Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile

• URL: http://arxiv.org/abs/2502.06155v2
• Date: Mon, 17 Feb 2025 07:08:23 GMT
• Title: Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
• Authors: Hangliang Ding, Dacheng Li, Runlong Su, Peiyuan Zhang, Zhijie Deng, Ion Stoica, Hao Zhang,
• Abstract summary: Diffusion Transformers (DiTs) with 3D full attention suffer from expensive inference due to the complexity of attention computation and numerous sampling steps. This paper addresses the inefficiency issue from two aspects: 1) Prune the 3D full attention based on the redundancy within video data, and 2) Shorten the sampling process by adopting existing multi-step consistency distillation.
• Score: 28.913893318345384
• License:
• Abstract: Despite the promise of synthesizing high-fidelity videos, Diffusion Transformers (DiTs) with 3D full attention suffer from expensive inference due to the complexity of attention computation and numerous sampling steps. For example, the popular Open-Sora-Plan model consumes more than 9 minutes for generating a single video of 29 frames. This paper addresses the inefficiency issue from two aspects: 1) Prune the 3D full attention based on the redundancy within video data; We identify a prevalent tile-style repetitive pattern in the 3D attention maps for video data, and advocate a new family of sparse 3D attention that holds a linear complexity w.r.t. the number of video frames. 2) Shorten the sampling process by adopting existing multi-step consistency distillation; We split the entire sampling trajectory into several segments and perform consistency distillation within each one to activate few-step generation capacities. We further devise a three-stage training pipeline to conjoin the low-complexity attention and few-step generation capacities. Notably, with 0.1% pretraining data, we turn the Open-Sora-Plan-1.2 model into an efficient one that is 7.4x -7.8x faster for 29 and 93 frames 720p video generation with a marginal performance trade-off in VBench. In addition, we demonstrate that our approach is amenable to distributed inference, achieving an additional 3.91x speedup when running on 4 GPUs with sequence parallelism.

Related papers

• Magic 1-For-1: Generating One Minute Video Clips within One Minute [53.07214657235465]
  We present Magic 1-For-1 (Magic141), an efficient video generation model with optimized memory consumption and inference latency. By applying a test time sliding window, we are able to generate a minute-long video within one minute with significantly improved visual quality and motion dynamics.
  arXiv  Detail & Related papers  (2025-02-11T16:58:15Z)
• Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity [59.80405282381126]
  Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability. We propose a training-free framework termed Sparse VideoGen (SVG) that leverages the inherent sparsity in 3D Full Attention to boost inference efficiency. SVG achieves up to 2.28x and 2.33x end-to-end speedup on CogVideoX-v1.5 and HunyuanVideo, respectively, while preserving generation quality.
  arXiv  Detail & Related papers  (2025-02-03T19:29:16Z)
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models [52.32078428442281]
  Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly. Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
  arXiv  Detail & Related papers  (2024-12-10T18:59:50Z)
• Fast and Memory-Efficient Video Diffusion Using Streamlined Inference [41.505829393818274]
  Current video diffusion models exhibit demanding computational requirements and high peak memory usage. We present Streamlined Inference, which leverages the temporal and spatial properties of video diffusion models. Our approach significantly reduces peak memory and computational overhead, making it feasible to generate high-quality videos on a single consumer GPU.
  arXiv  Detail & Related papers  (2024-11-02T07:52:18Z)
• Video-Infinity: Distributed Long Video Generation [73.30145218077074]
  Diffusion models have recently achieved remarkable results for video generation. Our method generates videos up to 2,300 frames in approximately 5 minutes, enabling long video generation at a speed 100 times faster than the prior methods.
  arXiv  Detail & Related papers  (2024-06-24T01:56:12Z)
• DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition [140.66371549815034]
  We propose a new transformer architecture, termed DualFormer, which can effectively and efficiently perform space-time attention for video recognition. We show that DualFormer sets new state-of-the-art 82.9%/85.2% top-1 accuracy on Kinetics-400/600 with around 1000G inference FLOPs which is at least 3.2 times fewer than existing methods with similar performances.
  arXiv  Detail & Related papers  (2021-12-09T03:05:19Z)
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining [58.10436813430554]
  Mini-batch training of graph neural networks (GNNs) requires a lot of computation and data movement. We argue in favor of performing mini-batch training with neighborhood sampling in a distributed multi-GPU environment. We present a sequence of improvements to mitigate these bottlenecks, including a performance-engineered neighborhood sampler. We also conduct an empirical analysis that supports the use of sampling for inference, showing that test accuracies are not materially compromised.
  arXiv  Detail & Related papers  (2021-10-16T02:41:35Z)

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.