Update README.md

Update the link of SR module architecture figure.

README.md

@@ -40,7 +40,7 @@ image.save("./frog.png")
 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:
 
 <p float="left">
-  <img src="https://raw.githubusercontent.com/kakaobrain/karlo/main/assets/improved_sr_arch.png"/>
+  <img src="https://raw.githubusercontent.com/kakaobrain/karlo/main/assets/improved_sr_arch.jpg"/>
 </p>
 
 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.