Update README.md

README.md

@@ -16,7 +16,7 @@ The Hummingbird model generates high-quality, diverse images from a multimodal c
 
 ### Official implementation of paper: [Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment](https://openreview.net/pdf?id=6kPBThI6ZJ)
 
-![image/png](/assets/teaser_comparison_v1.png)
+![image/png](https://roar-ai.github.io/hummingbird/static/images/teaser_comparison_v1.png)
 
 ## Prerequisites