Related papers: DraftAttention: Fast Video Diffusion via Low-Resol…

Recent advances in video generation have made it possible to produce visually compelling videos, with wide-ranging applications in content creation, entertainment, and virtual reality. However, most existing diffusion transformer based…

Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper,…

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal…

The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices…

The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4 Tensor Cores in Blackwell GPUs to accelerate attention…

Recent guidance methods in diffusion models steer reverse sampling by perturbing the model to construct an implicit weak model and guide generation away from it. Among these approaches, attention perturbation has demonstrated strong…

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…

Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To…

Efficient inference on GPUs using large language models remains challenging due to memory bandwidth limitations, particularly during data transfers between High Bandwidth Memory (HBM) and SRAM in attention computations. Approximate…

Designing sparse attention for diffusion transformers requires reconciling two-dimensional spatial locality with GPU efficiency, a trade-off that current methods struggle to achieve. Existing approaches enforce two-dimensional spatial…

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality trade-offs, and allocate computation uniformly across input spatial tokens, wasting resource allocation to…

Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like smartphones, and practical on-device generation is even…

Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quantisation techniques on Blackwell GPUs to move attention computation to 4-bit precision…

This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end…

Diffusion based approaches to long form text generation suffer from prohibitive computational cost and memory overhead as sequence length increases. We introduce SA-DiffuSeq, a diffusion framework that integrates sparse attention to…

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…

Diffusion Transformer (DiT) has emerged as a powerful model architecture for generating high-quality images and videos. In the case of video DiT, 3D Spatio-Temporal Attention increases token length in proportion to the number of frames,…

As Large Language Models (LLMs) scale to longer context windows, the computational cost of attention mechanisms, which traditionally grows quadratically with input length, presents a critical challenge for real-time and memory-constrained…

Text-to-image diffusion models have demonstrated unprecedented capabilities for flexible and realistic image synthesis. Nevertheless, these models rely on a time-consuming sampling procedure, which has motivated attempts to reduce their…