Update README.md

README.md

@@ -15,9 +15,7 @@ PixArt-XL-2-512x512](https://huggingface.co/PixArt-alpha/PixArt-XL-2-512x512), e
 
 We wanna highlight that the YOSO-PixArt was originally trained on 512 resolution. However, we found that we can construct a YOSO that enables generating samples with 1024 resolution by merging with [
 PixArt-XL-2-1024-MS](https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
-) (Section 6.2.1 in the paper) as follows:
-![Construction](construction.jpg)
-The impressive performance indicates the robust generalization ability of our YOSO. 
+) (Section 6.2.1 in the paper). The impressive performance indicates the robust generalization ability of our YOSO. 
 ## usage
 ```python
 import torch