Update index.html

Author: omnihuman-lab

index.html

@@ -91,16 +91,20 @@ <h3>Generated Videos</h3>
           <video src="video/main2.mp4"></video>
           <video src="video/main3.mp4"></video>
         </div>
+        <div class="video-slider">
+          <video src="video/talk2.mp4"></video>
+          <video src="video/talk3.mp4"></video>
+        </div>
 
+        <!-- 
       <h3>Talking</h3>
         <p>OmniHuman can support input of any aspect ratio in terms of speech. It significantly improves the handling of gestures, which is a challenge for existing methods, and produces highly realistic results. The audio and images for some of the test cases are sourced from <a href="https://www.youtube.com/watch?v=5Jk8qITsqdM&t=127s&ab_channel=TEDxTalks">link1</a>, <a href="https://www.youtube.com/watch?v=ITxWUu6UcWQ&t=251s&ab_channel=TEDxTalks">link2</a>, <a href="https://www.youtube.com/watch?v=oO8w6XcXJUs&ab_channel=RealTimewithBillMaher">link3</a>, <a href="https://www.youtube.com/watch?v=oO8w6XcXJUs&ab_channel=RealTimewithBillMaher">link4</a>.</p>
         <div class="video-slider">
-          <video src="video/talk1.mp4"></video>
           <video src="video/talk2.mp4"></video>
           <video src="video/talk3.mp4"></video>
         </div>
         
-
+ -->
 
 
       <h3>Diversity</h3>
@@ -117,18 +121,7 @@ <h3>Diversity</h3>
           <video src="video/div7.mp4"></video>
         </div>
 
-      <h3>More Halfbody Cases with Hands</h3>
-        <p>Here, we also provide additional examples specifically showcasing gesture movements. Some input images and audio come from TED, Pexels and AIGC.</p>
-        <div class="video-slider">
-          <video src="video/hands1.mp4"></video>
-          <video src="video/hands2.mp4"></video>
-          <video src="video/hands3.mp4"></video>
-        </div>
-        <div class="video-slider">
-<!--           <video src="video/hands4.mp4"></video> -->
-          <video src="video/hands5.mp4"></video>
-          <video src="video/hands6.mp4"></video>
-        </div>
+
 
 
       <h3>More Portrait Cases</h3>
@@ -165,10 +158,8 @@ <h3>Singing</h3>
 
 
       <h3>Compatibility with Video Driving</h3>
-        <p>Due to OmniHuman's mixed condition training characteristics, it can support not only audio driving but also video driving to mimic specific video actions, as well as combined audio and video driving (case is from <a href="https://www.youtube.com/watch?v=AbpNlshqtJc&ab_channel=TED">link</a>) to control specific body parts like recent methods. Below, we demonstrate these capabilities.</p>
-        <div class="video-slider">
-          <video src="video/comp.mp4"></video>
-        </div>
+        <p>Due to OmniHuman's mixed condition training characteristics, it can support not only audio driving but also video driving to mimic specific video actions, as well as combined audio and video driving to control specific body parts like recent methods.
+
 
 
       <h3>Ethics Concerns</h3>