Pith. sign in

REVIEW 9 cited by

DeepCache: Accelerating Diffusion Models for Free

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.00858 v2 pith:ODEU2THF submitted 2023-12-01 cs.CV cs.AI

Xinyin Ma , Gongfan Fang , Xinchao Wang This is my paper · ORCID
classification cs.CVcs.AI
keywords deepcachediffusionmodelsdenoisingfeaturesmethodsmodelretraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs, primarily attributed to the sequential denoising process and cumbersome model size. Traditional methods for compressing diffusion models typically involve extensive retraining, presenting cost and feasibility challenges. In this paper, we introduce DeepCache, a novel training-free paradigm that accelerates diffusion models from the perspective of model architecture. DeepCache capitalizes on the inherent temporal redundancy observed in the sequential denoising steps of diffusion models, which caches and retrieves features across adjacent denoising stages, thereby curtailing redundant computations. Utilizing the property of the U-Net, we reuse the high-level features while updating the low-level features in a very cheap way. This innovative strategy, in turn, enables a speedup factor of 2.3$\times$ for Stable Diffusion v1.5 with only a 0.05 decline in CLIP Score, and 4.1$\times$ for LDM-4-G with a slight decrease of 0.22 in FID on ImageNet. Our experiments also demonstrate DeepCache's superiority over existing pruning and distillation methods that necessitate retraining and its compatibility with current sampling techniques. Furthermore, we find that under the same throughput, DeepCache effectively achieves comparable or even marginally improved results with DDIM or PLMS. The code is available at https://github.com/horseee/DeepCache

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers

    cs.CV 2025-12 conditional novelty 6.0 of 10

    OUSAC uses evolutionary search to skip most classifier-free-guidance passes and adaptive low-rank caching to recover quality, cutting diffusion transformer compute by about 50–60% with equal or better FID.

  2. OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    A training-free cache-reuse scheme that spreads computation across the full diffusion trajectory and subtracts estimated noise, accelerating DiT sampling with claimed competitive quality.

  3. Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A training-free predictor-corrector method that accelerates Diffusion Transformers by solving a feature-ODE, achieving large compute reductions with modest quality loss.

  4. VMoBA: Mixture-of-Block Attention for Video Diffusion Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    VMoBA is a sparse attention mechanism for video diffusion models that combines cyclic 1D-2D-3D block partitioning with global and threshold-based block selection to reduce training FLOPs while keeping generation quality.

  5. Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Fine-tuning a pretrained diffusion model with a GAN objective and most weights frozen yields a one-step generator that matches or beats prior distillation methods on several datasets.

  6. dKV-Cache: The Cache for Diffusion Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    dKV-Cache reuses cached key and value states of decoded tokens during diffusion LM denoising, delivering 2-10x faster inference with near-lossless quality on several benchmarks.

  7. OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Training-free hierarchical feature caching across token, frame, block, and layer axes cuts diffusion inference latency up to 35% while preserving quality better than averaging-based token merging.

  8. Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

    cs.LG 2025-05 conditional novelty 5.0 of 10

    ScaleKV cuts KV cache memory for Visual Autoregressive text-to-image generation to 10% by classifying layers as drafters or refiners per scale and pruning low-attention tokens while keeping benchmark scores nearly unchanged.

  9. Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation

    cs.LG 2025-10 conditional novelty 4.0 of 10

    Predictive feature caching, borrowed from image diffusion, speeds up molecular flow-matching generation by 2-3x at near-matched quality by forecasting hidden features instead of recomputing them.

Pith tools