Improve model card with metadata and links

This PR improves the model card by:

- Adding the `pipeline_tag: image-to-image` to reflect the model's functionality.
- Specifying the `library_name: diffusers` as the model uses the Diffusers library.
- Linking to the project page and GitHub repository for detailed usage instructions and examples.

README.md

@@ -1,3 +1,17 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: image-to-image
+library_name: diffusers
+---
+
+<h1 align="center"> REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers </h1>
+
+<p align="center">
+  [🌐 Project Page](https://end2end-diffusion.github.io) &ensp;
+  [📃 Paper](https://arxiv.org/abs/2504.10483) &ensp;
+  [🤗 Github](https://github.com/REPA-E/REPA-E)
+</p>
+
+![](assets/vis-examples.jpg)
+
+REPA-E enables stable and effective joint training of both the VAE and the diffusion model, significantly accelerating training and improving generation quality. It achieves state-of-the-art FID scores on ImageNet 256×256.  For detailed usage instructions, including environment setup, training, and evaluation, please refer to the [project page](https://end2end-diffusion.github.io) and the [GitHub repository](https://github.com/REPA-E/REPA-E).