# BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers

arXiv: https://arxiv.org/abs/2503.15927 · HTML: https://mlsanity.com/paper/2503.15927/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 47 of its 60 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [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)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://mlsanity.com/paper/2408.11039/) (2024)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)

## Built on by (most cited first, 24 of 24)

- [FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation](https://mlsanity.com/paper/2505.20353/) (2025)
- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers](https://mlsanity.com/paper/2506.05096/) (2025)
- [TC-Pad'e: Trajectory-Consistent Pad'e Approximation for Diffusion Acceleration](https://mlsanity.com/paper/2603.02943/) (2026)
- [Causality in Video Diffusers is Separable from Denoising](https://mlsanity.com/paper/2602.10095/) (2026)
- [DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers](https://mlsanity.com/paper/2602.16968/) (2026)
- [Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers](https://mlsanity.com/paper/2603.10744/) (2026)
- [AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation](https://mlsanity.com/paper/2603.12575/) (2026)
- [Sortblock: Similarity-Aware Feature Reuse for Diffusion Model](https://mlsanity.com/paper/2508.00412/) (2025)
- [Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration](https://mlsanity.com/paper/2511.22533/) (2025)
- [ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE](https://mlsanity.com/paper/2606.06060/) (2026)
- [Budget-Constrained Step-Level Diffusion Caching](https://mlsanity.com/paper/2606.13496/) (2026)
- [Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration](https://mlsanity.com/paper/2508.12691/) (2025)
- [Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution](https://mlsanity.com/paper/2509.23980/) (2025)
- [Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness](https://mlsanity.com/paper/2603.00519/) (2026)
- [H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models](https://mlsanity.com/paper/2510.27171/) (2025)
- [FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers](https://mlsanity.com/paper/2511.20390/) (2025)
- [BAG: Budget-Aware Gating for Diffusion Caching](https://mlsanity.com/paper/2608.09231/) (2026)
- [Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models](https://mlsanity.com/paper/2511.21122/) (2025)
- [CorGi: Contribution-Guided Block-Wise Interval Caching for Training-Free Acceleration of Diffusion Transformers](https://mlsanity.com/paper/2512.24195/) (2025)
- [MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers](https://mlsanity.com/paper/2606.15615/) (2026)
- [SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation](https://mlsanity.com/paper/2606.30849/) (2026)
- [OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models](https://mlsanity.com/paper/2607.23844/) (2026)
- [RegionCache: Semantic-Aware Region Reuse for Efficient Multi-Turn Image Generation](https://mlsanity.com/paper/2608.29809/) (2026)

## Abstract (arXiv)

Diffusion models have demonstrated impressive generation capabilities, particularly with recent advancements leveraging transformer architectures to improve both visual and artistic quality. However, Diffusion Transformers (DiTs) continue to encounter challenges related to low inference speed, primarily due to the iterative denoising process. To address this issue, we propose BlockDance, a training-free approach that explores feature similarities at adjacent time steps to accelerate DiTs. Unlike previous feature-reuse methods that lack tailored reuse strategies for features at different scales, BlockDance prioritizes the identification of the most structurally similar features, referred to as Structurally Similar Spatio-Temporal (STSS) features. These features are primarily located within the structure-focused blocks of the transformer during the later stages of denoising. BlockDance caches and reuses these highly similar features to mitigate redundant computation, thereby accelerating DiTs while maximizing consistency with the generated results of the original model. Furthermore, considering the diversity of generated content and the varying distributions of redundant features, we introduce BlockDance-Ada, a lightweight decision-making network tailored for instance-specific acceleration. BlockDance-Ada dynamically allocates resources and provides superior content quality. Both BlockDance and BlockDance-Ada have proven effective across various generation tasks and models, achieving accelerations between 25% and 50% while maintaining generation quality.