Update README.md

README.md

@@ -25,7 +25,7 @@ library_name: diffusers
   <a href="https://huggingface.co/REPA-E">🤗 Models</a> &ensp;
   <a href="https://arxiv.org/abs/2504.10483">📃 Paper</a> &ensp;
   <br>
-  <a href="https://paperswithcode.com/sota/image-generation-on-imagenet-256x256?p=repa-e-unlocking-vae-for-end-to-end-tuning-of"><img src="https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/repa-e-unlocking-vae-for-end-to-end-tuning-of/image-generation-on-imagenet-256x256" alt="PWC"></a>
+  <!-- <a href="https://paperswithcode.com/sota/image-generation-on-imagenet-256x256?p=repa-e-unlocking-vae-for-end-to-end-tuning-of"><img src="https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/repa-e-unlocking-vae-for-end-to-end-tuning-of/image-generation-on-imagenet-256x256" alt="PWC"></a> -->
 </p>
 
 
@@ -41,7 +41,7 @@ We address a fundamental question: ***Can latent diffusion models and their VAE
   <img src="https://github.com/End2End-Diffusion/REPA-E/raw/main/assets/overview.jpg" width="100%" alt="teaser">
 </p>
 
-**REPA-E** significantly accelerates training — achieving over **17×** speedup compared to REPA and **45×** over the vanilla training recipe. Interestingly, end-to-end tuning also improves the VAE itself: the resulting **E2E-VAE** provides better latent structure and serves as a **drop-in replacement** for existing VAEs (e.g., SD-VAE), improving convergence and generation quality across diverse LDM architectures. Our method achieves state-of-the-art FID scores on ImageNet 256×256: **1.26** with CFG and **1.83** without CFG.
+**REPA-E** significantly accelerates training — achieving over **17×** speedup compared to REPA and **45×** over the vanilla training recipe. Interestingly, end-to-end tuning also improves the VAE itself: the resulting **E2E-VAE** provides better latent structure and serves as a **drop-in replacement** for existing VAEs (e.g., SD-VAE), improving convergence and generation quality across diverse LDM architectures. Our method achieves state-of-the-art FID scores on ImageNet 256×256: **1.12** with CFG and **1.69** without CFG.
 
  
 ## Usage and Training