English
Related papers

Related papers: Foresight: Adaptive Layer Reuse for Accelerated an…

200 papers

Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Jingfeng Yao , Bin Yang , Xinggang Wang

The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Junhyuk So , Jungwon Lee , Eunhyeok Park

Visual generation includes both image and video generation, training probabilistic models to create coherent, diverse, and semantically faithful content from scratch. While early research focused on unconditional sampling, practitioners now…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Zixiang Yang , Yue Ma , Yinhan Zhang , Shanhui Mo , Dongrui Liu , Linfeng Zhang

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Xuehai He , Weixi Feng , Tsu-Jui Fu , Varun Jampani , Arjun Akula , Pradyumna Narayana , Sugato Basu , William Yang Wang , Xin Eric Wang

Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent works show promising results by simply fine-tuning T2I…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Guangkai Xu , Yongtao Ge , Mingyu Liu , Chengxiang Fan , Kangyang Xie , Zhiyue Zhao , Hao Chen , Chunhua Shen

Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Vignesh Sundaresha

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Shuning Chang , Pichao Wang , Jiasheng Tang , Fan Wang , Yi Yang

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Robin Rombach , Andreas Blattmann , Dominik Lorenz , Patrick Esser , Björn Ommer

Diffusion models have demonstrated impressive generation capabilities, particularly with recent advancements leveraging transformer architectures to improve both visual and artistic quality. However, Diffusion Transformers (DiTs) continue…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Hui Zhang , Tingwei Gao , Jie Shao , Zuxuan Wu

Despite the remarkable generation quality of video Diffusion Transformer (DiT) models, their practical deployment is severely hindered by extensive computational requirements. This inefficiency stems from two key challenges: the quadratic…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yuechen Zhang , Jinbo Xing , Bin Xia , Shaoteng Liu , Bohao Peng , Xin Tao , Pengfei Wan , Eric Lo , Jiaya Jia

The content-agnostic, fixed-grid tokenizers used by standard large-scale vision models like Vision Transformer (ViT) and Vision Mamba (Vim) represent a fundamental performance bottleneck, creating a trade-off between capturing fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Shicheng Yin , Kaixuan Yin , Yang Liu , Weixing Chen , Liang Lin

Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remark- able capabilities. However, their practical deployment is of- ten hindered by slow inference speeds and high memory con-…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Sijie Wang , Qiang Wang , Shaohuai Shi

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

Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to…

Hardware Architecture · Computer Science 2026-04-13 Jinqi Wen , Tong Xie , Runsheng Wang , Meng Li

In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Zhengyao Lv , Chenyang Si , Junhao Song , Zhenyu Yang , Yu Qiao , Ziwei Liu , Kwan-Yee K. Wong

In recent years, there has been a significant surge of interest in unifying image comprehension and generation within Large Language Models (LLMs). This growing interest has prompted us to explore extending this unification to videos. The…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Yuying Ge , Yizhuo Li , Yixiao Ge , Ying Shan

Generating high-fidelity long videos with Diffusion Transformers (DiTs) is often hindered by significant latency, primarily due to the computational demands of attention mechanisms. For instance, generating an 8-second 720p video (110K…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Yifei Xia , Suhan Ling , Fangcheng Fu , Yujie Wang , Huixia Li , Xuefeng Xiao , Bin Cui

Text-to-image diffusion models often degrade when sampled at resolutions outside the final training resolution set. Prior work has largely emphasized higher resolution generation, enabling pretrained diffusion models to extrapolate beyond…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Ruozhen He , Moayed Haji-Ali , Ziyan Yang , Vicente Ordonez

Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text-video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Kwon Byung-Ki , Sohwi Lim , Nam Hyeon-Woo , Moon Ye-Bin , Tae-Hyun Oh

Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains. However, their reliance on multiple sequential forward passes significantly limits real-time performance. Previous acceleration methods have…

Computer Vision and Pattern Recognition · Computer Science 2025-02-17 Ziming Liu , Yifan Yang , Chengruidong Zhang , Yiqi Zhang , Lili Qiu , Yang You , Yuqing Yang