Add affiliation

app.py

@@ -19,21 +19,20 @@ with gr.Blocks(css='style.css') as demo:
         <h1 style="font-weight: 900; font-size: 3rem; margin: 0rem">
             Text2Video-Zero
         </h1>
-        <h2 style="font-weight: 450; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
-        We built <b>Text2Video-Zero</b>,  a first zero-shot text-to-video synthesis diffusion framework, that enables low cost yet high-quality and consistent video generation with only pre-trained text-to-image diffusion models without any training on videos or optimization!
-        Text2Video-Zero also naturally supports cool derivative works of pre-trained text-to-image models such as Instruct Pix2Pix, ControlNet and DreamBooth, and based on which we present Video Instruct Pix2Pix, Pose Conditional, Edge Conditional and, Edge Conditional and DreamBooth Specialized applications.
-        We hope our Text2Video-Zero will further democratize AI and empower creativity of everyone by unleashing the zero-shot video generation and editing capacity of the amazing text-to-image models and encourages future research!
-        </h2>
-        <h3 style="font-weight: 450; font-size: 1rem; margin: 0rem">
+        <h2 style="font-weight: 450; font-size: 1rem; margin: 0rem">
         Levon Khachatryan<sup>1*</sup>, Andranik Movsisyan<sup>1*</sup>, Vahram Tadevosyan<sup>1*</sup>, Roberto Henschel<sup>1*</sup>, Zhangyang Wang<sup>1,2</sup>, Shant Navasardyan<sup>1</sup>
         and <a href="https://www.humphreyshi.com/home">Humphrey Shi</a><sup>1,3,4</sup>
         [<a href="https://arxiv.org/abs/2303.13439" style="color:blue;">arXiv</a>] 
         [<a href="https://github.com/Picsart-AI-Research/Text2Video-Zero" style="color:blue;">GitHub</a>]
-        </h3>
-
-        <h3 style="font-weight: 450; font-size: 1rem; margin: 0rem">
+        </h2>
+        <h2 style="font-weight: 450; font-size: 1rem; margin: 0rem">
         <sup>1</sup>Picsart AI Resarch (PAIR), <sup>2</sup>UT Austin, <sup>3</sup>U of Oregon, <sup>4</sup>UIUC
-        </h3>
+        </h2>
+        <h2 style="font-weight: 450; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
+        We built <b>Text2Video-Zero</b>,  a first zero-shot text-to-video synthesis diffusion framework, that enables low cost yet high-quality and consistent video generation with only pre-trained text-to-image diffusion models without any training on videos or optimization!
+        Text2Video-Zero also naturally supports cool derivative works of pre-trained text-to-image models such as Instruct Pix2Pix, ControlNet and DreamBooth, and based on which we present Video Instruct Pix2Pix, Pose Conditional, Edge Conditional and, Edge Conditional and DreamBooth Specialized applications.
+        We hope our Text2Video-Zero will further democratize AI and empower creativity of everyone by unleashing the zero-shot video generation and editing capacity of the amazing text-to-image models and encourages future research!
+        </h2>
         </div>
         """)