EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching

• URL: http://arxiv.org/abs/2410.23788v1
• Date: Thu, 31 Oct 2024 10:13:05 GMT
• Title: EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
• Authors: Xinwang Chen, Ning Liu, Yichen Zhu, Feifei Feng, Jian Tang,
• Abstract summary: Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs. This work proposes the Efficient Diffusion Transformer (EDT) framework to reduce the computation budget of transformer-based DPMs. With lower FID, EDT-S, EDT-B, and EDT-XL attained speed-ups of 3.93x, 2.84x, and 1.92x respectively in the training phase, and 2.29x, 2.29x, and 2.22x respectively in inference.
• Score: 20.728136287477277
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical applications. To reduce the computation budget of transformer-based DPMs, this work proposes the Efficient Diffusion Transformer (EDT) framework. The framework includes a lightweight-design diffusion model architecture, and a training-free Attention Modulation Matrix and its alternation arrangement in EDT inspired by human-like sketching. Additionally, we propose a token relation-enhanced masking training strategy tailored explicitly for EDT to augment its token relation learning capability. Our extensive experiments demonstrate the efficacy of EDT. The EDT framework reduces training and inference costs and surpasses existing transformer-based diffusion models in image synthesis performance, thereby achieving a significant overall enhancement. With lower FID, EDT-S, EDT-B, and EDT-XL attained speed-ups of 3.93x, 2.84x, and 1.92x respectively in the training phase, and 2.29x, 2.29x, and 2.22x respectively in inference, compared to the corresponding sizes of MDTv2. The source code is released at https://github.com/xinwangChen/EDT.

Related papers

• VAE-REPA: Variational Autoencoder Representation Alignment for Efficient Diffusion Training [53.09658039757408]
  This paper proposes textbfnamex, a lightweight intrinsic guidance framework for efficient diffusion training.<n>name aligns the intermediate latent features of diffusion transformers with VAE features via a lightweight projection layer, supervised by a feature alignment loss.<n>Experiments demonstrate that name improves both generation quality and training convergence speed compared to vanilla diffusion transformers.
  arXiv  Detail & Related papers  (2026-01-25T13:22:38Z)
• E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources [12.244453688491731]
  Efficient Multimodal Diffusion Transformer (E-MMDiT) is an efficient and lightweight multimodal diffusion model with only 304M parameters for fast image synthesis.<n>Our model for 512px generation, trained with only 25M public data in 1.5 days on a single node of 8 AMD MI300X GPUs, achieves 0.66 on GenEval and easily reaches to 0.72 with some post-training techniques such as GRPO.
  arXiv  Detail & Related papers  (2025-10-31T03:13:08Z)
• SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation [62.14510717860079]
  We propose a Synergistic Diffusion-Autoregression paradigm that unifies the training efficiency of autoregressive models with the parallel inference capability of diffusion.<n>SDAR performs a lightweight paradigm conversion that transforms a well-trained autoregressive (AR) model into a blockwise diffusion model through brief, data-efficient adaptation.<n>Building on this insight, SDAR achieves efficient AR-to-diffusion conversion with minimal cost, preserving AR-level performance while enabling parallel generation.
  arXiv  Detail & Related papers  (2025-10-07T17:29:28Z)
• REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers [52.55041244336767]
  Traditional deep-learning wisdom dictates that end-to-end training is often preferable when possible.<n>For latent diffusion transformers, it is observed that end-to-end training both VAE and diffusion-model using standard diffusion-loss is ineffective.<n>We show that while diffusion loss is ineffective, end-to-end training can be unlocked through the representation-alignment (REPA) loss.
  arXiv  Detail & Related papers  (2025-04-14T17:59:53Z)
• DyDiT++: Dynamic Diffusion Transformers for Efficient Visual Generation [66.86241453156225]
  Diffusion Transformer (DiT) has demonstrated superior performance but suffers from substantial computational costs. We propose textbfDynamic textbfDiffusion textbfTransformer (DyDiT) DyDiT adjusts its computation along both emphtimestep and emphspatial dimensions.
  arXiv  Detail & Related papers  (2025-04-09T11:48:37Z)
• EDiT: Efficient Diffusion Transformers with Linear Compressed Attention [11.36660486878447]
  quadratic scaling properties of the attention in DiTs hinder image generation with higher resolution or on devices with limited resources. We introduce an efficient diffusion transformer (EDiT) to alleviate these efficiency bottlenecks. We demonstrate the effectiveness of the EDiT and MM-EDiT architectures by integrating them into PixArt-Sigma(conventional DiT) and Stable Diffusion 3.5-Medium (MM-DiT)
  arXiv  Detail & Related papers  (2025-03-20T21:58:45Z)
• EXION: Exploiting Inter- and Intra-Iteration Output Sparsity for Diffusion Models [12.931893842093718]
  We present EXION, the first SW-HW co-designed diffusion accelerator. It exploits the unique inter- and intra-iteration output sparsity in diffusion models. It achieves dramatic improvements in performance and energy efficiency by 3.2-379.3x and 45.1-3067.6x compared to a server GPU and by 42.6-1090.9x and 196.9-4668.2x compared to an edge GPU.
  arXiv  Detail & Related papers  (2025-01-10T03:07:28Z)
• Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models [33.519892081718716]
  We propose aligning the latent space with pre-trained vision foundation models when training the visual tokenizers. Our proposed VA-VAE significantly expands the reconstruction-generation frontier of latent diffusion models. We build an enhanced DiT baseline with improved training strategies and architecture designs, termed LightningDiT.
  arXiv  Detail & Related papers  (2025-01-02T18:59:40Z)
• Shrinking the Giant : Quasi-Weightless Transformers for Low Energy Inference [0.30104001512119216]
  Building models with fast and energy-efficient inference is imperative to enable a variety of transformer-based applications. We build on an approach for learning LUT networks directly via an Extended Finite Difference method. This allows for a computational and energy-efficient inference solution for transformer-based models.
  arXiv  Detail & Related papers  (2024-11-04T05:38:56Z)
• Dynamic Diffusion Transformer [67.13876021157887]
  Diffusion Transformer (DiT) has demonstrated superior performance but suffers from substantial computational costs. We propose Dynamic Diffusion Transformer (DyDiT), an architecture that dynamically adjusts its computation along both timestep and spatial dimensions during generation. With 3% additional fine-tuning, our method reduces the FLOPs of DiT-XL by 51%, accelerates generation by 1.73, and achieves a competitive FID score of 2.07 on ImageNet.
  arXiv  Detail & Related papers  (2024-10-04T14:14:28Z)
• MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation [44.74056930805525]
  We introduce a novel Masked Diffusion Transformer for co-speech gesture generation, referred to as MDT-A2G. This model employs a mask modeling scheme specifically designed to strengthen temporal relation learning among sequence gestures. Experimental results demonstrate that MDT-A2G excels in gesture generation, boasting a learning speed that is over 6$times$ faster than traditional diffusion transformers.
  arXiv  Detail & Related papers  (2024-08-06T17:29:01Z)
• FORA: Fast-Forward Caching in Diffusion Transformer Acceleration [39.51519525071639]
  Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos. Fast-FORward CAching (FORA) is designed to accelerate DiT by exploiting the repetitive nature of the diffusion process.
  arXiv  Detail & Related papers  (2024-07-01T16:14:37Z)
• Binarized Diffusion Model for Image Super-Resolution [61.963833405167875]
  Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating advanced diffusion models (DMs) Existing binarization methods result in significant performance degradation. We introduce a novel binarized diffusion model, BI-DiffSR, for image SR.
  arXiv  Detail & Related papers  (2024-06-09T10:30:25Z)
• TerDiT: Ternary Diffusion Models with Transformers [83.94829676057692]
  TerDiT is a quantization-aware training scheme for ternary diffusion models with transformers. We focus on the ternarization of DiT networks and scale model sizes from 600M to 4.2B.
  arXiv  Detail & Related papers  (2024-05-23T17:57:24Z)
• Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory [11.3128832831327]
  Increasing the size of a Transformer model does not always lead to enhanced performance. improved generalization ability occurs as the model memorizes the training samples. We present a theoretical framework that sheds light on the memorization process and performance dynamics of transformer-based language models.
  arXiv  Detail & Related papers  (2024-05-14T15:48:36Z)
• SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer [102.39050180060913]
  Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. Recent breakthroughs have been driven by mask strategy that significantly improves the training efficiency of DiT with additional intra-image contextual learning. In this work, we address these limitations by novelly unleashing the self-supervised discrimination knowledge to boost DiT training.
  arXiv  Detail & Related papers  (2024-03-25T17:59:35Z)
• 2-D SSM: A General Spatial Layer for Visual Transformers [79.4957965474334]
  A central objective in computer vision is to design models with appropriate 2-D inductive bias. We leverage an expressive variation of the multidimensional State Space Model. Our approach introduces efficient parameterization, accelerated computation, and a suitable normalization scheme.
  arXiv  Detail & Related papers  (2023-06-11T09:41:37Z)
• Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation [130.30465659190773]
  Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices. We introduce a novel GAN compression method, termed DMAD, by proposing a Differentiable Mask and a co-Attention Distillation. Experiments show DMAD can reduce the Multiply Accumulate Operations (MACs) of CycleGAN by 13x and that of Pix2Pix by 4x while retaining a comparable performance against the full model.
  arXiv  Detail & Related papers  (2020-11-17T02:39:19Z)

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.