diff --git a/index.html b/index.html
index f3869cd..58ac88f 100644
--- a/index.html
+++ b/index.html
@@ -231,7 +231,9 @@ <h3>
        		the text prompt, thus simplifying the learning of mapping from embeddings to image outputs. Finally, to align the pre-trained Stable Diffusion model (1.4) with the embeddings of our modular 
        		encoder, we retrain the conditioning by finetuning the cross-attention weights (2.2). 
 		</p>
-                <image src="MultiFusion/src/imgs/architecture.png" alt="architecture figure"><br>
+                <image src="MultiFusion/src/imgs/architecture.png" alt="architecture figure 1"><br>
+		<image src="/src/imgs/architecture.png" alt="architecture figure 2"><br>
+		<image src="src/imgs/architecture.png" alt="architecture figure 3"><br>
             </div>
         </div>