# Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache arXiv: https://arxiv.org/abs/2602.22654 · HTML: https://mlsanity.com/paper/2602.22654/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. - Builds on 51 of its 60 references that are in the map. - First posted on arXiv 26 Feb 2026. ## Placed in - Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/) ## Builds on (most cited first, 30 of 51) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022) - [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022) - [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022) - [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021) - [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022) - [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023) - [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023) - [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024) - [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022) - [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023) - [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022) - [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) - [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024) - [Mean Flows for One-step Generative Modeling](https://mlsanity.com/paper/2505.13447/) (2025) - [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023) - [Q-Diffusion: Quantizing Diffusion Models](https://mlsanity.com/paper/2302.04304/) (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) - [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://mlsanity.com/paper/2402.13929/) (2024) - [SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds](https://mlsanity.com/paper/2306.00980/) (2023) - [Token Merging for Fast Stable Diffusion](https://mlsanity.com/paper/2303.17604/) (2023) - [Structural Pruning for Diffusion Models](https://mlsanity.com/paper/2305.10924/) (2023) - [Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://mlsanity.com/paper/2406.01125/) (2024) ## Built on by (most cited first, 8 of 8) - [ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE](https://mlsanity.com/paper/2606.06060/) (2026) - [SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers](https://mlsanity.com/paper/2606.29360/) (2026) - [BAG: Budget-Aware Gating for Diffusion Caching](https://mlsanity.com/paper/2608.09231/) (2026) - [GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression](https://mlsanity.com/paper/2608.03517/) (2026) - [ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead](https://mlsanity.com/paper/2609.33202/) (2026) - [The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching](https://mlsanity.com/paper/2609.39343/) (2026) - [CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration](https://mlsanity.com/paper/2610.12530/) (2026) - [Frequency-Step Cache: Separating Synchronization and Repair for Efficient Autoregressive Video Diffusion](https://mlsanity.com/paper/2610.15922/) (2026) ## Abstract (arXiv) Diffusion models have demonstrated remarkable success in image and video generation, yet their practical deployment remains hindered by the substantial computational overhead of multi-step iterative sampling. Among acceleration strategies, caching-based methods offer a training-free and effective solution by reusing or predicting features across timesteps. However, existing approaches rely on fixed or locally adaptive schedules without considering the global structure of the denoising trajectory, often leading to error accumulation and visual artifacts. To overcome this limitation, we propose DPCache, a novel training-free acceleration framework that formulates diffusion sampling acceleration as a global path planning problem. DPCache constructs a Path-Aware Cost Tensor from a small calibration set to quantify the path-dependent error of skipping timesteps conditioned on the preceding key timestep. Leveraging this tensor, DPCache employs dynamic programming to select an optimal sequence of key timesteps that minimizes the total path cost while preserving trajectory fidelity. During inference, the model performs full computations only at these key timesteps, while intermediate outputs are efficiently predicted using cached features. Extensive experiments on DiT, FLUX, and HunyuanVideo demonstrate that DPCache achieves strong acceleration with minimal quality loss, outperforming prior acceleration methods by +0.031 ImageReward at 4.87× speedup and even surpassing the full-step baseline by +0.028 ImageReward at 3.54× speedup on FLUX, validating the effectiveness of our path-aware global scheduling framework. Code is available at https://github.com/argsss/DPCache.