RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention
- URL: http://arxiv.org/abs/2512.24086v1
- Date: Tue, 30 Dec 2025 08:55:20 GMT
- Title: RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention
- Authors: Aiyue Chen, Yaofu Liu, Junjian Huang, Guang Lian, Yiwu Yao, Wangli Lan, Jing Lin, Zhixin Ma, Tingting Zhou, Harry Yang,
- Abstract summary: RainFusion2.0 is an online adaptive, hardware-efficient, and low-overhead sparse attention mechanism to accelerate video and image generative models.<n>It can achieve 80% sparsity while achieving an end-to-end speedup of 1.51.8x without compromising video quality.
- Score: 10.041502708600865
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applications. Furthermore, with hardware advancements, a wide range of devices besides graphics processing unit (GPU), such as application-specific integrated circuit (ASIC), have been increasingly adopted for model inference. Sparse attention, which leverages the inherent sparsity of attention by skipping computations for insignificant tokens, is an effective approach to mitigate computational costs. However, existing sparse attention methods have two critical limitations: the overhead of sparse pattern prediction and the lack of hardware generality, as most of these methods are designed for GPU. To address these challenges, this study proposes RainFusion2.0, which aims to develop an online adaptive, hardware-efficient, and low-overhead sparse attention mechanism to accelerate both video and image generative models, with robust performance across diverse hardware platforms. Key technical insights include: (1) leveraging block-wise mean values as representative tokens for sparse mask prediction; (2) implementing spatiotemporal-aware token permutation; and (3) introducing a first-frame sink mechanism specifically designed for video generation scenarios. Experimental results demonstrate that RainFusion2.0 can achieve 80% sparsity while achieving an end-to-end speedup of 1.5~1.8x without compromising video quality. Moreover, RainFusion2.0 demonstrates effectiveness across various generative models and validates its generalization across diverse hardware platforms.
Related papers
- Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation [50.04968365065964]
Diffusion-based talking head models generate high-quality, photorealistic videos but suffer from slow inference.<n>We introduce Lightning-fast Caching-based Parallel denoising prediction (LightningCP)<n>We also propose Decoupled Foreground Attention (DFA) to further accelerate attention computations.
arXiv Detail & Related papers (2025-08-25T02:58:39Z) - Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation [21.87891961960399]
Compact Attention is a hardware-aware acceleration framework featuring three innovations.<n>Our method achieves 1.62.5x acceleration in attention on single- GPU setups.<n>This work provides a principled approach to unlocking efficient long-form video generation through structured sparsity exploitation.
arXiv Detail & Related papers (2025-08-18T14:45:42Z) - PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models [14.14413223631804]
In visual generation, the quadratic complexity of attention mechanisms results in high memory and computational costs.<n>We propose an alternative strategy: *reorganizing* the attention pattern to alleviate the challenges.<n>Inspired by the local aggregation nature of visual feature extraction, we design a novel **Pattern-Aware token ReOrdering (PARO)** technique.
arXiv Detail & Related papers (2025-06-19T06:25:02Z) - FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers [63.788600404496115]
FullDiT2 is an efficient in-context conditioning framework for general controllability in both video generation and editing tasks.<n>FullDiT2 achieves significant computation reduction and 2-3 times speedup in averaged time cost per diffusion step.
arXiv Detail & Related papers (2025-06-04T17:57:09Z) - Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape [38.76559841681518]
A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video length.<n>Existing techniques fail to preserve visual quality at extremely high sparsity levels and might even incur non-negligible compute overheads.<n>We propose Re-ttention, which implements very high sparse attention for visual generation models.
arXiv Detail & Related papers (2025-05-28T22:39:12Z) - RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy [10.53687668536011]
RainFusion exploits inherent sparsity nature in visual data to accelerate attention computation while preserving video quality.<n>Our proposed bf RainFusion is a plug-and-play method that can be seamlessly integrated into state-of-the-art 3D-attention video generation models.
arXiv Detail & Related papers (2025-05-27T11:15:02Z) - Training-Free Efficient Video Generation via Dynamic Token Carving [54.52061549312799]
Jenga is an inference pipeline that combines dynamic attention carving with progressive resolution generation.<n>As a plug-and-play solution, Jenga enables practical, high-quality video generation on modern hardware.
arXiv Detail & Related papers (2025-05-22T16:21:32Z) - DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos.<n>These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
arXiv Detail & Related papers (2025-04-28T09:20:50Z) - Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference [31.901686946969786]
Dovetail is an inference method that leverages the complementary characteristics of heterogeneous devices and the advantages of speculative decoding.<n>Dovetail achieves inference speedups ranging from 1.79x to 10.1x across different devices, while maintaining consistency and stability in the distribution of generated texts.
arXiv Detail & Related papers (2024-12-25T15:45:18Z) - Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and
Algorithm Co-design [66.39546326221176]
Attention-based neural networks have become pervasive in many AI tasks.
The use of the attention mechanism and feed-forward network (FFN) demands excessive computational and memory resources.
This paper proposes a hardware-friendly variant that adopts a unified butterfly sparsity pattern to approximate both the attention mechanism and the FFNs.
arXiv Detail & Related papers (2022-09-20T09:28:26Z) - FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation [81.76975488010213]
Dense optical flow estimation plays a key role in many robotic vision tasks.
Current networks often occupy large number of parameters and require heavy computation costs.
Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations.
arXiv Detail & Related papers (2021-03-08T03:09:37Z)
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.