ywlee88 commited on
Commit
4ba0b2d
1 Parent(s): 70ed488

update README

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ KOALA-700M-LLaVA-Caption and KOALA-1B-LLaVA-Caption is trained on the synthesize
27
 
28
  ## Abstract
29
  ### TL;DR
30
- > We propose a fast text-to-image model, called KOALA, by compressing SDXL's U-Net and distilling knowledge from SDXL into our model. KOALA-700M can generate a 1024x1024 image in less than 1.5 seconds on an NVIDIA 4090 GPU, which is more than 2x faster than SDXL.
31
 
32
  <details><summary>FULL abstract</summary>
33
  Stable diffusion is the mainstay of the text-to-image (T2I) synthesis in the community due to its generation performance and open-source nature.
 
27
 
28
  ## Abstract
29
  ### TL;DR
30
+ > We propose a fast text-to-image model, called KOALA, by compressing SDXL's U-Net and distilling knowledge from SDXL into our model. KOALA-700M can generate a 1024x1024 image in less than 1.5 seconds on an NVIDIA 4090 GPU, which is more than 2x faster than SDXL. KOALA-700M can be used as a decent alternative between SDM and SDXL in limited resources.
31
 
32
  <details><summary>FULL abstract</summary>
33
  Stable diffusion is the mainstay of the text-to-image (T2I) synthesis in the community due to its generation performance and open-source nature.