Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models

• URL: http://arxiv.org/abs/2507.14797v1
• Date: Sun, 20 Jul 2025 03:08:06 GMT
• Title: Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models
• Authors: Beier Zhu, Ruoyu Wang, Tong Zhao, Hanwang Zhang, Chi Zhang,
• Abstract summary: Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face image quality degradation under a low-latency budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as ours), a novel ODE solver that mitigates truncation errors by incorporating multiple parallel gradient evaluations in each ODE step.
• Score: 53.087070073434845
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature. Existing solver-based acceleration methods often face image quality degradation under a low-latency budget. In this paper, we propose the Ensemble Parallel Direction solver (dubbed as \ours), a novel ODE solver that mitigates truncation errors by incorporating multiple parallel gradient evaluations in each ODE step. Importantly, since the additional gradient computations are independent, they can be fully parallelized, preserving low-latency sampling. Our method optimizes a small set of learnable parameters in a distillation fashion, ensuring minimal training overhead. In addition, our method can serve as a plugin to improve existing ODE samplers. Extensive experiments on various image synthesis benchmarks demonstrate the effectiveness of our \ours~in achieving high-quality and low-latency sampling. For example, at the same latency level of 5 NFE, EPD achieves an FID of 4.47 on CIFAR-10, 7.97 on FFHQ, 8.17 on ImageNet, and 8.26 on LSUN Bedroom, surpassing existing learning-based solvers by a significant margin. Codes are available in https://github.com/BeierZhu/EPD.

Related papers

• ODE$_t$(ODE$_l$): Shortcutting the Time and Length in Diffusion and Flow Models for Faster Sampling [33.87434194582367]
  In this work, we explore a complementary direction in which the quality-complexity tradeoff can be dynamically controlled.<n>We employ time- and length-wise consistency terms during flow matching training, and as a result, the sampling can be performed with an arbitrary number of time steps.<n>Compared to the previous state of the art, image generation experiments on CelebA-HQ and ImageNet show a latency reduction of up to 3$times$ in the most efficient sampling mode.
  arXiv  Detail & Related papers  (2025-06-26T18:59:59Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations [53.180374639531145]
  Self-Refining Diffusion Samplers (SRDS) retain sample quality and can improve latency at the cost of additional parallel compute.<n>We take inspiration from the Parareal algorithm, a popular numerical method for parallel-in-time integration of differential equations.
  arXiv  Detail & Related papers  (2024-12-11T11:08:09Z)
• PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores [4.595421654683656]
  Diffusion Probabilistic Models (DPMs) have shown remarkable potential in image generation.<n>Most existing solutions accelerate the sampling process by proposing fast ODE solvers.<n>We propose PFDiff, a novel training-free and timestep-skipping strategy, which enables existing fast ODE solvers to operate with fewer NFE.
  arXiv  Detail & Related papers  (2024-08-16T16:12:44Z)
• Accelerating Parallel Sampling of Diffusion Models [25.347710690711562]
  We propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms by a factor of 4$sim$14 times.
  arXiv  Detail & Related papers  (2024-02-15T14:27:58Z)
• Fast ODE-based Sampling for Diffusion Models in Around 5 Steps [17.500594480727617]
  We propose Approximate MEan-Direction solver (AMED-r) that eliminates truncation errors by directly learning the mean direction for fast sampling. Our method can be easily used as a plugin to further improve existing ODE-based samplers.
  arXiv  Detail & Related papers  (2023-11-30T13:07:19Z)
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step [119.18813219518042]
  Super-resolution (SR) methods based on diffusion models exhibit promising results. But their practical application is hindered by the substantial number of required inference steps. We propose a simple yet effective method for achieving single-step SR generation, named SinSR.
  arXiv  Detail & Related papers  (2023-11-23T16:21:29Z)
• Towards More Accurate Diffusion Model Acceleration with A Timestep Aligner [84.97253871387028]
  A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. We propose a timestep aligner that helps find a more accurate integral direction for a particular interval at the minimum cost. Experiments show that our plug-in design can be trained efficiently and boost the inference performance of various state-of-the-art acceleration methods.
  arXiv  Detail & Related papers  (2023-10-14T02:19:07Z)
• Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference [60.32804641276217]
  We propose Latent Consistency Models (LCMs), enabling swift inference with minimal steps on any pre-trained LDMs. A high-quality 768 x 768 24-step LCM takes only 32 A100 GPU hours for training. We also introduce Latent Consistency Fine-tuning (LCF), a novel method that is tailored for fine-tuning LCMs on customized image datasets.
  arXiv  Detail & Related papers  (2023-10-06T17:11:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.