← Back to all news
arXiv Computer Vision By Bingxin Xing, Yu Zhang, Jiatong Ding, Lei Lu, Ping Wang

Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion Transformers

Read the original on arXiv Computer Vision →

Sink‑Sparse Hybrid Attention is a train‑free method that replaces dense self‑attention in Diffusion Transformers with reusable static sink masks and a lightweight pooled‑KV branch, keeping model weights and sampling schedules unchanged. It identifies reusable high‑mass structures from a small offline calibration set and applies them across future generations. Experiments on Wan2.1‑T2V‑1.3B and Z‑Image‑Turbo show 1.54× and 1.57× end‑to‑end speedups while preserving generation quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 21

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

PISA introduces a training‑free Piecewise Sparse Attention mechanism that preserves full attention span while reducing complexity. It keeps exact computation for critical blocks and approximates non‑critical ones using block‑wise Taylor expansion, avoiding the quality loss seen in conventional sparse attention. Experiments show significant speedups—up to 2.57× on Hunyuan‑Video—while maintaining or improving visual quality across video and image generation tasks.

By Haopeng Li, Shitong Shao, Wenliang Zhong, Zikai Zhou, Lichen Bai, Hui Xiong, Zeke Xie
llmsdiffusionefficiency
More like this →
arXiv Computer Vision
Sep 22

SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to $265\times$ Single-GPU Acceleration of Visual Generation

arXiv:2609.23153v1 Announce Type: new Abstract: Video diffusion transformers are expensive because attention dominates long spatiotemporal token sequences. We identify the \emph{high-sparsity trap}:...

By Yuxi Liu, Haoyu Li, Zekun Zhang, Tengxu Sun, Yixiang Cai, Jiayong Li, Yifei Xia, Tianle Liu, Baole Ai, Ang Wang, Jiamang Wang, Lin Qu, Kai Zhang, Kun Yuan, Bin Cui
llmsdiffusionefficiency
More like this →
arXiv Computer Vision
Sep 28

Where Compute Matters: Heterogeneous Attention for Efficient Video Diffusion

The paper introduces HetA-DiT, a heterogeneous attention mechanism for video diffusion models that allocates computation based on token difficulty. A lightweight uncertainty branch predicts denoising difficulty, routing uncertain tokens through dense global attention while applying efficient local attention to reliable tokens. This adaptive routing retains global context where needed, offers a single parameter to balance quality and efficiency, and achieves competitive generation quality while only about 20% of tokens use dense attention.

By Olga Zatsarynna, Denis Korzhenkov, Juergen Gall, Amir Habibian, Mohsen Ghafoorian
llmsdiffusionefficiency
More like this →