pith. sign in

arxiv: 2505.21036 · v2 · pith:QV2SWJBInew · submitted 2025-05-27 · 💻 cs.CV · cs.AI

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy

classification 💻 cs.CV cs.AI
keywords attentionvideogenerationmodelspatternrainfusionmethodsparse
0
0 comments X
read the original abstract

Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion}, a novel training-free sparse attention method that exploits inherent sparsity nature in visual data to accelerate attention computation while preserving video quality. Specifically, we identify three unique sparse patterns in video generation attention calculations--Spatial Pattern, Temporal Pattern and Textural Pattern. The sparse pattern for each attention head is determined online with negligible overhead (\textasciitilde\,0.2\%) with our proposed {\bf ARM} (Adaptive Recognition Module) during inference. 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 without additional training or calibration. We evaluate our method on leading open-sourced models including HunyuanVideo, OpenSoraPlan-1.2 and CogVideoX-5B, demonstrating its broad applicability and effectiveness. Experimental results show that RainFusion achieves over {\bf 2\(\times\)} speedup in attention computation while maintaining video quality, with only a minimal impact on VBench scores (-0.2\%).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention

    cs.CV 2026-05 unverdicted novelty 7.0

    HASTE delivers up to 1.93x speedup on Wan2.1 video DiTs via head-wise adaptive sparse attention using temporal mask reuse and error-guided per-head calibration while preserving video quality.

  2. Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering

    cs.CV 2026-03 conditional novelty 7.0

    Attention sparsity in video DiTs is an input-stable layer-wise property, enabling offline profiling and online bidirectional QK co-clustering for up to 1.93x speedup with PSNR up to 29 dB.

  3. RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention

    cs.CV 2025-12 unverdicted novelty 4.0

    RainFusion2.0 delivers 80% sparse attention in DiT models for video and image generation, yielding 1.5-1.8x end-to-end speedup with no quality loss via hardware-efficient block-wise prediction.