From ab9d3e50492b3e29f71ded9246e233065a80a36a Mon Sep 17 00:00:00 2001
From: HannahBenita <77296142+HannahBenita@users.noreply.github.com>
Date: Fri, 1 Dec 2023 12:45:52 +0100
Subject: [PATCH] Update index.html

---
 index.html | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/index.html b/index.html
index 80afda8..9f67a0e 100644
--- a/index.html
+++ b/index.html
@@ -246,7 +246,7 @@ <h4>Image Fidelity and Text-to-Image Alignment</h4>
 		<image src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/evaluation.png" class="img-responsive"><br>
 		<h4>Compositional Robustness</h4>
 		<p>Image Composition is a known limitation of Diffusion Models. Through evaluation of our new benchmark <a href="https://huggingface.co/datasets/AIML-TUDA/MCC-250">MCC-250</a> we show that multimodal prompting leads to more compositional robustness as judged by humans.</p>
-		<image height="100" src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/compositional_robustness.png" class="img-responsive" alt="method"><br>
+		<image height="100px" src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/compositional_robustness.png" class="img-responsive" alt="method"><br>
 		<h4>Multilinguality</h4>
 		<image src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/multilingual_alignment.png" class="img-responsive" alt="method"><br>	
 		<p>Evaluating the alignment of prompt embeddings as well as generated images across multiple languagese we show that well aligned embeddings enable the transfer of multiligualism to downstream tasks even for task-specific monolingual training data.</p>
@@ -259,7 +259,7 @@ <h3>
         Attention Manipulation for Multimodal inference
         </h3>
 	<p> Attention Manipulation allows us to weight image and text tokens at inference time and guide their influence on the resulting generation. </p>
-	<image style='border:1px solid #000000' src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/attn_manipulation.png" class="img-responsive" alt="method"><br>	
+	<image src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/attn_manipulation.png" class="img-responsive" alt="method"><br>	
 	</div>
         </div>
 
@@ -269,19 +269,19 @@ <h3>
 	        Applications
 	        </h3>
 		<h4>Interleaved multilingual, multimodal prompting</h4>
-		<image style='border:1px solid #000000' src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/prompting_example.png" class="img-responsive" alt="method"><br>	
+		<image src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/prompting_example.png" class="img-responsive" alt="method"><br>	
 		<h4>Image Composition</h4>
 		<p>MultiFusion increases expressivness in composition through arbitrary and flexible promptin of image and text sequences.</p>
-		<image style='border:1px solid #000000' src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/image_composition.png" class="img-responsive" alt="method"><br>	
+		<image height="100px" src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/image_composition.png" class="img-responsive" alt="method"><br>	
 		<h4>Negative Prompting</h4>
 		<p>Negative prompting with images enables a more powerful supression than through text prompts.</p>
-		<image style='border:1px solid #000000' src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/negative_prompting.png" class="img-responsive" alt="method"><br>	
+		<image height="100px" src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/negative_prompting.png" class="img-responsive" alt="method"><br>	
 		<h4>Style Modification</h4>
 		MultiFusion enables simple style transfer through one reference image capturing all the facets of a unique style such as color pallette, composition contrast, etc. making elaborate prompts obsolete. Additionally, MultiFusion enables highly individual prompting such as "in the style of a picture I drew".
-		<image style='border:1px solid #000000' src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/style_transfer.png" class="img-responsive" alt="method"><br>	
+		<image src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/style_transfer.png" class="img-responsive" alt="method"><br>	
 		<h4>Image Variation</h4>
 		<p>MultiFusion produces meaningful image variations without the need for inversion or renoising if the input image.</p>
-		<image style='border:1px solid #000000' src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/image_variation.png" class="img-responsive" alt="method"><br>	
+		<image height="100px" src="https://Aleph-Alpha.github.io/MultiFusion/src/imgs/image_variation.png" class="img-responsive" alt="method"><br>	
 	
 	</div>
         </div>