# Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free

arXiv: https://arxiv.org/abs/2501.00375 · HTML: https://mlsanity.com/paper/2501.00375/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 14 of its 46 references that are in the map.
- First posted on arXiv 31 Dec 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)
- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 14 of 14)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds](https://mlsanity.com/paper/2306.00980/) (2023)
- [Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://mlsanity.com/paper/2406.01125/) (2024)
- [Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching](https://mlsanity.com/paper/2406.01733/) (2024)
- [Token Pooling in Vision Transformers](https://mlsanity.com/paper/2110.03860/) (2021)
- [Progressive Distillation for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2202.00512/) (2022)
- [MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization](https://mlsanity.com/paper/2405.17873/) (2024)
- [BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion](https://mlsanity.com/paper/2305.15798/) (2023)

## Built on by (most cited first, 30 of 30)

- [From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers](https://mlsanity.com/paper/2503.06923/) (2025)
- [FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning](https://mlsanity.com/paper/2503.23367/) (2025)
- [FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching](https://mlsanity.com/paper/2510.08669/) (2025)
- [Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching](https://mlsanity.com/paper/2509.10312/) (2025)
- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [Accelerating Diffusion Transformer via Gradient-Optimized Cache](https://mlsanity.com/paper/2503.05156/) (2025)
- [SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping](https://mlsanity.com/paper/2506.08908/) (2025)
- [SADA: Stability-guided Adaptive Diffusion Acceleration](https://mlsanity.com/paper/2507.17135/) (2025)
- [Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers](https://mlsanity.com/paper/2510.04188/) (2025)
- [Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas](https://mlsanity.com/paper/2506.03275/) (2025)
- [Universal Properties of Activation Sparsity in Modern Large Language Models](https://mlsanity.com/paper/2509.00454/) (2025)
- [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)
- [Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor](https://mlsanity.com/paper/2508.02240/) (2025)
- [ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor](https://mlsanity.com/paper/2604.01552/) (2026)
- [LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration](https://mlsanity.com/paper/2602.20497/) (2026)
- [Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers](https://mlsanity.com/paper/2601.07396/) (2026)
- [SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration](https://mlsanity.com/paper/2602.04361/) (2026)
- [DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers](https://mlsanity.com/paper/2602.16968/) (2026)
- [Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer](https://mlsanity.com/paper/2511.19778/) (2025)
- [No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching](https://mlsanity.com/paper/2512.12604/) (2025)
- [Shiva-DiT: Residual-Based Differentiable Top-k Selection for Efficient Diffusion Transformers](https://mlsanity.com/paper/2602.05605/) (2026)
- [FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis](https://mlsanity.com/paper/2603.07192/) (2026)
- [Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models](https://mlsanity.com/paper/2604.26365/) (2026)
- [LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching](https://mlsanity.com/paper/2608.17973/) (2026)
- [RemEdit: Efficient Diffusion Editing with Riemannian Geometry](https://mlsanity.com/paper/2601.17927/) (2026)
- [SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer](https://mlsanity.com/paper/2603.07057/) (2026)
- [Dynamic Video Generation: Shaping Video Generation Across Time and Space](https://mlsanity.com/paper/2605.21042/) (2026)
- [Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache](https://mlsanity.com/paper/2609.05981/) (2026)
- [RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance](https://mlsanity.com/paper/2609.36433/) (2026)

## Abstract (arXiv)

Stable Diffusion has achieved remarkable success in the field of text-to-image generation, with its powerful generative capabilities and diverse generation results making a lasting impact. However, its iterative denoising introduces high computational costs and slows generation speed, limiting broader adoption. The community has made numerous efforts to reduce this computational burden, with methods like feature caching attracting attention due to their effectiveness and simplicity. Nonetheless, simply reusing features computed at previous timesteps causes the features across adjacent timesteps to become similar, reducing the dynamics of features over time and ultimately compromising the quality of generated images. In this paper, we introduce a dynamics-aware token pruning (DaTo) approach that addresses the limitations of feature caching. DaTo selectively prunes tokens with lower dynamics, allowing only high-dynamic tokens to participate in self-attention layers, thereby extending feature dynamics across timesteps. DaTo combines feature caching with token pruning in a training-free manner, achieving both temporal and token-wise information reuse. Applied to Stable Diffusion on the ImageNet, our approach delivered a 9× speedup while reducing FID by 0.33, indicating enhanced image quality. On the COCO-30k, we observed a 7× acceleration coupled with a notable FID reduction of 2.17.