Update README.md

README.md

@@ -10,9 +10,9 @@ pinned: false
 🔥 We are the Visual Intelligence Research Section in the Superintelligence Creative Research Laboratory, Electronics and Telecommunications Research Institute, Daejeon, South Korea
 
 🐨 KOALA for text-to-image generation (feat. Knowledge Distillation based Stable Diffusion XL )
-<img src="https://dl.dropboxusercontent.com/scl/fi/lhf2gtwmtxhrtbupj40ra/img-kollava-i2t.png?rlkey=f3ezc1e4ka58t8qla1zls4qyn&dl=1" width="1024px" />
+<img src="https://dl.dropboxusercontent.com/scl/fi/lhf2gtwmtxhrtbupj40ra/img-kollava-i2t.png?rlkey=f3ezc1e4ka58t8qla1zls4qyn&dl=1" width="800px" />
 
 💬 Ko-LLaVA for responding with text when given an image or a video  (feat. Korean Large Language and Vision Assistant)  
 <div align="center">
-<img src="https://dl.dropboxusercontent.com/scl/fi/lhf2gtwmtxhrtbupj40ra/img-kollava-i2t.png?rlkey=f3ezc1e4ka58t8qla1zls4qyn&dl=1" width="1024px" />
+<img src="https://dl.dropboxusercontent.com/scl/fi/lhf2gtwmtxhrtbupj40ra/img-kollava-i2t.png?rlkey=f3ezc1e4ka58t8qla1zls4qyn&dl=1" width="800px" />
 </div>