shkim-kb commited on
Commit
3e578ac
1 Parent(s): c8dc097

Update README.md

Browse files

Update the link of SR module architecture figure.

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -40,7 +40,7 @@ image.save("./frog.png")
40
  Karlo is a text-conditional diffusion model based on unCLIP, composed of prior, decoder, and super-resolution modules. In this repository, we include the improved version of the standard super-resolution module for upscaling 64px to 256px only in 7 reverse steps, as illustrated in the figure below:
41
 
42
  <p float="left">
43
- <img src="https://raw.githubusercontent.com/kakaobrain/karlo/main/assets/improved_sr_arch.png"/>
44
  </p>
45
 
46
  In specific, the standard SR module trained by DDPM objective upscales 64px to 256px in the first 6 denoising steps based on the respacing technique. Then, the additional fine-tuned SR module trained by [VQ-GAN](https://compvis.github.io/taming-transformers/)-style loss performs the final reverse step to recover high-frequency details. We observe that this approach is very effective to upscale the low-resolution in a small number of reverse steps.
 
40
  Karlo is a text-conditional diffusion model based on unCLIP, composed of prior, decoder, and super-resolution modules. In this repository, we include the improved version of the standard super-resolution module for upscaling 64px to 256px only in 7 reverse steps, as illustrated in the figure below:
41
 
42
  <p float="left">
43
+ <img src="https://raw.githubusercontent.com/kakaobrain/karlo/main/assets/improved_sr_arch.jpg"/>
44
  </p>
45
 
46
  In specific, the standard SR module trained by DDPM objective upscales 64px to 256px in the first 6 denoising steps based on the respacing technique. Then, the additional fine-tuned SR module trained by [VQ-GAN](https://compvis.github.io/taming-transformers/)-style loss performs the final reverse step to recover high-frequency details. We observe that this approach is very effective to upscale the low-resolution in a small number of reverse steps.