REVIEW 6 cited by
Accelerating Diffusion Models via Early Stop of the Diffusion Process
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Denoising Diffusion Probabilistic Models (DDPMs) have achieved impressive performance on various generation tasks. By modeling the reverse process of gradually diffusing the data distribution into a Gaussian distribution, generating a sample in DDPMs can be regarded as iteratively denoising a randomly sampled Gaussian noise. However, in practice DDPMs often need hundreds even thousands of denoising steps to obtain a high-quality sample from the Gaussian noise, leading to extremely low inference efficiency. In this work, we propose a principled acceleration strategy, referred to as Early-Stopped DDPM (ES-DDPM), for DDPMs. The key idea is to stop the diffusion process early where only the few initial diffusing steps are considered and the reverse denoising process starts from a non-Gaussian distribution. By further adopting a powerful pre-trained generative model, such as GAN and VAE, in ES-DDPM, sampling from the target non-Gaussian distribution can be efficiently achieved by diffusing samples obtained from the pre-trained generative model. In this way, the number of required denoising steps is significantly reduced. In the meantime, the sample quality of ES-DDPM also improves substantially, outperforming both the vanilla DDPM and the adopted pre-trained generative model. On extensive experiments across CIFAR-10, CelebA, ImageNet, LSUN-Bedroom and LSUN-Cat, ES-DDPM obtains promising acceleration effect and performance improvement over representative baseline methods. Moreover, ES-DDPM also demonstrates several attractive properties, including being orthogonal to existing acceleration methods, as well as simultaneously enabling both global semantic and local pixel-level control in image generation.
Forward citations
Cited by 6 Pith papers
-
IDLM: Inverse-distilled Diffusion Language Models
IDLM distills pretrained discrete diffusion language models into few-step generators, cutting inference steps by 4–64× with roughly matched GenPPL and entropy.
-
OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
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.
-
A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement
PGUSE combines a predictive speech enhancer with a diffusion model, fusing their outputs and truncating the diffusion start to improve universal speech enhancement with low inference cost.
-
EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models
EC-Diff accelerates edge-cloud diffusion inference with a k-step noise approximation strategy and a two-stage greedy search for the cloud-edge handoff point, claiming about 2x speedup with preserved quality.
-
SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations
Phase-aware sampling cuts Stable Diffusion's compute by roughly 2.4x to 5.7x with only small CLIP-score changes, and the accompanying FPGA accelerator turns this into 2.7x to 6.0x energy savings over an Nvidia V100 GPU.
-
Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
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.
Discussion (0). Continue with ORCID to comment.