diff --git a/docs/appstore/intro.md b/docs/appstore/intro.md
index cec2f64464f9dc4d20f408f7cf64b07f9af9a849..dab8d7bccbee5455673fdea04c537de9da28f9d5 100644
--- a/docs/appstore/intro.md
+++ b/docs/appstore/intro.md
@@ -79,7 +79,7 @@ AI 应用市场提供了简单易用的 API，帮助开发者快速将应用集
 ```python showLineNumbers title="Python"
 import requests
 
-requests.get("https://ai.gitee.com/v1/app",
+requests.get("{{SITE_URL}}/v1/app",
     headers={
         "Authorization": "Bearer YOUR_APP_TOKEN_HERE" # 如果是公开的 APP 就不需要设置 Authorization
     },
@@ -108,7 +108,7 @@ requests.get("https://ai.gitee.com/v1/app",
 #### 获取验证码
 
 ```python showLineNumbers title="Python"
-requests.post("https://ai.gitee.com/v1/app/auth/vcode",
+requests.post("{{SITE_URL}}/v1/app/auth/vcode",
     headers={
       "Authorization": "Bearer YOUR_APP_TOKEN_HERE",
       "Content-Type": "application/json"
@@ -125,7 +125,7 @@ requests.post("https://ai.gitee.com/v1/app/auth/vcode",
 #### 获取用户子令牌（相当于用户的身份认证）
 
 ```python showLineNumbers title="Python"
-requests.post("https://ai.gitee.com/v1/app/auth/token",
+requests.post("{{SITE_URL}}/v1/app/auth/token",
     headers={
       "Authorization": "Bearer YOUR_APP_TOKEN_HERE",
       "Content-Type": "application/json"
@@ -147,7 +147,7 @@ requests.post("https://ai.gitee.com/v1/app/auth/token",
 在使用计费 API 之前需要先 [设置收费策略](./price) 。目前应用市场支持支付宝和微信两种支付形式，使用计费 API 的示例代码如下：
 
 ```python showLineNumbers title="Python"
-requests.post("https://ai.gitee.com/v1/app/pay",
+requests.post("{{SITE_URL}}/v1/app/pay",
     headers={
       "Authorization": "Bearer APP_USER_TOKEN_HERE", # 这里的 APP_USER_TOKEN_HERE 是用户的子令牌
       "Content-Type": "application/json"
diff --git a/docs/integrations/Development-Tools/claude-code.md b/docs/integrations/Development-Tools/claude-code.md
index 50fa313062b8cdd16479cb50b94ea45626186541..ed248f514c6eec30fb7f98297c368f2bbef0eaa6 100644
--- a/docs/integrations/Development-Tools/claude-code.md
+++ b/docs/integrations/Development-Tools/claude-code.md
@@ -39,7 +39,7 @@ Serverless API 支持在 Claude Code 中调用，使用步骤如下：
       "Providers": [
         {
           "name": "gitee",
-          "api_base_url": "https://ai.gitee.com/v1/chat/completions",
+          "api_base_url": "{{SITE_URL}}/v1/chat/completions",
           "api_key": "your-api-key",
           "models": ["kimi-k2-instruct"],
           "transformer": {
diff --git a/docs/products/apis/async-task.md b/docs/products/apis/async-task.md
index 1eca00d39cffeee68b2b141195f3178362b4dc9d..f391301deb518741b2aa68ce2caa0f9a66ea0128 100644
--- a/docs/products/apis/async-task.md
+++ b/docs/products/apis/async-task.md
@@ -11,11 +11,11 @@
 异步任务接口采用提交-查询模式：
 
 - **提交接口**：用于创建异步任务，例如文本生成音乐的提交接口为 `/async/music/generations`
-- **查询接口**：统一的任务状态查询接口 `https://ai.gitee.com/api/v1/task/<task_id>`
-- **任务取消接口**：`https://ai.gitee.com/api/v1/task/<task_id>/cancel`
-- **配额查询接口**：`https://ai.gitee.com/v1/tasks/available-quota`
-- **任务状态接口**：`https://ai.gitee.com/v1/task/<task_id>/status`
-- **任务记录接口**：`https://ai.gitee.com/v1/task/<task_id>`
+- **查询接口**：统一的任务状态查询接口 `{{SITE_URL}}/api/v1/task/<task_id>`
+- **任务取消接口**：`{{SITE_URL}}/api/v1/task/<task_id>/cancel`
+- **配额查询接口**：`{{SITE_URL}}/v1/tasks/available-quota`
+- **任务状态接口**：`{{SITE_URL}}/v1/task/<task_id>/status`
+- **任务记录接口**：`{{SITE_URL}}/v1/task/<task_id>`
 
 ## 工作流程
 
@@ -37,7 +37,7 @@ from PIL import Image
 from io import BytesIO
 from requests_toolbelt.multipart.encoder import MultipartEncoder
 
-API_URL = "https://ai.gitee.com/v1/async/music/generations"
+API_URL = "{{SITE_URL}}/v1/async/music/generations"
 headers = {
     "Authorization": "Bearer <your token>",
 }
@@ -163,16 +163,16 @@ with open("output.mp3", "wb") as f:
 ```bash showLineNumbers title="bash"
 # 查询可用配额
 curl -H "Authorization: Bearer <your_token>" \
-     https://ai.gitee.com/v1/tasks/available-quota
+     {{SITE_URL}}/v1/tasks/available-quota
 
 # 取消不需要的任务
 curl -X POST \
      -H "Authorization: Bearer <your_token>" \
-     https://ai.gitee.com/api/v1/task/<task_id>/cancel
+     {{SITE_URL}}/api/v1/task/<task_id>/cancel
 
 # 查询任务状态
 curl -H "Authorization: Bearer <your_token>" \
-     https://ai.gitee.com/v1/task/<task_id>/status
+     {{SITE_URL}}/v1/task/<task_id>/status
 ```
 
 ## 常见问题
@@ -181,19 +181,19 @@ curl -H "Authorization: Bearer <your_token>" \
 A: 根据任务复杂度不同，通常在 1-10 分钟内完成。
 
 **Q: 是否可以取消正在进行的任务？**
-A: 支持任务取消。使用取消接口 `https://ai.gitee.com/api/v1/task/<task_id>/cancel` 可以取消 waiting 或 in_progress 状态的任务。
+A: 支持任务取消。使用取消接口 `{{SITE_URL}}/api/v1/task/<task_id>/cancel` 可以取消 waiting 或 in_progress 状态的任务。
 
 **Q: 什么是并发配额限制？**
 A: 每个账号的异步任务有并发配额限制，包括处于 waiting 和 in_progress 状态的任务总数。超过配额将无法提交新任务。
 
 **Q: 如何查询我的可用配额？**
-A: 使用配额查询接口 `https://ai.gitee.com/v1/tasks/available-quota` 可以查询当前可用的异步任务并发配额。
+A: 使用配额查询接口 `{{SITE_URL}}/v1/tasks/available-quota` 可以查询当前可用的异步任务并发配额。
 
 **Q: 下载链接有效期多长？**
 A: 下载链接通常有效期为 24 小时，请及时下载保存。
 
 **Q: 如何获取任务的详细信息？**
-A: 使用任务记录接口 `https://ai.gitee.com/v1/task/<task_id>` 可以获取任务的完整信息，包括参数、状态、结果等。
+A: 使用任务记录接口 `{{SITE_URL}}/v1/task/<task_id>` 可以获取任务的完整信息，包括参数、状态、结果等。
 
 
 **Q: 如何处理配额不足的情况？**
diff --git a/docs/products/apis/images-vision/controlnet.md b/docs/products/apis/images-vision/controlnet.md
index b59c4e01f61862b4a3ce96bd866084f04872b8f8..a7e733a70fcee6ff448318ad72b49be9e485ad78 100644
--- a/docs/products/apis/images-vision/controlnet.md
+++ b/docs/products/apis/images-vision/controlnet.md
@@ -48,7 +48,7 @@ import base64
 import requests
 
 client = OpenAI(
-    base_url="https://ai.gitee.com/v1",
+    base_url="{{SITE_URL}}/v1",
     api_key="XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
 )
 
diff --git a/docs/products/apis/images-vision/faceid.md b/docs/products/apis/images-vision/faceid.md
index 6f1303c7ac2c316c9187b1d9f8c853ff08bb9f9c..73dfee8c0e8f4646ac3f0fa275f084091367958d 100644
--- a/docs/products/apis/images-vision/faceid.md
+++ b/docs/products/apis/images-vision/faceid.md
@@ -109,7 +109,7 @@ import base64
 from PIL import Image
 from io import BytesIO
 
-API_URL = "https://ai.gitee.com/v1/images/face-migration"
+API_URL = "{{SITE_URL}}/v1/images/face-migration"
 headers = {
     "Authorization": "Bearer <add your token>"
 }
diff --git a/docs/products/apis/images-vision/fuzzy.md b/docs/products/apis/images-vision/fuzzy.md
index 2acd1efcf3aa9eb0eaa6db10cd86b3f0f8c0c810..c06f46dc0dc49530bbf42ed53b441caea125c037 100644
--- a/docs/products/apis/images-vision/fuzzy.md
+++ b/docs/products/apis/images-vision/fuzzy.md
@@ -77,7 +77,7 @@ from PIL import Image
 from io import BytesIO
 from requests_toolbelt import MultipartEncoder
 
-API_URL = "https://ai.gitee.com/v1/images/style-migration"
+API_URL = "{{SITE_URL}}/v1/images/style-migration"
 headers = {
     "Authorization": "Bearer <your token>",
 }
diff --git a/docs/products/apis/texts/text-generation.md b/docs/products/apis/texts/text-generation.md
index a1df7d076f37e25ef96c5ddf2caeec5ebfa6062f..d808821bba721be2b63029bc99d5186e6f09dc29 100644
--- a/docs/products/apis/texts/text-generation.md
+++ b/docs/products/apis/texts/text-generation.md
@@ -51,7 +51,7 @@ import TabItem from '@theme/TabItem';
   <TabItem value="js" label="JavaScript">
     ```javascript showLineNumbers
     async function query(data) {
-        const response = await fetch('https://ai.gitee.com/v1/chat/completions', {
+        const response = await fetch('{{SITE_URL}}/v1/chat/completions', {
             headers: {
                 Authorization: 'Bearer xxxxx',
                 'Content-Type': 'application/json',
diff --git a/docs/products/training/image-generate.md b/docs/products/training/image-generate.md
index 670519d76f4f0042be537161e34cbdceddc0503d..d825c7da7c51cb7390cf19254cc3d57f673401a6 100644
--- a/docs/products/training/image-generate.md
+++ b/docs/products/training/image-generate.md
@@ -8,7 +8,7 @@ sidebar_position: 2
 
 图像大模型本身已经学到非常多通用的艺术风格和物体，但是它没法理解某个具体的人、具体的事物是什么样子的。通过微调，我们可以教会大模型画出您身边某个具体的人或事物。
 
-目前支持微调的模型包括：`SDXL 1.0` 以及 `FLUX-Dev` 。
+目前支持微调的模型包括：`FLUX.1-Krea-dev` 、 `FLUX.1-Dev` 以及 `SDXL 1.0` 。
 
 本文将通过 5 张特定狗狗照片的数据集，通过模力方舟提供的开箱即用的模型微调功能。让大模型 “记住” 特定狗狗的特征。
 
@@ -62,13 +62,12 @@ sidebar_position: 2
 ![entry](/img/training/guide/task-data-args.png)
 
 ## 步骤四：算力选择
-点击 `下一步` ，进入算力选择页面，确定后点击 `支付并开始训练`
+点击 `下一步，选择算力` ，进入算力选择页面，确定后点击 `支付并开始训练`
 
 ![entry](/img/training/guide/task-data-cpu.png)
 
 点击右下载角 `开始训练`按钮，进入任务排队状态，稍等片刻，系统将为您的任务分配资源，开始训练。
 
-![entry](/img/training/guide/task-result-padding.png)
 ![entry](/img/training/guide/task-result-training.png)
 
 训练完成后，您可以查看到训练结果，包括模型的 `loss` ，训练程序会在每个 `循环轮次` 保存一次模型，同时生成 3 张图片，用于评估模型的训练效果。
diff --git a/docs/products/training/text-generate.md b/docs/products/training/text-generate.md
index 83eead318d0e6b3c594beaac1bfc998574fe83ec..1c6351937ff36e5151d41ad1591bf9630088e849 100644
--- a/docs/products/training/text-generate.md
+++ b/docs/products/training/text-generate.md
@@ -84,7 +84,7 @@ import ReactPlayer from 'react-player/lazy';
 
 ### 配置训练参数
 
-在配置训练参数前，您需要上传数据集，您可以在 [此处](https://ai.gitee.com/datasets/wang-tu1357/gsm8k_thinking_chinese/tree/master) 下载测试数据集进行测试。
+在配置训练参数前，您需要上传数据集，您可以在 [此处]({{SITE_URL}}/datasets/wang-tu1357/gsm8k_thinking_chinese/tree/master) 下载测试数据集进行测试。
 
 ![上传数据集](/img/training/guide-llm/train-only-messages.png)
 
diff --git a/docusaurus.config.ts b/docusaurus.config.ts
index c05ae8353c65ac49a4573280c8d1904ba25e2017..db73ae27766801c8680f7c53b4a250bde434b46c 100644
--- a/docusaurus.config.ts
+++ b/docusaurus.config.ts
@@ -10,7 +10,7 @@ const SITE_URL = process.env.DOCS_SITE_URL;
 envCheck();
 
 const config: Config = {
-  title: 'MoArk',
+  title: '模力方舟',
   tagline: 'Building AI Applications Made Simple',
   favicon: `${CDN_PREFIX}/img/favicon.ico`,
 
diff --git a/static/img/training/guide/task-data-cpu.png b/static/img/training/guide/task-data-cpu.png
index ff9ef6b858d26082f99e6c5892a9a369bdeb52a5..6d1a335c9d48b34562c9e055f235f3bbf7ecfaa0 100644
Binary files a/static/img/training/guide/task-data-cpu.png and b/static/img/training/guide/task-data-cpu.png differ
diff --git a/static/img/training/guide/task-data-processing.png b/static/img/training/guide/task-data-processing.png
index 485e53943aa2f71b2f163967527b03a09146ffe9..479847e34cc1f030b0e921f61fb23fd813c7e87e 100644
Binary files a/static/img/training/guide/task-data-processing.png and b/static/img/training/guide/task-data-processing.png differ
diff --git a/static/img/training/guide/task-data-tags-edit.png b/static/img/training/guide/task-data-tags-edit.png
index b4fd7e10fbb1aa869576da3cda6e46e2e4000dd9..a5cfb5cf9027ad13ec8abac0cd1325f22f6754e9 100644
Binary files a/static/img/training/guide/task-data-tags-edit.png and b/static/img/training/guide/task-data-tags-edit.png differ
diff --git a/static/img/training/guide/task-result-padding.png b/static/img/training/guide/task-result-padding.png
deleted file mode 100644
index 35582920b0e027c5f503eeb89fedf0310c168070..0000000000000000000000000000000000000000
Binary files a/static/img/training/guide/task-result-padding.png and /dev/null differ