README.md

---
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">
  <a href="https://scholar.google.com.au/citations?user=GQzvqS4AAAAJ" target="_blank">Xingjian&nbsp;Leng</a><sup>1*</sup> &ensp; <b>&middot;</b> &ensp;
  <a href="https://1jsingh.github.io/" target="_blank">Jaskirat&nbsp;Singh</a><sup>1*</sup> &ensp; <b>&middot;</b> &ensp;
  <a href="https://hou-yz.github.io/" target="_blank">Yunzhong&nbsp;Hou</a><sup>1</sup> &ensp; <b>&middot;</b> &ensp;
  <a href="https://people.csiro.au/X/Z/Zhenchang-Xing/" target="_blank">Zhenchang&nbsp;Xing</a><sup>2</sup>&ensp; <b>&middot;</b> &ensp;
  <a href="https://www.sainingxie.com/" target="_blank">Saining&nbsp;Xie</a><sup>3</sup>&ensp; <b>&middot;</b> &ensp;
  <a href="https://zheng-lab-anu.github.io/" target="_blank">Liang&nbsp;Zheng</a><sup>1</sup>&ensp;
</p>

<p align="center">
  <sup>1</sup> Australian National University &emsp; <sup>2</sup>Data61-CSIRO &emsp; <sup>3</sup>New York University &emsp; <br>
  <sub><sup>*</sup>Project Leads&emsp;</sub>
</p>

<p align="center">
  <a href="https://End2End-Diffusion.github.io">🌐 Project Page</a> &ensp;
  <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> -->
</p>


<!-- <p align="center">
  <img src="https://github.com/End2End-Diffusion/REPA-E/raw/main/assets/vis-examples.jpg" width="100%" alt="teaser">
</p> -->

---

We address a fundamental question: ***Can latent diffusion models and their VAE tokenizer be trained end-to-end?*** While training both components jointly with standard diffusion loss is observed to be ineffective — often degrading final performance — we show that this limitation can be overcome using a simple representation-alignment (REPA) loss. Our proposed method, **REPA-E**, enables stable and effective joint training of both the VAE and the diffusion model.

<p align="center">
  <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: **1.12** with CFG and **1.69** without CFG.


<h1 align="left" style="color:#ff000d">🆕 AutoencoderKL-Compatible Release</h1>

> **New in this release:** We are releasing the **REPA-E E2E-VAE** as a fully **Hugging Face AutoencoderKL** checkpoint — ready to use with `diffusers` out of the box.

We previously released the REPA-E VAE checkpoint, which required loading through the model class in our REPA-E repository.  
This new version provides a **Hugging Face–compatible AutoencoderKL** checkpoint that can be loaded directly via the `diffusers` API — no extra code or custom wrapper needed.  

It offers **plug-and-play compatibility** with diffusion pipelines and can be seamlessly used to build or train new diffusion models.

## ⚡️ Quickstart 
```python
from diffusers import AutoencoderKL

vae = AutoencoderKL.from_pretrained("REPA-E/e2e-sdvae-hf").to("cuda")
```
> Use `vae.encode(...)` / `vae.decode(...)` in your pipeline. (A full example is provided below.)

## 📦 Requirements
The following packages are required to load and run the REPA-E VAEs with the `diffusers` library:

```bash
pip install diffusers>=0.33.0
pip install torch>=2.3.1
```

## 🚀 Example Usage
Below is a minimal example showing how to load and use the REPA-E end-to-end trained SD-VAE with `diffusers`:

```python
from io import BytesIO
import requests

from diffusers import AutoencoderKL
import numpy as np
import torch
from PIL import Image


response = requests.get("https://s3.amazonaws.com/masters.galleries.prod.dpreview.com/2935392.jpg?X-Amz-Expires=3600&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAUIXIAMA3N436PSEA/20251019/us-east-1/s3/aws4_request&X-Amz-Date=20251019T103721Z&X-Amz-SignedHeaders=host&X-Amz-Signature=219dc5f98e5c2e5f3b72587716f75889b8f45b0a01f1bd08dbbc44106e484144")
device = "cuda"

image = torch.from_numpy(
    np.array(
        Image.open(BytesIO(response.content)).resize((512, 512))
    )
).permute(2, 0, 1).unsqueeze(0).to(torch.float32) / 127.5 - 1
image = image.to(device)

vae = AutoencoderKL.from_pretrained("REPA-E/e2e-sdvae-hf").to(device)

with torch.no_grad():
    latents = vae.encode(image).latent_dist.sample()
    reconstructed = vae.decode(latents).sample

```


## 📚 Citation

```bibtex
@article{leng2025repae,
  title={REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers},
  author={Xingjian Leng and Jaskirat Singh and Yunzhong Hou and Zhenchang Xing and Saining Xie and Liang Zheng},
  year={2025},
  journal={arXiv preprint arXiv:2504.10483},
}
```