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

Xingjian Leng^1*   ·   Jaskirat Singh^1*   ·   Yunzhong Hou¹   ·   Zhenchang Xing²  ·   Saining Xie³  ·   Liang Zheng¹ 

¹ Australian National University   ²Data61-CSIRO   ³New York University  
_{^*Project Leads}

🌐 Project Page   🤗 Models   📃 Paper  

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.

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 for detailed notes on end-to-end training and inference using REPA-E.

📚 Citation

@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},
}