Update README.md

README.md

@@ -10,9 +10,7 @@
 [Yu Qiao](https://scholar.google.com/citations?user=gFtI-8QAAAAJ&hl), 
 [Yali Wang†](https://scholar.google.com/citations?user=hD948dkAAAAJ)
 
-[![arXiv](https://img.shields.io/badge/arXiv-2408.10605-b31b1b.svg)](https://arxiv.org/abs/2408.10605)
-[![GitHub](https://img.shields.io/badge/GitHub-MUSES-blue?logo=github)](https://github.com/DINGYANB/MUSES)
-[![Hugging Face Space](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-yellow)](https://huggingface.co/yanboding/MUSES/)
+[![arXiv](https://img.shields.io/badge/arXiv-2408.10605-b31b1b.svg)](https://arxiv.org/abs/2408.10605) [![GitHub](https://img.shields.io/badge/GitHub-MUSES-blue?logo=github)](https://github.com/DINGYANB/MUSES) [![Hugging Face Space](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-yellow)](https://huggingface.co/yanboding/MUSES/)
 
 </div>
 
@@ -20,7 +18,7 @@
 
 Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries.
 
-<img width="800" alt="image" src="https://github.com/DINGYANB/MUSES/blob/main/assets/demo.png">
+<img width="800" alt="image" src="https://huggingface.co/yanboding/MUSES/blob/main/demo.png">
 </a>
 
 
@@ -33,7 +31,7 @@ Our MUSES realize 3D controllable image generation by developing a progressive w
 
 By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects, through an explainable integration of top-down planning and bottom-up generation. 
 
-<img width="800" alt="image" src="https://github.com/DINGYANB/MUSES/blob/main/assets/overview.png">
+<img width="800" alt="image" src="https://huggingface.co/yanboding/MUSES/blob/main/overview.png">
 </a>