# Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

arXiv: https://arxiv.org/abs/2505.14687 · HTML: https://mlsanity.com/paper/2505.14687/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 51 of its 56 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [Q-Diffusion: Quantizing Diffusion Models](https://mlsanity.com/paper/2302.04304/) (2023)

## Built on by (most cited first, 13 of 13)

- [DiCache: Let Diffusion Model Determine Its Own Cache](https://mlsanity.com/paper/2508.17356/) (2025)
- [Bidirectional Sparse Attention for Faster Video Diffusion Training](https://mlsanity.com/paper/2509.01085/) (2025)
- [A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens](https://mlsanity.com/paper/2604.04913/) (2026)
- [QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification](https://mlsanity.com/paper/2509.23681/) (2025)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [Frequency-Aware Flow Matching for High-Quality Image Generation](https://mlsanity.com/paper/2604.15521/) (2026)
- [Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation](https://mlsanity.com/paper/2511.19835/) (2025)
- [UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention](https://mlsanity.com/paper/2510.16325/) (2025)
- [Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration](https://mlsanity.com/paper/2511.22533/) (2025)
- [DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking](https://mlsanity.com/paper/2603.06351/) (2026)
- [Attention Sinks in Diffusion Transformers: A Causal Analysis](https://mlsanity.com/paper/2605.09313/) (2026)
- [ACID: Adaptive Caching for vIDeo generation](https://mlsanity.com/paper/2607.12358/) (2026)
- [SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention](https://mlsanity.com/paper/2608.12780/) (2026)

## Abstract (arXiv)

Diffusion-based Transformers have demonstrated impressive generative capabilities, but their high computational costs hinder practical deployment, for example, generating an 8192× 8192 image can take over an hour on an A100 GPU. In this work, we propose GRAT (GRouping first, ATtending smartly), a training-free attention acceleration strategy for fast image and video generation without compromising output quality. The key insight is to exploit the inherent sparsity in learned attention maps (which tend to be locally focused) in pretrained Diffusion Transformers and leverage better GPU parallelism. Specifically, GRAT first partitions contiguous tokens into non-overlapping groups, aligning both with GPU execution patterns and the local attention structures learned in pretrained generative Transformers. It then accelerates attention by having all query tokens within the same group share a common set of attendable key and value tokens. These key and value tokens are further restricted to structured regions, such as surrounding blocks or criss-cross regions, significantly reducing computational overhead (e.g., attaining a 35.8× speedup over full attention when generating 8192× 8192 images) while preserving essential attention patterns and long-range context. We validate GRAT on pretrained Flux and HunyuanVideo for image and video generation, respectively. In both cases, GRAT achieves substantially faster inference without any fine-tuning, while maintaining the performance of full attention. We hope GRAT will inspire future research on accelerating Diffusion Transformers for scalable visual generation.