--- license: mit pipeline_tag: image-to-image library_name: diffusers ---

REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

Xingjian Leng1*·Jaskirat Singh1*·Yunzhong Hou1·Zhenchang Xing2·Saining Xie3·Liang Zheng1

1 Australian National University   2Data61-CSIRO   3New York University  
*Project Leads 

🌐 Project Page🤗 Models📃 Paper
PWC

teaser

--- 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.

teaser

**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. ## Usage and Training Please refer our [Github Repo](https://github.com/End2End-Diffusion/REPA-E) for detailed notes on end-to-end training and inference using REPA-E. ## 📚 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}, } ```