English
Related papers

Related papers: Efficient Scaling of Diffusion Transformers for Te…

200 papers

Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Bowen Lin , Fanjiang Ye , Yihua Liu , Zhenghui Guo , Boyuan Zhang , Weijian Zheng , Yufan Xu , Tiancheng Xing , Yuke Wang , Chengming Zhang

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Xiaohua Zhai , Alexander Kolesnikov , Neil Houlsby , Lucas Beyer

Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in state-of-the-art models like Stable Diffusion 3 and Flux.1.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Joonghyuk Shin , Alchan Hwang , Yujin Kim , Daneul Kim , Jaesik Park

Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net architectures, where…

Image and Video Processing · Electrical Eng. & Systems 2026-03-16 Junqi Shi , Ming Lu , Xingchen Li , Anle Ke , Ruiqi Zhang , Zhan Ma

Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Alec Helbling , Tuna Han Salih Meral , Ben Hoover , Pinar Yanardag , Duen Horng Chau

Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived quality of audio depends not solely on its content, pitch,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-23 Huadai Liu , Rongjie Huang , Xuan Lin , Wenqiang Xu , Maozong Zheng , Hong Chen , Jinzheng He , Zhou Zhao

Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. While recent studies…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-18 Keon Lee , Dong Won Kim , Jaehyeon Kim , Seungjun Chung , Jaewoong Cho

Recent advancements in diffusion models, particularly the architectural transformation from UNet-based models to Diffusion Transformers (DiTs), significantly improve the quality and scalability of image and video generation. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Lei Chen , Yuan Meng , Chen Tang , Xinzhu Ma , Jingyan Jiang , Xin Wang , Zhi Wang , Wenwu Zhu

In this study, we explore Transformer-based diffusion models for image and video generation. Despite the dominance of Transformer architectures in various fields due to their flexibility and scalability, the visual generative domain…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Shoufa Chen , Mengmeng Xu , Jiawei Ren , Yuren Cong , Sen He , Yanping Xie , Animesh Sinha , Ping Luo , Tao Xiang , Juan-Manuel Perez-Rua

Diffusion-based methods have been acknowledged as a powerful paradigm for end-to-end visuomotor control in robotics. Most existing approaches adopt a Diffusion Policy in U-Net architecture (DP-U), which, while effective, suffers from…

Robotics · Computer Science 2025-09-30 Linzhi Wu , Aoran Mei , Xiyue Wang , Guo-Niu Zhu , Zhongxue Gan

Diffusion transformers (DiTs) have emerged as a powerful architecture for high-fidelity image generation, yet the quadratic cost of self-attention poses a major scalability bottleneck. To address this, linear attention mechanisms have been…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Boyuan Cao , Xingbo Yao , Chenhui Wang , Jiaxin Ye , Yujie Wei , Hongming Shan

This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Zhaoqing Wang , Xiaobo Xia , Runnan Chen , Dongdong Yu , Changhu Wang , Mingming Gong , Tongliang Liu

Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based on a convolutional neural network (CNN) remains dominant in diffusion models. We design a simple and general ViT-based architecture (named U-ViT) for…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Fan Bao , Shen Nie , Kaiwen Xue , Yue Cao , Chongxuan Li , Hang Su , Jun Zhu

This paper presents SANA-1.5, a linear Diffusion Transformer for efficient scaling in text-to-image generation. Building upon SANA-1.0, we introduce three key innovations: (1) Efficient Training Scaling: A depth-growth paradigm that enables…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Enze Xie , Junsong Chen , Yuyang Zhao , Jincheng Yu , Ligeng Zhu , Chengyue Wu , Yujun Lin , Zhekai Zhang , Muyang Li , Junyu Chen , Han Cai , Bingchen Liu , Daquan Zhou , Song Han

Pre-trained stable diffusion models (SD) have shown great advances in visual correspondence. In this paper, we investigate the capabilities of Diffusion Transformers (DiTs) for accurate dense correspondence. Distinct from SD, DiTs exhibit a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Chaofan Gan , Yuanpeng Tu , Xi Chen , Tieyuan Chen , Yuxi Li , Mehrtash Harandi , Weiyao Lin

Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Yongsheng Yu , Wei Xiong , Weili Nie , Yichen Sheng , Shiqiu Liu , Jiebo Luo

Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The prevailing paradigm has commonly employed self-attention…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 ZiYi Dong , Chengxing Zhou , Weijian Deng , Pengxu Wei , Xiangyang Ji , Liang Lin

We present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone: The increase of model parameters is mainly due to more attention…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Dustin Podell , Zion English , Kyle Lacey , Andreas Blattmann , Tim Dockhorn , Jonas Müller , Joe Penna , Robin Rombach

Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Pengtao Chen , Mingzhu Shen , Peng Ye , Jianjian Cao , Chongjun Tu , Christos-Savvas Bouganis , Yiren Zhao , Tao Chen

Diffusion Transformers (DiT) have become a leading architecture in image generation. However, the quadratic complexity of attention mechanisms, which are responsible for modeling token-wise relationships, results in significant latency when…

Computer Vision and Pattern Recognition · Computer Science 2024-12-23 Songhua Liu , Zhenxiong Tan , Xinchao Wang