Update app.py

app.py

@@ -157,16 +157,22 @@ DanTagGen(Danbooru Tag Generator) is a LLM model designed for generating Danboou
 It aims to provide user a more convinient way to make prompts for Text2Image model which is trained on Danbooru datasets.
 
 #### How to use it:
-1. Fill the informations on the left most section.
-2. Add the general tags you want to use. ("prompt before refined")
+1. Fill the informations on the left section.
+2. Put the general tags you want to use into the "Input your general tags" textarea. ("prompt before refined")
 3. If you want to ban some tags. Put them into the "black list" text area.
 4. Choose the target length: **Long or Short is recommended**
     * Very Short: around 10 tags
     * Short: around 20 tags
     * Long: around 40 tags
     * very long: around 60 tags
-5. Submit!!
-6. You will get formated result on the upper-right section, LLM raw result on the bottom-right section.
+5. Adjust some parameters
+    * Width and height is for calculating the aspect ratio. It is recommended to directly put the height and width you want to use
+6. Submit!!
+7. You will get formated result on the upper-right section, LLM raw result on the bottom-right section.
+
+#### Notice
+The formated result use same format as what Kohaku-XL Delta used. <br>
+The performance of using the output from this demo for other model is not guaranteed.
 """)
         with gr.Row():
             with gr.Column(scale=4):