Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

• URL: http://arxiv.org/abs/2410.06940v4
• Date: Wed, 18 Jun 2025 04:35:42 GMT
• Title: Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
• Authors: Sihyun Yu, Sangkyung Kwak, Huiwon Jang, Jongheon Jeong, Jonathan Huang, Jinwoo Shin, Saining Xie,
• Abstract summary: One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
• Score: 72.48325960659822
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned through recent self-supervised learning methods. We argue that one main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations. Moreover, training can be made easier by incorporating high-quality external visual representations, rather than relying solely on the diffusion models to learn them independently. We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders. The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs. For instance, our method can speed up SiT training by over 17.5$\times$, matching the performance (without classifier-free guidance) of a SiT-XL model trained for 7M steps in less than 400K steps. In terms of final generation quality, our approach achieves state-of-the-art results of FID=1.42 using classifier-free guidance with the guidance interval.

Related papers

• Learning Diffusion Models with Flexible Representation Guidance [37.301580601018365]
  We present a systematic framework for incorporating representation guidance into diffusion models.<n>We introduce two new strategies for enhancing representation alignment in diffusion models.<n>Experiments across image, protein sequence, and molecule generation tasks demonstrate superior performance as well as accelerated training.
  arXiv  Detail & Related papers  (2025-07-11T19:29:02Z)
• DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning [53.27049077100897]
  generative pre-training has been shown to yield discriminative representations, paving the way towards unified visual generation and understanding.<n>This work introduces self-conditioning, a mechanism that internally leverages the rich semantics inherent in denoising network to guide its own decoding layers.<n>Results are compelling: our method boosts both generation FID and recognition accuracy with 1% computational overhead and generalizes across diverse diffusion architectures.
  arXiv  Detail & Related papers  (2025-05-16T08:47:16Z)
• No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves [59.79343544931784]
  Self-Representation Alignment (SRA) is a simple yet straightforward method that obtains representation guidance through a self-distillation manner.<n> Experimental results indicate that applying SRA to DiTs and SiTs yields consistent performance improvements.
  arXiv  Detail & Related papers  (2025-05-05T17:58:05Z)
• Efficient Generative Model Training via Embedded Representation Warmup [6.783363935446626]
  Diffusion models excel at generating high-dimensional data but fall short in training efficiency and representation quality compared to self-supervised methods. We identify a key bottleneck: the underutilization of high-quality, semantically rich representations during training. We propose Embedded Representation Warmup (ERW), a plug-and-play framework where in the first stage we get the ERW module.
  arXiv  Detail & Related papers  (2025-04-14T12:43:17Z)
• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• Plug-and-Play Diffusion Distillation [14.359953671470242]
  We propose a new distillation approach for guided diffusion models. An external lightweight guide model is trained while the original text-to-image model remains frozen. We show that our method reduces the inference of classifier-free guided latent-space diffusion models by almost half.
  arXiv  Detail & Related papers  (2024-06-04T04:22:47Z)
• Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling [2.91204440475204]
  Diffusion Probabilistic Models (DPMs) have emerged as a powerful class of deep generative models. They rely on sequential denoising steps during sample generation. We propose a novel method that integrates denoising phases directly into the model's architecture.
  arXiv  Detail & Related papers  (2024-05-31T08:19:44Z)
• Denoising Autoregressive Representation Learning [13.185567468951628]
  Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We show that the learned representation can be improved by using tailored noise schedules and longer training in larger models.
  arXiv  Detail & Related papers  (2024-03-08T10:19:00Z)
• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
  Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI) In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion) Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
  arXiv  Detail & Related papers  (2024-02-15T18:59:18Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training. It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models. While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• Denoising Diffusion Autoencoders are Unified Self-supervised Learners [58.194184241363175]
  This paper shows that the networks in diffusion models, namely denoising diffusion autoencoders (DDAE), are unified self-supervised learners. DDAE has already learned strongly linear-separable representations within its intermediate layers without auxiliary encoders. Our diffusion-based approach achieves 95.9% and 50.0% linear evaluation accuracies on CIFAR-10 and Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-03-17T04:20:47Z)
• Diffusion-Based Representation Learning [65.55681678004038]
  We augment the denoising score matching framework to enable representation learning without any supervised signal. In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective. Using the same approach, we propose to learn an infinite-dimensional latent code that achieves improvements of state-of-the-art models on semi-supervised image classification.
  arXiv  Detail & Related papers  (2021-05-29T09:26:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.