diff --git a/README.cn.md b/README.cn.md
index 64e0b14..dbd8f8c 100644
--- a/README.cn.md
+++ b/README.cn.md
@@ -151,10 +151,12 @@ civitai不是每个图片都有关键词，一个模型中，也不是所有预
 
 
 
-## Civitai API失效
-Civitai在面临类似DDos的问题的时候，会把整个网站立刻置于Cloudflare验证机制的保护下，包括API的接口。于是，API请求，就会被跳转到Cloudflare的真人验证页面而无法获取任何信息。
+## Civitai API检查
+自从上次Civitai网站挂了之后，它对连接频率检查就好像变严格了。当它觉得扩展发送的请求频率过高，就会把扩展的API请求，跳转到Cloudflare的真人验证页面，而导致扩展无法获取任何信息。
 
-这种情况，请耐心等待Civitai恢复之后，再连接Civitai。根据以往经验，每次Civitai这样折腾一轮要6-8小时。
+这种情况，只能停止连接civitai，并耐心等待Civitai解封。可能要等好几个小时。
+
+从v1.5.1版开始，本扩展开始强制TI扫描必须每个连接后延迟1秒，以避免请求过快被当作攻击。所以，如果你是使用1.5.1或以后的版本，应该没有这个问题。
 
 
 ## 新特性
diff --git a/README.md b/README.md
index 5a6269d..47681da 100644
--- a/README.md
+++ b/README.md
@@ -150,10 +150,12 @@ There are 2 cases this hash code can not find the model on civitai:
 In these cases, you can always link a model to civitai by filling its URL in this extension.
 
 
-## Civitai API Fail
-When Civitai is facing some issue like DDos, it gonna put civitai under Cloudflare's protection, which gonna re-direct our API request to a real human checking page. Then this extension can not get any information back.  
+## Civitai API Security Check
+Since last website down of civitai, it has more strict checking for request's frequency. Once it thinks this extension is sending requests to quickly, it gonna re-direct extension's API request to Cloudflare's real human checking page. Then this extension can not get any information back. 
 
-In that case, juse wait for civitai's recovering. It could take 6-8 hours.  
+In that case, you have to wait until civitai unblock you. It could take hours.  
+
+Since v1.5.1, TI scanning is forced to delay 1 second to avoid this case. So you should be find if you are using 1.5.1 or later.  
 
 
 ## Feature Request
@@ -166,6 +168,9 @@ From v1.5, v1.x goes into maintenance phase.
 Enjoy!
 
 # Change Log
+## v1.5.1
+* Force TI scanning delay 1 second to prevent from civitai treating this extension's requests as attacking.
+
 ## v1.5.0
 * Download a model by Civitai model page's url
 * Resume downloading from break-point