pith. sign in

arxiv: 2205.12524 · v2 · pith:I6KHFLK3new · submitted 2022-05-25 · 💻 cs.CV

Accelerating Diffusion Models via Early Stop of the Diffusion Process

classification 💻 cs.CV
keywords denoisinges-ddpmddpmsdiffusiondistributionprocessaccelerationdiffusing
0
0 comments X
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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

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

  1. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

    cs.LG 2022-09 unverdicted novelty 8.0

    Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.

  2. Muninn: Your Trajectory Diffusion Model But Faster

    cs.RO 2026-05 unverdicted novelty 7.0

    Muninn accelerates diffusion trajectory planners up to 4.6x by spending an uncertainty budget to decide when to cache denoiser outputs, preserving performance and certifying bounded deviation from full computation.

  3. Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access

    cs.LG 2025-05 conditional novelty 7.0

    The paper establishes an O(ε^{-4}) sample complexity bound for score estimation in diffusion models without requiring access to the empirical risk minimizer.

  4. Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

    cs.CV 2023-10 unverdicted novelty 7.0

    Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.

  5. GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes

    cs.LG 2026-05 unverdicted novelty 6.0

    GLIDE combines multi-scale historical graphs with dual-stream encoding and prior-guided leap inference in a dual-branch diffusion denoiser to improve distribution fitting and next-event prediction in STPPs while lower...

  6. Efficient Diffusion Distillation via Embedding Loss

    cs.CV 2026-04 unverdicted novelty 6.0

    Embedding Loss aligns feature distributions via MMD in random network embeddings to boost one-step diffusion distillation, reaching SOTA FID of 1.475 on CIFAR-10 unconditional generation.