Update README.md

README.md

@@ -53,6 +53,10 @@ license: creativeml-openrail-m
       <div style="color: #666; padding-left:8px;"><strong>1024x576</strong> for wide 16:9, <strong>768x768</strong> for square, and <strong>640x1024</strong> for portrait</div>
       <i style="color: #666666e8; padding-left:8px;">Feel free to experiment with higher resolutions, Juusoz made all the examples at higher than recommended resolutions</i>
     </li>
+    <li style="margin-bottom: 10px;">
+      <div style="display: inline-block; width: 120px; font-weight: 500; color: #333;">Vae</div> 
+      <div style="color: #666; padding-left:8px;"><a href="https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.ckpt">vae-ft-mse-840000-ema-pruned.ckpt</a></div>
+    </li>
     <div style="display: flex;">
       <li style="margin-bottom: 10px;">
         <div style="display: inline-block; width: 120px; font-weight: 500; color: #333;">CFG</div> 
@@ -72,17 +76,17 @@ license: creativeml-openrail-m
 <!--Prompt format-->
 <div style="padding:10px; margin: 20px 0; background-color: #f9f9f9; box-shadow: 0 4px 6px rgba(0,0,0,0.1);" id="promptformat">
   <h2 style="font-size:28px; font-family: Arial, Helvetica, sans-serif; font-weight: bold; margin:0; color: #222;">Prompt Format</h2>
-  <p style="font-size: 18px; color: #666;">The prompts we trained on are available in the corresponding T{version} Konosuba prompt list.txt file.</p>
-  <div style="padding:0 8px">
-    <strong style="font-size: 16px; color: #333;">Format:</strong>
-    <code style="font-size: 14px; padding: 6px; background-color: #f5f5f5; border-radius: 4px; color: #000;">Parent tag, description prompt 1, description prompt 2, etc;</code>
+  <p style="font-size: 18px; color: #666;">It is recommended to use booru styled tags to for the prompts.</p>
+  <div style="padding:8px">
+    <strong style="font-size: 16px; color: #333;">Example:</strong>
+    <code style="font-size: 14px; padding: 6px; line-height: 22px; background-color: #f5f5f5; border-radius: 4px; color: #000;">woman, decorated horns, long robes, fog, long curly hair, freckles, solo, masterpiece, reflective, depth of field, caustics, detailed night, forest, leaves, moonlight, eyes, orange hair, green eyes, vines</code>
   </div>
   <div style="padding:8px">
     <strong style="font-size: 16px; color: #333;">Example:</strong>
-    <code style="font-size: 14px; padding: 6px; background-color: #f5f5f5; border-radius: 4px; color: #000;">Megumin, holding staff, casting, close-up; sparkle; night;</code>
+    <code style="font-size: 14px; padding: 6px; line-height: 22px; background-color: #f5f5f5; border-radius: 4px; color: #000;">1girl, solo, skirt, book, glasses, long hair, looking at viewer, bookshelf, jacket, plaid skirt, school uniform, long sleeves, parted lips, semi-rimless eyewear, bangs, blush, holding, blazer, indoors, sweater, under-rim eyewear, red-framed eyewear, holding book, brown eyes, library, sitting</code>
   </div>
-  <p style="font-size: 18px; color: #666;">The <strong style="color: #333;">parent tag</strong> serves as the primary label for the overall theme of the image and acts as the main subject. The <strong style="color: #333;">description prompts</strong> are a comprehensive list of attributes, objects, actions, and other elements that describe the subject in detail. Each subject is separated by a semicolon (;) while the individual attributes, objects, actions, and elements are separated by a comma (,).</p>
-  <p style="font-size: 18px; color: #666;">Just because we haven’t trained on something doesn’t mean the base AI model doesn’t already know what it is, so feel free to get creative and try new things!</p>
+  <p style="font-size: 18px; color: #666;">The tags were generated with <a href="https://github.com/toriato/stable-diffusion-webui-wd14-tagger">WD14 tagger</a> for the dataset.</p>
+  <p style="font-size: 18px; color: #666;">The model has also been fine tuned to be better at handling shorter prompts.</p>
 </div>
 
 <!--Examples-->