English
Related papers

Related papers: ResDiT: Evoking the Intrinsic Resolution Scalabili…

200 papers

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Rui Tian , Zuxuan Wu , Qi Dai , Han Hu , Yu Qiao , Yu-Gang Jiang

The diffusion transformer (DiT) architecture has attracted significant attention in image generation, achieving better fidelity, performance, and diversity. However, most existing DiT - based image generation methods focus on global - aware…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Zhen Xiong , Yuqi Li , Chuanguang Yang , Tiao Tan , Zhihong Zhu , Siyuan Li , Yue Ma

Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention mechanism's quadratic scaling with the number of image…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Noam Issachar , Guy Yariv , Sagie Benaim , Yossi Adi , Dani Lischinski , Raanan Fattal

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

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

We identify a core failure mode that occurs when using the usual linear interpolation on rotary positional embeddings (RoPE) for mixed-resolution denoising with Diffusion Transformers. When tokens from different spatial grids are mixed, the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Haoyu Wu , Jingyi Xu , Qiaomu Miao , Dimitris Samaras , Hieu Le

Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Zeyu Lu , Zidong Wang , Di Huang , Chengyue Wu , Xihui Liu , Wanli Ouyang , Lei Bai

The Text-to-Video (T2V) model aims to generate dynamic and expressive videos from textual prompts. The generation pipeline typically involves multiple modules, such as language encoder, Diffusion Transformer (DiT), and Variational…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-17 Heyang Huang , Cunchen Hu , Jiaqi Zhu , Ziyuan Gao , Liangliang Xu , Yizhou Shan , Yungang Bao , Sun Ninghui , Tianwei Zhang , Sa Wang

Recent advances in diffusion models have enabled high-quality image generation, leading to increasing demand for post-generation editing that modifies local regions while preserving global structure. Achieving such flexible and precise…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Hanyi Wang , Han Fang , Zheng Wang , Shilin Wang , Ee-Chien Chang

In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Through detailed exploration, we offer a suite of ready-to-use…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Jiahao Wang , Ning Kang , Lewei Yao , Mengzhao Chen , Chengyue Wu , Songyang Zhang , Shuchen Xue , Yong Liu , Taiqiang Wu , Xihui Liu , Kaipeng Zhang , Shifeng Zhang , Wenqi Shao , Zhenguo Li , Ping Luo

Recent advances indicate that diffusion models hold great promise in image super-resolution. While the latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Kun Cheng , Lei Yu , Zhijun Tu , Xiao He , Liyu Chen , Yong Guo , Mingrui Zhu , Nannan Wang , Xinbo Gao , Jie Hu

Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Shen Zheng , Jiaran Cai , Yuansheng Guan , Shenneng Huang , Xingpei Ma , Junjie Cao , Hanfeng Zhao , Qiang Zhang , Shunsi Zhang , Xiao-Ping Zhang

Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage refinements. We introduce the Dynamic Chunking Diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Akash Haridas , Utkarsh Saxena , Parsa Ashrafi Fashi , Mehdi Rezagholizadeh , Vikram Appia , Emad Barsoum

Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Zhiyu Jin , Xuli Shen , Bin Li , Xiangyang Xue

Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional…

Graphics · Computer Science 2026-02-06 Aryan Mikaeili , Or Patashnik , Andrea Tagliasacchi , Daniel Cohen-Or , Ali Mahdavi-Amiri

Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve…

Machine Learning · Computer Science 2026-05-27 Xing Cong , Hanlin Tang , Kan Liu , Lan Tao , Lin Qu , Chenhao Xie

Instruction-based video editing requires transforming a source video according to a natural-language instruction while preserving irrelevant content and remaining temporally coherent. We argue that existing Diffusion Transformer (DiT)…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Yan Li , Lin Liu , Xiaopeng Zhang , Qi Tian

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Runhui Huang , Jianhua Han , Guansong Lu , Xiaodan Liang , Yihan Zeng , Wei Zhang , Hang Xu

Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to convolutional UNets. However, the isotropic design of DiTs…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Quan Dao , Dimitris Metaxas

Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce training cost, yet na\"ive…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Dogyun Park , Moayed Haji-Ali , Yanyu Li , Willi Menapace , Sergey Tulyakov , Hyunwoo J. Kim , Aliaksandr Siarohin , Anil Kag