ODE$_t$(ODE$_l$): Shortcutting the Time and Length in Diffusion and Flow Models for Faster Sampling

• URL: http://arxiv.org/abs/2506.21714v2
• Date: Wed, 02 Jul 2025 20:53:10 GMT
• Title: ODE$_t$(ODE$_l$): Shortcutting the Time and Length in Diffusion and Flow Models for Faster Sampling
• Authors: Denis Gudovskiy, Wenzhao Zheng, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer,
• Abstract summary: 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.
• Score: 33.87434194582367
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, continuous normalizing flows (CNFs) and diffusion models (DMs) have been studied using the unified theoretical framework. Although such models can generate high-quality data points from a noise distribution, the sampling demands multiple iterations to solve an ordinary differential equation (ODE) with high computational complexity. Most existing methods focus on reducing the number of time steps during the sampling process to improve efficiency. In this work, we explore a complementary direction in which the quality-complexity tradeoff can be dynamically controlled in terms of time steps and in the length of the neural network. We achieve this by rewiring the blocks in the transformer-based architecture to solve an inner discretized ODE w.r.t. its length. Then, 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 and transformer blocks. Unlike others, our ODE$_t$(ODE$_l$) approach is solver-agnostic in time dimension and decreases both latency and memory usage. 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, and a FID score improvement of up to 3.5 points for high-quality sampling. We release our code and model weights with fully reproducible experiments.

Related papers

• Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models [53.087070073434845]
  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.
  arXiv  Detail & Related papers  (2025-07-20T03:08:06Z)
• TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics [42.99251753481681]
  We introduce a new sampling method that is up to $186%$ faster than the current state of the art solver for comparative FID on ImageNet512.<n>The key to our method resides in using higher-dimensional initial noise, allowing to produce more detailed samples.
  arXiv  Detail & Related papers  (2025-06-26T20:30:27Z)
• Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity [11.71206628091551]
  Diffusion models are costly to train and evaluate, reducing the inference cost for diffusion models remains a major goal. Inspired by the recent empirical success in accelerating diffusion models via the parallel sampling techniqueciteshih2024parallel, we propose to divide the sampling process into $mathcalO(1)$ blocks with parallelizable Picard iterations within each block. Our results shed light on the potential of fast and efficient sampling of high-dimensional data on fast-evolving modern large-memory GPU clusters.
  arXiv  Detail & Related papers  (2024-05-24T23:59:41Z)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Accelerating Diffusion Sampling with Optimized Time Steps [69.21208434350567]
  Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis. Their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps.
  arXiv  Detail & Related papers  (2024-02-27T10:13:30Z)
• 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)
• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)
• IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers [20.784780497613557]
  We propose to model time series purely with continuous processes whose state evolution can be approximated directly by IVPs. This eliminates the need for recurrent computation and enables multiple states to evolve in parallel. Experiments on three real-world datasets show that the proposed method can systematically outperform its predecessors, achieve state-of-the-art results, and have significant advantages in terms of data efficiency.
  arXiv  Detail & Related papers  (2023-05-11T11:53:31Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• Fast Sampling of Diffusion Models via Operator Learning [74.37531458470086]
  We use neural operators, an efficient method to solve the probability flow differential equations, to accelerate the sampling process of diffusion models. Compared to other fast sampling methods that have a sequential nature, we are the first to propose a parallel decoding method. We show our method achieves state-of-the-art FID of 3.78 for CIFAR-10 and 7.83 for ImageNet-64 in the one-model-evaluation setting.
  arXiv  Detail & Related papers  (2022-11-24T07:30:27Z)

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.