Luo-Yihong
/

yoso_pixart1024

Model card Files Files and versions Community

Yihong Luo commited on Mar 18

Commit

49b40f7

•

1 Parent(s): 8689b54

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -4,8 +4,8 @@ This algorithm was proposed in YOSO.
 This model is fine-tuning from PixArt, enabling one-step inference to perform text-to-image generation.
-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-1024 (Eq(17) in the paper) as follows:
 ## usage
 ```python

 This model is fine-tuning from PixArt, enabling one-step inference to perform text-to-image generation.
+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-1024 (Eq(15) in the paper) as follows:
+![Construction](construction.jpg)
 ## usage
 ```python