{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/repa-e-unlocking-vae-for-end-to-end-tuning-of","title":"REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers","arxiv_id":null,"date":"2025-04-15","proceeding":null,"authors":["Xingjian Leng","Jaskirat Singh","Yunzhong Hou","Zhenchang Xing","Saining Xie","Liang Zheng"],"abstract":"In this paper we tackle a fundamental question: \"Can we train latent diffusion models together with the variational auto-encoder (VAE) tokenizer in an end-to-end manner?\" Traditional deep-learning wisdom dictates that end-to-end training is often preferable when possible. However, for latent diffusion transformers, it is observed that end-to-end training both VAE and diffusion-model using standard diffusion-loss is ineffective, even causing a degradation in final performance. We show that while diffusion loss is ineffective, end-to-end training can be unlocked through the representation-alignment (REPA) loss -- allowing both VAE and diffusion model to be jointly tuned during the training process. Despite its simplicity, the proposed training recipe (REPA-E) shows remarkable performance; speeding up diffusion model training by over 17x and 45x over REPA and vanilla training recipes, respectively. Interestingly, we observe that end-to-end tuning with REPA-E also improves the VAE itself; leading to improved latent space structure and downstream generation performance. In terms of final performance, our approach sets a new state-of-the-art; achieving FID of 1.26 and 1.83 with and without classifier-free guidance on ImageNet 256 x 256. Code is available at https://end2end-diffusion.github.io/.","url_abs":"https://arxiv.org/abs/2504.10483","url_pdf":"https://arxiv.org/pdf/2504.10483","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"repa-e-unlocking-vae-for-end-to-end-tuning-of","repo_url":"https://github.com/End2End-Diffusion/REPA-E","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"SiT-XL/2 + REPA-E","rank_in_archive_order":7,"of":94,"metrics":{"FID":"1.26","Inception score":"314.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}