tip Note
+The VNC display feature requires the service to be running in Xvfb + VNC mode.
+:::
+
+### Configuration Management
+
+- **Server Configuration**: Port, authentication, and heartbeat settings.
+- **Adapter Configuration**: Exclusive settings for each backend.
+- **Browser Settings**: Path, headless mode, and proxy settings.
+
+### Instance Management
+
+Manage browser instance and Worker configurations (requires a restart to take effect).
+
+## Quick Actions
+
+### Restarting in Login Mode
+
+1. Go to the "Cache & Restart" page.
+2. Click the dropdown arrow next to the "Restart" button.
+3. Select the restart mode:
+   - **Normal Restart**: Restarts in standard mode.
+   - **Login Mode Restart**: Restarts with the `-login` parameter.
+   - **Specific Worker Login**: Select a specific Worker to enter login mode.
+
+### Clearing Cache
+
+1. Go to the "Cache & Restart" page.
+2. Find the "Cache Management" area.
+3. Click the "Clear Cache" button.
diff --git a/docs/en/api/chat.md b/docs/en/api/chat.md
new file mode 100644
index 0000000..d7e470f
--- /dev/null
+++ b/docs/en/api/chat.md
@@ -0,0 +1,175 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Chat Completions
+
+The chat generation interface, compatible with the OpenAI Chat Completions API.
+
+## Endpoint
+
+```
+POST /v1/chat/completions
+```
+
+## Request Parameters
+
+| Parameter | Type | Required | Description |
+| --- | --- | --- | --- |
+| `model` | string | ✅ | Model name |
+| `messages` | array | ✅ | List of messages |
+| `stream` | boolean | ❌ | Whether to enable streaming responses (recommended) |
+
+### messages Format
+
+```json
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": "Generate a cute cat"
+    }
+  ]
+}
+```
+
+### Multi-modal Requests (Image-to-Image / Image-to-Text)
+
+```json
+{
+  "messages": [
+    {
+      "role": "user",
+      "content": [
+        {
+          "type": "text",
+          "text": "Make this image more vibrant"
+        },
+        {
+          "type": "image_url",
+          "image_url": {
+            "url": "data:image/jpeg;base64,/9j/4AAQ..."
+          }
+        }
+      ]
+    }
+  ]
+}
+```
+
+## Image Limitations
+
+| Item | Description |
+| --- | --- |
+| Supported Formats | PNG, JPEG, GIF, WebP |
+| Quantity Limit | Default 5, Maximum 10 |
+| Data Format | Base64 Data URL (`data:image/jpeg;base64,...`) |
+| Auto-transformation | The server automatically converts images to JPG format |
+
+## Non-streaming Response
+
+### Request Example
+
+```bash
+curl -X POST http://localhost:3000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer sk-your-key" \
+  -d '{
+    "model": "gemini-3-pro-image-preview",
+    "messages": [
+      {
+        "role": "user",
+        "content": "generate a cat"
+      }
+    ]
+  }'
+```
+
+### Response Example
+
+```json
+{
+  "id": "chatcmpl-1732374740123",
+  "object": "chat.completion",
+  "created": 1732374740,
+  "model": "gemini-3-pro-image-preview",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "![generated](data:image/jpeg;base64,/9j/4AAQ...)"
+      },
+      "finish_reason": "stop"
+    }
+  ]
+}
+```
+
+## Streaming Response
+
+::: tip Recommendation
+Streaming mode includes a heartbeat mechanism to keep the connection alive, preventing timeouts during long generations.
+:::
+
+### Request Example
+
+```bash
+curl -X POST http://localhost:3000/v1/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer sk-your-key" \
+  -d '{
+    "model": "gemini-3-pro-image-preview",
+    "stream": true,
+    "messages": [
+      {
+        "role": "user",
+        "content": "generate a cat"
+      }
+    ]
+  }'
+```
+
+### Response Example
+
+```
+data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1732374740,"model":"gemini-3-pro-image-preview","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}
+
+: keep-alive
+
+: keep-alive
+
+data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1732374740,"model":"gemini-3-pro-image-preview","choices":[{"index":0,"delta":{"content":"![generated](data:image/jpeg;base64,/9j/4AAQ...)"},"finish_reason":"stop"}]}
+
+data: [DONE]
+```
+
+## Error Handling
+
+### Queue Full (429)
+
+```json
+{
+  "error": {
+    "message": "Queue is full",
+    "type": "rate_limit_exceeded",
+    "code": "QUEUE_FULL"
+  }
+}
+```
+
+::: tip Solution
+Enabling streaming mode (`stream: true`) allows for unlimited queuing, avoiding 429 errors.
+:::
+
+### Model Not Supported (400)
+
+```json
+{
+  "error": {
+    "message": "No Worker supports model: invalid-model",
+    "type": "invalid_request_error",
+    "code": "MODEL_NOT_FOUND"
+  }
+}
+```
diff --git a/docs/en/api/cookies.md b/docs/en/api/cookies.md
new file mode 100644
index 0000000..c6cdd8c
--- /dev/null
+++ b/docs/en/api/cookies.md
@@ -0,0 +1,74 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Cookies API
+
+Retrieve cookies from browser instances, which can be used by other tools.
+
+## Endpoint
+
+```
+GET /v1/cookies
+```
+
+## Query Parameters
+
+| Parameter | Type | Required | Description |
+| --- | --- | --- | --- |
+| `name` | string | ❌ | Browser instance name |
+| `domain` | string | ❌ | Filter cookies by a specific domain |
+
+## Request Example
+
+### Get All Cookies
+
+```bash
+curl -X GET http://localhost:3000/v1/cookies \
+  -H "Authorization: Bearer sk-your-key"
+```
+
+### Specify Instance and Domain
+
+```bash
+curl -X GET "http://localhost:3000/v1/cookies?name=browser_default&domain=lmarena.ai" \
+  -H "Authorization: Bearer sk-your-key"
+```
+
+## Response Format
+
+```json
+{
+  "instance": "browser_default",
+  "cookies": [
+    {
+      "name": "_GRECAPTCHA",
+      "value": "09ADxxxxxx",
+      "domain": "www.google.com",
+      "path": "/recaptcha",
+      "expires": 1780000000,
+      "httpOnly": true,
+      "secure": true,
+      "sameSite": "None"
+    },
+    {
+      "name": "OTZ",
+      "value": "8888888_24_24__24_",
+      "domain": "accounts.google.com",
+      "path": "/",
+      "expires": 1760000000,
+      "httpOnly": false,
+      "secure": true,
+      "sameSite": "None"
+    }
+  ]
+}
+```
+
+## Usage Scenarios
+
+::: tip Application Scenarios
+- Export cookies for use in other automation tools.
+- Leverage this project's automatic session renewal to keep cookies fresh.
+- Debug login state issues.
+:::
diff --git a/docs/en/api/models.md b/docs/en/api/models.md
new file mode 100644
index 0000000..86e9886
--- /dev/null
+++ b/docs/en/api/models.md
@@ -0,0 +1,82 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Models API
+
+Retrieve the list of currently available models.
+
+## Endpoint
+
+```
+GET /v1/models
+```
+
+## Request Example
+
+```bash
+curl -X GET http://localhost:3000/v1/models \
+  -H "Authorization: Bearer sk-your-key"
+```
+
+## Response Format
+
+```json
+{
+  "object": "list",
+  "data": [
+    {
+      "id": "gemini-3-pro-image-preview",
+      "object": "model",
+      "created": 1732456789,
+      "owned_by": "internal_server"
+    },
+    {
+      "id": "lmarena/gemini-3-pro-image-preview",
+      "object": "model",
+      "created": 1732456789,
+      "owned_by": "lmarena"
+    },
+    {
+      "id": "seedream-4-high-res-fal",
+      "object": "model",
+      "created": 1732456789,
+      "owned_by": "internal_server"
+    }
+  ]
+}
+```
+
+## Model Naming Conventions
+
+### Short Form
+
+Use the Model ID directly:
+
+```
+gemini-3-pro-image-preview
+```
+
+The system will automatically match a Worker that supports this model.
+
+### Explicit Backend Form
+
+Use the `backend/model` format:
+
+```
+lmarena/gemini-3-pro-image-preview
+gemini_biz/gemini-3-pro-image-preview
+```
+
+This forces the request to be handled by a specific backend.
+
+## Model Types
+
+| Type | Description |
+| --- | --- |
+| `image` | Image generation models |
+| `text` | Text generation models |
+
+::: info Note
+The list of returned models depends on the currently configured Workers and their adapter types.
+:::
diff --git a/docs/en/api/overview.md b/docs/en/api/overview.md
new file mode 100644
index 0000000..4fad784
--- /dev/null
+++ b/docs/en/api/overview.md
@@ -0,0 +1,78 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# API Overview
+
+WebAI2API provides a RESTful API compatible with the OpenAI format.
+
+## Basic Information
+
+- **Base URL**: `http://localhost:3000`
+- **Authentication**: Bearer Token
+
+### Request Headers
+
+```http
+Authorization: Bearer sk-your-secret-key
+Content-Type: application/json
+```
+
+## API Endpoints List
+
+### OpenAI Compatible Interfaces
+
+| Method | Endpoint | Description |
+| --- | --- | --- |
+| POST | `/v1/chat/completions` | Chat Generation |
+| GET | `/v1/models` | Retrieve Model List |
+| GET | `/v1/cookies` | Retrieve Cookies |
+
+## Error Responses
+
+All API errors return a consistent format:
+
+```json
+{
+  "error": {
+    "message": "Error description",
+    "type": "error_type",
+    "code": "ERROR_CODE"
+  }
+}
+```
+
+### Common Error Codes
+
+| HTTP Status | Error Type | Description |
+| --- | --- | --- |
+| 401 | `unauthorized` | Authentication failed |
+| 400 | `invalid_request` | Invalid request parameters |
+| 404 | `not_found` | Resource not found |
+| 429 | `rate_limit` | Too many requests |
+| 500 | `internal_error` | Internal server error |
+| 503 | `service_unavailable` | Service unavailable |
+
+## Streaming Responses
+
+For requests with `stream: true`, the response uses the Server-Sent Events (SSE) format:
+
+```
+data: {"id":"...","object":"chat.completion.chunk",...}
+
+: keep-alive
+
+data: {"id":"...","object":"chat.completion.chunk",...}
+
+data: [DONE]
+```
+
+::: tip Heartbeat/Keep-alive
+Streaming requests automatically send heartbeat packets to prevent connection timeouts. The format depends on the configured `keepalive.mode`.
+:::
+
+## Related Documents
+
+- [Chat Completions](/en/api/chat) - Detailed documentation for the chat generation interface.
+- [Models](/en/api/models) - Model list interface.
+- [Cookies](/en/api/cookies) - Cookie retrieval interface.
diff --git a/docs/en/config/instances.md b/docs/en/config/instances.md
new file mode 100644
index 0000000..d3580a3
--- /dev/null
+++ b/docs/en/config/instances.md
@@ -0,0 +1,195 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Instance Configuration
+
+Instance and Worker are the core configuration concepts of WebAI2API.
+
+## Concepts
+
+### Instance (Browser Instance)
+
+An Instance represents an independent browser process with:
+- Dedicated user data directory.
+- Independent Cookies and login sessions.
+- Optional exclusive proxy configuration.
+
+### Worker
+
+A Worker is a single tab within an Instance responsible for interacting with a specific platform. Multiple Workers under the same Instance:
+- Share browser data and login states.
+- Share proxy configuration.
+- Can be of different adapter types.
+
+## Configuration Structure
+
+```yaml
+backend:
+  pool:
+    instances:
+      - name: "browser_default"    # Instance ID
+        userDataMark: "01"         # Data directory identifier (Optional)
+        proxy:                      # Instance-level proxy (Optional)
+          enable: true
+          type: socks5
+          host: 127.0.0.1
+          port: 1080
+        workers:                    # List of Workers
+          - name: "worker1"
+            type: lmarena
+          - name: "worker2"
+            type: zai_is
+```
+
+## Instance Settings
+
+| Setting | Type | Required | Description |
+| --- | --- | --- | --- |
+| `name` | string | ✅ | Unique identifier for the instance, used in logs and Cookie retrieval. |
+| `userDataMark` | string | ❌ | Data directory identifier. Leave empty to use the default directory. |
+| `proxy` | object | ❌ | Instance-level proxy configuration. See [Proxy Settings](/en/config/proxy). |
+| `workers` | array | ✅ | List of Worker configurations. |
+
+### Data Directory
+
+- Default Location: `data/camoufoxUserData`
+- With `userDataMark`: `data/camoufoxUserData_{mark}`
+
+## Worker Settings
+
+| Setting | Type | Required | Description |
+| --- | --- | --- | --- |
+| `name` | string | ✅ | Unique identifier for the Worker (must be globally unique). |
+| `type` | string | ✅ | Adapter type. |
+| `mergeTypes` | array | ❌ | List of adapter types for aggregation mode (required if type=merge). |
+| `mergeMonitor` | string | ❌ | Backend to monitor while idle (Optional). |
+
+### Adapter Types
+
+| Type | Description |
+| --- | --- |
+| `lmarena` | LMArena Image Generation |
+| `lmarena_text` | LMArena Text Generation |
+| `gemini_biz` | Gemini Business Image Generation |
+| `gemini_biz_text` | Gemini Business Text Generation |
+| `gemini` | Google Gemini |
+| `zai_is` | zAI Image Generation |
+| `nanobananafree_ai` | Nano Banana Free |
+| `merge` | Aggregation Mode (Multiple backends in a single tab) |
+
+## Model Filter
+
+Each adapter can be configured with its own model allowlist/blocklist to control the available models for that specific adapter.
+
+### Configuration
+
+The Model Filter is configured under `backend.adapter.<AdapterID>`:
+
+```yaml
+backend:
+  adapter:
+    lmarena:
+      returnUrl: false
+      modelFilter:
+        mode: whitelist                        # whitelist or blacklist
+        list:                                  # List of models to enable or disable
+          - gemini-3-pro-image-preview
+          - gemini-3-pro-image-preview-2k
+          - gemini-2.5-flash-image-preview
+```
+
+### Settings
+
+| Item | Type | Required | Description |
+| --- | --- | --- | --- |
+| `mode` | string | ✅ | Filter mode: `whitelist` or `blacklist`. |
+| `list` | array | ✅ | List of Model IDs. |
+
+### Filter Modes
+
+- **whitelist**: Only models specified in the list are allowed; others will be filtered out.
+- **blacklist**: Models specified in the list are disabled; others remain usable.
+
+### Recommendations
+
+::: tip Use WebUI for Configuration
+We recommend using the Adapter Settings interface in the WebUI to configure model filters; visual operation is more convenient.
+:::
+
+::: warning Notes
+- Model IDs must exactly match the IDs actually supported by the adapter.
+- In whitelist mode, if the list is empty or there are no matching models, the adapter will be unusable.
+- Model filter configurations for each adapter are independent.
+:::
+
+## Aggregation Mode (Merge)
+
+Aggregation mode allows a single tab to support multiple backends, enabling failover:
+
+```yaml
+workers:
+  - name: "merged_worker"
+    type: merge
+    mergeTypes: [gemini_biz, lmarena, zai_is]
+    mergeMonitor: gemini_biz  # Backend to monitor while idle
+```
+
+::: tip Advantages of Aggregation Mode
+- Saves browser resources.
+- Automatic failover.
+- Unified login state.
+:::
+
+## Configuration Examples
+
+### Single Instance, Single Worker
+
+```yaml
+instances:
+  - name: "default"
+    workers:
+      - name: "worker1"
+        type: lmarena
+```
+
+### Multi-Instance Isolation
+
+```yaml
+instances:
+  # Instance 1: US Proxy
+  - name: "browser_us"
+    userDataMark: "us"
+    proxy:
+      enable: true
+      type: socks5
+      host: us-proxy.example.com
+      port: 1080
+    workers:
+      - name: "us_worker"
+        type: lmarena
+
+  # Instance 2: Japan Proxy
+  - name: "browser_jp"
+    userDataMark: "jp"
+    proxy:
+      enable: true
+      type: socks5
+      host: jp-proxy.example.com
+      port: 1080
+    workers:
+      - name: "jp_worker"
+        type: lmarena
+```
+
+### Aggregation Mode Example
+
+```yaml
+instances:
+  - name: "browser_merged"
+    workers:
+      - name: "all_in_one"
+        type: merge
+        mergeTypes: [gemini_biz, lmarena, zai_is]
+        mergeMonitor: gemini_biz
+```
diff --git a/docs/en/config/overview.md b/docs/en/config/overview.md
new file mode 100644
index 0000000..92cff0c
--- /dev/null
+++ b/docs/en/config/overview.md
@@ -0,0 +1,124 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Configuration Overview
+
+WebAI2API uses a YAML format configuration file `config.yaml`.
+
+::: warning Note
+The project configuration can now be fully managed via the WebUI. If you are not familiar with YAML files, please skip this section and use the WebUI to modify settings!
+:::
+
+## Configuration Structure
+
+```yaml
+# Log Level
+logLevel: info
+
+# Server Configuration
+server:
+  port: 3000
+  auth: sk-your-key
+  keepalive:
+    mode: "comment"
+
+# Backend Configuration
+backend:
+  pool:
+    strategy: least_busy
+    failover:
+      enabled: true
+      maxRetries: 2
+    instances:
+      - name: "browser_default"
+        workers:
+          - name: "default"
+            type: lmarena
+  adapter:
+    gemini_biz:
+      entryUrl: ""
+
+# Queue Configuration
+queue:
+  queueBuffer: 2
+  imageLimit: 5
+
+# Browser Configuration
+browser:
+  path: ""
+  headless: false
+  proxy:
+    enable: false
+```
+
+## Configuration Items
+
+### Logging
+
+| Item | Type | Default | Description |
+| --- | --- | --- | --- |
+| `logLevel` | string | `info` | Log visibility levels: `debug`, `info`, `warn`, `error` |
+
+### Server (server)
+
+| Item | Type | Default | Description |
+| --- | --- | --- | --- |
+| `port` | number | `3000` | HTTP service listening port |
+| `auth` | string | - | API Authentication Token (Bearer Token) |
+| `keepalive.mode` | string | `comment` | Keep-alive mode: `comment` or `content` |
+
+::: tip Keep-alive Mode
+- **comment**: Sends a `:keepalive` comment. Does not pollute the data stream (recommended).
+- **content**: Sends an empty delta. Useful for clients that reset timeouts only upon receiving valid JSON.
+:::
+
+### Queue (queue)
+
+| Item | Type | Default | Description |
+| --- | --- | --- | --- |
+| `queueBuffer` | number | `2` | Extra queuing slots for non-streaming requests. 0 means unlimited. |
+| `imageLimit` | number | `5` | Maximum number of images per request (Max 10). |
+
+### Browser (browser)
+
+| Item | Type | Default | Description |
+| --- | --- | --- | --- |
+| `path` | string | `""` | Path to Camoufox executable. Leave empty to use default. |
+| `headless` | boolean | `false` | Whether to enable headless mode. |
+| `proxy` | object | - | Global proxy configuration. |
+
+### Adapter Configuration (backend.adapter)
+
+Each adapter can be configured with its own model allowlist/blocklist to control the available models for that specific adapter.
+
+| Item | Type | Default | Description |
+| --- | --- | --- | --- |
+| `modelFilter.mode` | string | - | Filter mode: `whitelist` or `blacklist`. |
+| `modelFilter.list` | array | - | List of models (to be enabled or disabled based on `mode`). |
+
+::: tip Model Filtering
+- **whitelist (Allowlist)**: Only models in the list are permitted.
+- **blacklist (Blocklist)**: Models in the list are disabled; others are available.
+- Using the WebUI for configuration is recommended.
+:::
+
+Configuration Example:
+
+```yaml
+backend:
+  adapter:
+    lmarena:
+      returnUrl: false
+      modelFilter:
+        mode: whitelist                        # Allowlist mode
+        list:                                  # Only enable the following models
+          - gemini-3-pro-image-preview
+          - gemini-3-pro-image-preview-2k
+          - gemini-2.5-flash-image-preview
+```
+
+## Related Documents
+
+- [Instances Configuration](/en/config/instances) - Detailed browser instance and Worker configuration.
+- [Proxy Settings](/en/config/proxy) - Detailed proxy setup.
diff --git a/docs/en/config/proxy.md b/docs/en/config/proxy.md
new file mode 100644
index 0000000..a25442c
--- /dev/null
+++ b/docs/en/config/proxy.md
@@ -0,0 +1,89 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Proxy Settings
+
+WebAI2API supports global proxy and instance-level proxy configurations.
+
+## Proxy Priority
+
+1. **Instance-level Proxy**: If an Instance is configured with its own proxy, that proxy is used.
+2. **Global Proxy**: If the instance is not configured, the global proxy is used.
+3. **Direct Connection**: If neither is configured, a direct connection is established.
+
+## Global Proxy Configuration
+
+Configure the global proxy in `browser.proxy`:
+
+```yaml
+browser:
+  proxy:
+    enable: true
+    type: http          # http or socks5
+    host: 127.0.0.1
+    port: 7890
+    # Optional authentication
+    user: username
+    passwd: password
+```
+
+## Instance-level Proxy Configuration
+
+Configure a dedicated proxy for a specific Instance:
+
+```yaml
+backend:
+  pool:
+    instances:
+      - name: "browser_us"
+        proxy:
+          enable: true
+          type: socks5
+          host: us-proxy.example.com
+          port: 1080
+          user: myuser
+          passwd: mypassword
+        workers:
+          - name: "us_worker"
+            type: lmarena
+```
+
+## Settings
+
+| Item | Type | Required | Description |
+| --- | --- | --- | --- |
+| `enable` | boolean | ✅ | Whether to enable the proxy. |
+| `type` | string | ✅ | Proxy type: `http` or `socks5`. |
+| `host` | string | ✅ | Proxy server address. |
+| `port` | number | ✅ | Proxy server port. |
+| `user` | string | ❌ | Proxy authentication username. |
+| `passwd` | string | ❌ | Proxy authentication password. |
+
+## Forced Direct Connection
+
+If you need a specific instance to force a direct connection even when a global proxy is configured:
+
+```yaml
+instances:
+  - name: "browser_direct"
+    proxy:
+      enable: false    # Explicitly disable proxy
+    workers:
+      - name: "direct_worker"
+        type: lmarena
+```
+
+## Proxy Selection Recommendations
+
+::: tip Recommended Configuration
+- **Type**: SOCKS5 proxies are generally more versatile than HTTP proxies.
+- **Stability**: Choose stable and reliable proxy service providers.
+- **IP Quality**: Use tools like [ping0.cc](https://ping0.cc) to check the quality of your IP.
+:::
+
+::: warning Notes
+- Proxy quality directly affects the frequency of CAPTCHA challenges.
+- Frequent IP changes may lead to account risk management.
+- We recommend using residential IPs or static datacenter IPs.
+:::
diff --git a/docs/en/guide/deployment.md b/docs/en/guide/deployment.md
new file mode 100644
index 0000000..b882c8a
--- /dev/null
+++ b/docs/en/guide/deployment.md
@@ -0,0 +1,94 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Quick Deployment
+
+This project supports **Manual Deployment (Recommended)** and **Docker Containerization Deployment**.
+
+## Manual Deployment
+
+### 1. Clone the Project
+
+```bash
+git clone https://github.com/foxhui/WebAI2API.git
+cd WebAI2API
+```
+
+### 2. Install Dependencies
+
+```bash
+# 1. Install NPM dependencies
+pnpm install
+# 2. Install browser and other pre-compiled dependencies
+npm run init 
+# Use a proxy
+# Use -proxy to interactively input proxy configuration
+npm run init -- -proxy=http://username:passwd@host:port
+```
+
+::: warning Note
+`npm run init` needs to download files from GitHub. Please ensure your network is connected.
+:::
+
+### 3. Start the Service
+
+```bash
+# Standard Start
+npm start
+# Linux System - Start with Virtual Display
+npm start -- -xvfb -vnc
+# Login Mode (Temporarily disables headless mode and automation)
+npm start -- -login (-xvfb -vnc)
+```
+
+## Docker Deployment
+
+::: warning **Security Alert**
+- Docker images have Virtual Display (Xvfb) and VNC service enabled by default.
+- You can connect through the Virtual Display section of the WebUI.
+- **WebUI transmissions are not encrypted. For public network environments, please use SSH tunneling or HTTPS.**
+:::
+
+### Docker CLI
+
+```bash
+docker run -d --name webai-2api \
+  -p 3000:3000 \
+  -v "$(pwd)/data:/app/data" \
+  --shm-size=2gb \
+  foxhui/webai-2api:latest
+```
+
+### Docker Compose
+
+```yaml
+services:
+  webai-2api:
+    image: foxhui/webai-2api:latest
+    container_name: webai-2api
+    restart: unless-stopped
+    ports:
+      - "3000:3000"
+    volumes:
+      - ./data:/app/data
+    shm_size: '2gb'
+    init: true
+```
+
+Start the service:
+
+```bash
+docker compose up -d
+```
+
+## Verify Installation
+
+After the service starts, visit the following URLs for verification:
+
+- **Web Management Interface**: http://localhost:3000
+- **API Interface Test**: http://localhost:3000/v1/chat/completions
+
+## Next Steps
+
+Once deployment is complete, please read [First Use](/en/guide/first-use) to complete login initialization.
diff --git a/docs/en/guide/first-use.md b/docs/en/guide/first-use.md
new file mode 100644
index 0000000..4a6a34b
--- /dev/null
+++ b/docs/en/guide/first-use.md
@@ -0,0 +1,109 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# First Use
+
+When using WebAI2API for the first time, you need to complete the login initialization to use it normally.
+
+## 1. Adjust Configuration File
+
+The program will copy the configuration file from `config.example.yaml` to `data/config.yaml` upon its first run.
+
+::: tip Tip
+**Restarts are required for configuration changes to take effect!**
+:::
+
+```yaml
+server:
+  # Listening port
+  port: 3000
+  # Authentication API Token (Generate with: npm run genkey)
+  # This setting affects both API endpoints and the WebUI
+  auth: sk-change-me-to-your-secure-key
+```
+
+## 2. Access Web Management Interface
+
+Once the service is started, open your browser and visit:
+```
+http://localhost:3000
+```
+
+::: tip Tip
+**Remote Access**: Replace `localhost` with your server's IP address.
+**API Token**: The `auth` key configured in the configuration file.
+**Security Suggestion**: For public environments, use Nginx/Caddy with HTTPS or access via SSH tunnel.
+:::
+
+## 3. Initialize Account Login
+
+> [!IMPORTANT]
+> **The following initialization steps must be completed for first-time use**:
+
+1. **Connect to Virtual Display**:
+   - Linux/Docker: Connect via the "Virtual Display" section in the WebUI.
+   - Windows: Operable directly in the popup browser window.
+
+2. **Complete Account Login**:
+   - Manually log in to the required AI website accounts (check account requirements in the WebUI Adapter Management).
+   - Send an arbitrary message in the input box to trigger and complete human verification (if necessary).
+   - Agree to terms of service or新手 (onboarding) guides (if necessary).
+   - Ensure you are no longer blocked by any "first-time use" content.
+
+3. **SSH Tunneling Example** (Recommended for public servers):
+   ```bash
+   # Run in your local terminal to map the server's WebUI locally
+   ssh -L 3000:127.0.0.1:3000 root@Server_IP
+   
+   # Then access locally
+   # WebUI: http://localhost:3000
+   ```
+
+::: tip Running Suggestions
+To reduce the risk of being flagged, **we strongly recommend keeping non-headless mode enabled long-term** (or using Virtual Display Xvfb).
+
+**Regarding Headful/Headless Mode**:
+- **Headful Mode** (Default): Shows the browser window, useful for debugging and manual intervention.
+- **Headless Mode**: Runs in the background, saves resources, but you cannot view the browser interface, and it may be more easily detected by some websites.
+:::
+
+## Login Mode
+
+Login mode will force disable headless mode.
+
+### Basic Usage
+```bash
+# Start the first Worker for login
+npm start -- -login
+```
+
+### Multi-Worker Login
+
+If you have configured multiple Workers, you need to complete the login for each one individually:
+
+```bash
+# Log in to each Worker sequentially
+npm start -- -login=worker1
+npm start -- -login=worker2
+```
+
+::: info Shared Login State
+Multiple Workers under the same Instance (browser instance) share the login state. If using Unified Login like Google OAuth, you only need to log in once.
+:::
+
+### WebUI Login Mode
+
+Once the service is running, you can also switch to login mode via the WebUI:
+
+1. Visit http://localhost:3000
+2. Go to the "System Management" page
+3. Click the dropdown arrow on the "Restart" button
+4. Select "Restart in Login Mode" or specify a specific Worker to log in.
+
+## 4. Next Steps
+
+Once the login is complete, please read the following:
+
+- [Configuration Guide](/en/config/overview) - Learn more about all configuration options.
+- [API Reference](/en/api/overview) - Start using the API.
diff --git a/docs/en/guide/introduction.md b/docs/en/guide/introduction.md
new file mode 100644
index 0000000..b262082
--- /dev/null
+++ b/docs/en/guide/introduction.md
@@ -0,0 +1,42 @@
+# WebAI2API
+
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+## Project Introduction
+
+**WebAI2API** is a tool that converts web-based AI services into a universal API based on **Camoufox (Playwright)**. By mimicking human operations to interact with websites like LMArena and Gemini, it provides interfaces compatible with the **OpenAI format**, while supporting **multi-window concurrency** and **multi-account management** (browser instance data isolation).
+
+### 📋 Support List
+
+| Website | Text Gen | Image Gen | Video Gen |
+| :--- | :---: | :---: | :---: | 
+| [**LMArena**](https://lmarena.ai/) | ✅ | ✅ | 🚫 |
+| [**Gemini Enterprise Business**](https://business.gemini.google/) | ✅ | ✅ | ✅ |
+| [**Nano Banana Free**](https://nanobananafree.ai/) | 🚫 | ✅ | 🚫 |
+| [**zAI**](https://zai.is/) | ✅ | ✅ | 🚫 |
+| [**Google Gemini**](https://gemini.google.com/) | ✅ | ✅ | ✅ | 
+| [**ZenMux**](https://zenmux.ai/) | ✅ | ❌ | 🚫 | 
+| [**ChatGPT**](https://chatgpt.com/) | ✅ | ✅ | 🚫 | 
+| [**DeepSeek**](https://chat.deepseek.com/) | ✅ | 🚫 | 🚫 | 
+| [**Sora**](https://sora.chatgpt.com/) | 🚫 | 🚫 | ✅ | 
+| [**Google Flow**](https://labs.google/fx/zh/tools/flow) | 🚫 | ✅ | ❌ | 
+| [**Doubao**](https://www.doubao.com/) | ✅ | ✅ | ❌ | 
+| More coming soon... | - | - | - | 
+
+::: tip Note
+**Get Full Model List**: Use the `GET /v1/models` endpoint to view all available models and their details in your current configuration.
+
+✅ Supported; ❌ Not currently supported, but may be in the future; 🚫 Not supported by the website.
+:::
+
+## Screenshots
+
+![WebAI2API](/guide_introduction/1.webp)
+
+![WebAI2API](/guide_introduction/2.webp) 
+
+![WebAI2API](/guide_introduction/3.webp) 
+
+![WebAI2API](/guide_introduction/4.webp) 
diff --git a/docs/en/guide/requirements.md b/docs/en/guide/requirements.md
new file mode 100644
index 0000000..76d210b
--- /dev/null
+++ b/docs/en/guide/requirements.md
@@ -0,0 +1,83 @@
+::: info
+This English version is translated by **Gemini 3 Flash**.
+:::
+
+# Requirements
+
+Before you start deploying WebAI2API, please ensure that your environment meets the following requirements.
+
+## System Requirements
+
+### Operating System
+
+- **Windows**: Windows 10/11 or Windows Server 2016+
+- **Linux**: Ubuntu 18.04+, Debian 10+, CentOS 7+, or other mainstream distributions
+- **macOS**: macOS 10.15 (Catalina) or higher
+
+### Hardware Configuration
+
+| Resource | Minimum | Recommended (Single Instance) | Recommended (Multi-Instance) |
+| :--- | :--- | :--- | :--- |
+| **CPU** | 1 Core | 2 Cores or above | 2 Cores or above |
+| **Memory** | 1 GB | 2 GB or above | 4 GB or above |
+| **Disk** | 2 GB available | 5 GB or above | 7 GB or above |
+
+::: tip Real-world Performance
+- **Oracle Free Tier** (1C1G, Debian 12): Limited resources, can be laggy, suitable for testing or light use only.
+- **Alibaba Cloud Lightweight** (2C2G, Debian 11): Runs smoothly, used for project development and testing.
+:::
+
+## Software Dependencies
+
+### Node.js
+
+- **Version Requirement**: v20.0.0 or higher (ABI 115+)
+- **Package Manager**: pnpm (recommended) or npm
+
+```bash
+# Check Node.js version
+node --version
+
+# Install pnpm (if not installed)
+npm install -g pnpm
+```
+
+### Camoufox
+
+Camoufox is the core dependency of this project and will be downloaded automatically during the installation process.
+
+::: warning Network Requirements
+The installation process requires downloading pre-compiled dependencies like Camoufox from GitHub. Please ensure your network has access to GitHub.
+:::
+
+## Docker Environment (Optional)
+
+If you choose to deploy via Docker, you need to install:
+
+- **Docker**: 20.10.0 or higher
+- **Docker Compose**: 2.0.0 or higher (optional)
+
+```bash
+# Check Docker version
+docker --version
+docker compose version
+```
+
+## Linux Specific Dependencies
+
+When running in non-headless mode on Linux, you may need to install additional packages:
+
+```bash
+# Ubuntu/Debian
+sudo apt-get install xvfb x11vnc
+
+# CentOS/RHEL
+sudo yum install xorg-x11-server-Xvfb x11vnc
+
+# Arch Linux
+sudo pacman -S xorg-server-xvfb x11vnc
+```
+
+## Next Steps
+
+Once your environment is ready, please proceed to [Quick Deployment](/en/guide/deployment) to start the installation.
diff --git a/docs/en/index.md b/docs/en/index.md
new file mode 100644
index 0000000..1768249
--- /dev/null
+++ b/docs/en/index.md
@@ -0,0 +1,34 @@
+---
+layout: home
+
+hero:
+  name: "WebAI2API"
+  text: "Web-based AI Services to OpenAI Compatible API"
+  tagline: Based on Camoufox (Playwright), mimicking human interactions with LMArena, Gemini, and more
+  actions:
+    - theme: brand
+      text: Quick Start
+      link: /en/guide/deployment
+    - theme: alt
+      text: Introduction
+      link: /en/guide/introduction
+    - theme: alt
+      text: GitHub
+      link: https://github.com/foxhui/WebAI2API
+  image:
+    src: /favicon.png
+
+features:
+  - icon: 🤖
+    title: Human-like Interaction
+    details: Mimics human typing and mouse trajectories, evading automation detection via feature camouflaging.
+  - icon: 🎨
+    title: Web Management
+    details: Provides a visual management interface supporting real-time logs, VNC connection, and adapter management.
+  - icon: 🚀
+    title: Concurrent Isolation
+    details: Supports multi-window concurrency with instance-level data isolation for multiple accounts.
+  - icon: 🛡️
+    title: Stable Protection
+    details: Built-in task queue, load balancing, failover, and error retries.
+---
diff --git a/docs/guide/introduction.md b/docs/guide/introduction.md
index 5abc4ba..b1be5cd 100644
--- a/docs/guide/introduction.md
+++ b/docs/guide/introduction.md
@@ -18,6 +18,7 @@
 | [**DeepSeek**](https://chat.deepseek.com/) | ✅ | 🚫 | 🚫 | 
 | [**Sora**](https://sora.chatgpt.com/) | 🚫 | 🚫 | ✅ | 
 | [**Google Flow**](https://labs.google/fx/zh/tools/flow) | 🚫 | ✅ | ❌ | 
+| [**豆包**](https://www.doubao.com/) | ✅ | ✅ | ❌ | 
 | 待续... | - | - | - | 
 
 ::: tip 实测环境表现
@@ -28,10 +29,10 @@
 
 ## 项目截图
 
-![Image](https://github.com/user-attachments/assets/296a518e-c42b-4e39-8ff6-9b4381ed4f6e)
+![Image](/guide_introduction/1.webp)
 
-![Image](https://github.com/user-attachments/assets/bfa30ece-6947-4f18-b2c9-ccc8087b7e89) 
+![Image](/guide_introduction/2.webp) 
 
-![Image](https://github.com/user-attachments/assets/5b15ebd2-7593-4f0e-8561-83d6ba5d88ab) 
+![Image](/guide_introduction/3.webp) 
 
-![Image](https://github.com/user-attachments/assets/53deea29-4071-4a07-8a61-211761c5f2f7) 
+![Image](/guide_introduction/4.webp) 
diff --git a/docs/public/guide_introduction/1.webp b/docs/public/guide_introduction/1.webp
new file mode 100644
index 0000000..662c081
Binary files /dev/null and b/docs/public/guide_introduction/1.webp differ
diff --git a/docs/public/guide_introduction/2.webp b/docs/public/guide_introduction/2.webp
new file mode 100644
index 0000000..83d3a46
Binary files /dev/null and b/docs/public/guide_introduction/2.webp differ
diff --git a/docs/public/guide_introduction/3.webp b/docs/public/guide_introduction/3.webp
new file mode 100644
index 0000000..4ed218b
Binary files /dev/null and b/docs/public/guide_introduction/3.webp differ
diff --git a/docs/public/guide_introduction/4.webp b/docs/public/guide_introduction/4.webp
new file mode 100644
index 0000000..497e3d8
Binary files /dev/null and b/docs/public/guide_introduction/4.webp differ