# FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models

arXiv: https://arxiv.org/abs/2312.03517 · HTML: https://mlsanity.com/paper/2312.03517/

## Key facts

- Cited by 20 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 52 references that are in the map.
- First posted on arXiv 6 Dec 2023.

## Placed in

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

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

- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [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)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [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)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (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)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Universal Guidance for Diffusion Models](https://mlsanity.com/paper/2302.07121/) (2023)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)

## Built on by (most cited first, 20 of 20)

- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality](https://mlsanity.com/paper/2410.19355/) (2024)
- [MagCache: Fast Video Generation with Magnitude-Aware Cache](https://mlsanity.com/paper/2506.09045/) (2025)
- [BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers](https://mlsanity.com/paper/2503.15927/) (2025)
- [Importance-Based Token Merging for Efficient Image and Video Generation](https://mlsanity.com/paper/2411.16720/) (2024)
- [DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers](https://mlsanity.com/paper/2503.22796/) (2025)
- [DVD-Quant: Data-free Video Diffusion Transformers Quantization](https://mlsanity.com/paper/2505.18663/) (2025)
- [Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study](https://mlsanity.com/paper/2411.13588/) (2024)
- [Learnable Sparsity for Vision Generative Models](https://mlsanity.com/paper/2412.02852/) (2024)
- [Relational Feature Caching for Accelerating Diffusion Transformers](https://mlsanity.com/paper/2602.19506/) (2026)
- [Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation](https://mlsanity.com/paper/2604.02979/) (2026)
- [PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models](https://mlsanity.com/paper/2503.19731/) (2025)
- [FlashOmni: A Unified Sparse Attention Engine for Diffusion Transformers](https://mlsanity.com/paper/2509.25401/) (2025)
- [CHAI: CacHe Attention Inference for text2video](https://mlsanity.com/paper/2602.16132/) (2026)
- [Staleness-Centric Optimizations for Parallel Diffusion MoE Inference](https://mlsanity.com/paper/2411.16786/) (2024)
- [Q&C: When Quantization Meets Cache in Efficient Image Generation](https://mlsanity.com/paper/2503.02508/) (2025)
- [cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifold](https://mlsanity.com/paper/2511.12931/) (2025)
- [Importance-Aware OBS Pruning for Diffusion Models](https://mlsanity.com/paper/2607.20048/) (2026)
- [GeoShrink: Accelerating Diffusion Transformers with Two Lines of Code](https://mlsanity.com/paper/2609.33723/) (2026)
- [ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching](https://mlsanity.com/paper/2610.04510/) (2026)

## Abstract (arXiv)

The substantial computational costs of diffusion models, especially due to the repeated denoising steps necessary for high-quality image generation, present a major obstacle to their widespread adoption. While several studies have attempted to address this issue by reducing the number of score function evaluations (NFE) using advanced ODE solvers without fine-tuning, the decreased number of denoising iterations misses the opportunity to update fine details, resulting in noticeable quality degradation. In our work, we introduce an advanced acceleration technique that leverages the temporal redundancy inherent in diffusion models. Reusing feature maps with high temporal similarity opens up a new opportunity to save computation resources without compromising output quality. To realize the practical benefits of this intuition, we conduct an extensive analysis and propose a novel method, FRDiff. FRDiff is designed to harness the advantages of both reduced NFE and feature reuse, achieving a Pareto frontier that balances fidelity and latency trade-offs in various generative tasks.