diff --git a/README.md b/README.md
index af8eb6a3d2..372abe41de 100644
--- a/README.md
+++ b/README.md
@@ -99,14 +99,10 @@ Notes:
 -  Please select the `optimize-model` and `use_cache` options to accelerate the model.
 
 
-Now you may click the `Load` button to load the model with IPEX-LLM optimizations.
+Now you may click the `Load` button to load the model with IPEX-LLM optimizations. If everything goes well, you will get a message as shown below.
 
 ![Image text](https://github.com/intel-analytics/text-generation-webui/blob/8ebee0651dd56012c4a9e0ba6932efec4c7d1b2e/readme_folder/image3.png)
 
-After the model is loaded, a warm-up process is started in the background. 
-After warm-up is completed, a `Warmup finished!` message is shown.
-
-![Image text](https://github.com/intel-analytics/text-generation-webui/blob/8ebee0651dd56012c4a9e0ba6932efec4c7d1b2e/readme_folder/image3b.png)
 
 ##### 4.4 Run the Model on WebUI
 
diff --git a/readme_folder/image3.png b/readme_folder/image3.png
index e114d8c057..3f9c763e15 100644
Binary files a/readme_folder/image3.png and b/readme_folder/image3.png differ
diff --git a/readme_folder/image3b.png b/readme_folder/image3b.png
deleted file mode 100644
index 3f9c763e15..0000000000
Binary files a/readme_folder/image3b.png and /dev/null differ