add images

index.html

@@ -175,8 +175,10 @@ <h1 class="display-2 fw-bold title">
     <div class="album py-5 col-lg-5 mx-auto text-bg-dark">
         <div class="container">
             <h1>Abstract</h1>
-
+<!-- 
             <p style="text-align: justify;">
+
+              
               We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies au
               toregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide
               range of vision-language tasks including visual question-answering, text-to-image
@@ -185,7 +187,14 @@ <h1>Abstract</h1>
               to existing individual models tailored for understanding or generation, which with
               an equivalent or larger number of parameters. This signifiantly highlights its potential as a next-generation foundation model. Code and models are released at
               <a href='https://github.com/showlab/Show-o' target='_blank'>https://github.com/showlab/Show-o</a>.
-            </p>
+            </p> -->
+
+            <p style="text-align: justify;">
+              We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.
+            </p> 
+
+
+
         </div>
     </div>