Yihong Luo commited on
Commit
e494dc2
1 Parent(s): a662069

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -4,6 +4,9 @@ This algorithm was proposed in YOSO.
4
 
5
  This model is fine-tuning from PixArt, enabling one-step inference to perform text-to-image generation.
6
 
 
 
 
7
  ## usage
8
  ```python
9
  from diffusers import PixArtAlphaPipeline, LCMScheduler, Transformer2DModel, DPMSolverMultistepScheduler
 
4
 
5
  This model is fine-tuning from PixArt, enabling one-step inference to perform text-to-image generation.
6
 
7
+ 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:
8
+
9
+
10
  ## usage
11
  ```python
12
  from diffusers import PixArtAlphaPipeline, LCMScheduler, Transformer2DModel, DPMSolverMultistepScheduler