# Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching

arXiv: https://arxiv.org/abs/2509.10312 · HTML: https://mlsanity.com/paper/2509.10312/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [Post-training Quantization on Diffusion Models](https://mlsanity.com/paper/2211.15736/) (2022)
- [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023)
- [Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://mlsanity.com/paper/2406.01125/) (2024)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [Real-Time Video Generation with Pyramid Attention Broadcast](https://mlsanity.com/paper/2408.12588/) (2024)
- [FORA: Fast-Forward Caching in Diffusion Transformer Acceleration](https://mlsanity.com/paper/2407.01425/) (2024)
- [From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers](https://mlsanity.com/paper/2503.06923/) (2025)
- [Token Fusion: Bridging the Gap between Token Pruning and Token Merging](https://mlsanity.com/paper/2312.01026/) (2023)
- [DiTFastAttn: Attention Compression for Diffusion Transformer Models](https://mlsanity.com/paper/2406.08552/) (2024)
- [Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent](https://mlsanity.com/paper/2411.02265/) (2024)
- [DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization](https://mlsanity.com/paper/2410.16942/) (2024)
- [Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free](https://mlsanity.com/paper/2501.00375/) (2024)
- [Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching](https://mlsanity.com/paper/2412.18911/) (2024)
- [Ditto: Accelerating Diffusion Model via Temporal Value Similarity](https://mlsanity.com/paper/2501.11211/) (2025)
- [Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model](https://mlsanity.com/paper/2501.00946/) (2025)

## Built on by (most cited first, 19 of 19)

- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing](https://mlsanity.com/paper/2606.26740/) (2026)
- [DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching](https://mlsanity.com/paper/2602.05449/) (2026)
- [Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration](https://mlsanity.com/paper/2603.01623/) (2026)
- [WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching](https://mlsanity.com/paper/2603.06331/) (2026)
- [Motion-Aware Caching for Efficient Autoregressive Video Generation](https://mlsanity.com/paper/2605.01725/) (2026)
- [LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration](https://mlsanity.com/paper/2602.20497/) (2026)
- [ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration](https://mlsanity.com/paper/2606.26769/) (2026)
- [Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications](https://mlsanity.com/paper/2511.08416/) (2025)
- [BeCARE: Budgeted Cache Refresh for Diffusion Transformer Acceleration](https://mlsanity.com/paper/2605.27075/) (2026)
- [SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers](https://mlsanity.com/paper/2606.29360/) (2026)
- [OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference](https://mlsanity.com/paper/2607.29398/) (2026)
- [Disagree to Accelerate: Closing the Loop on Diffusion Feature Forecasts](https://mlsanity.com/paper/2608.01740/) (2026)
- [LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching](https://mlsanity.com/paper/2608.17973/) (2026)
- [SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation](https://mlsanity.com/paper/2606.30849/) (2026)
- [Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2608.21450/) (2026)
- [Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache](https://mlsanity.com/paper/2609.05981/) (2026)
- [SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching](https://mlsanity.com/paper/2610.02660/) (2026)
- [Tikhonov-Stabilized Bezier Representation Forecasting for Training-free Diffusion Acceleration](https://mlsanity.com/paper/2610.16448/) (2026)

## Abstract (arXiv)

Diffusion transformers have gained significant attention in recent years for their ability to generate high-quality images and videos, yet still suffer from a huge computational cost due to their iterative denoising process. Recently, feature caching has been introduced to accelerate diffusion transformers by caching the feature computation in previous timesteps and reusing it in the following timesteps, which leverage the temporal similarity of diffusion models while ignoring the similarity in the spatial dimension. In this paper, we introduce Cluster-Driven Feature Caching (ClusCa) as an orthogonal and complementary perspective for previous feature caching. Specifically, ClusCa performs spatial clustering on tokens in each timestep, computes only one token in each cluster and propagates their information to all the other tokens, which is able to reduce the number of tokens by over 90%. Extensive experiments on DiT, FLUX and HunyuanVideo demonstrate its effectiveness in both text-to-image and text-to-video generation. Besides, it can be directly applied to any diffusion transformer without requirements for training. For instance, ClusCa achieves 4.96x acceleration on FLUX with an ImageReward of 99.49%, surpassing the original model by 0.51%. The code is available at https://github.com/Shenyi-Z/Cache4Diffusion.