Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility

• URL: http://arxiv.org/abs/2505.18521v1
• Date: Sat, 24 May 2025 05:38:35 GMT
• Title: Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
• Authors: Yiheng Li, Feng Liang, Dan Kondratyuk, Masayoshi Tomizuka, Kurt Keutzer, Chenfeng Xu,
• Abstract summary: We show how immiscibility eases denoising and improves efficiency.<n>We propose a family of implementations including K-nearest neighbor (KNN) noise selection and image scaling to reduce miscibility.<n>This work establishes a potentially new direction for future research into high-efficiency diffusion training.
• Score: 62.272571285823595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via linear assignment accelerates training by simplifying denoising. To extend immiscible diffusion beyond the inefficient linear assignment under high batch sizes and high dimensions, we refine this concept to a broader miscibility reduction at any layer and by any implementation. Specifically, we empirically demonstrate the bijective nature of the denoising process with respect to immiscible diffusion, ensuring its preservation of generative diversity. Moreover, we provide thorough analysis and show step-by-step how immiscibility eases denoising and improves efficiency. Extending beyond linear assignment, we propose a family of implementations including K-nearest neighbor (KNN) noise selection and image scaling to reduce miscibility, achieving up to >4x faster training across diverse models and tasks including unconditional/conditional generation, image editing, and robotics planning. Furthermore, our analysis of immiscibility offers a novel perspective on how optimal transport (OT) enhances diffusion training. By identifying trajectory miscibility as a fundamental bottleneck, we believe this work establishes a potentially new direction for future research into high-efficiency diffusion training. The code is available at https://github.com/yhli123/Immiscible-Diffusion.

Related papers

• Enhanced DACER Algorithm with High Diffusion Efficiency [26.268226121403515]
  We introduce a temporal weighting mechanism that enables the model to efficiently eliminate large-scale noise in the early stages.<n>We show that the DACER2 algorithm achieves state-of-the-art performance in most MuJoCo control tasks with only five diffusion steps.
  arXiv  Detail & Related papers  (2025-05-29T13:21:58Z)
• 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)
• Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following [21.81411085058986]
  Reward-gradient guided denoising generates trajectories that maximize both a differentiable reward function and the likelihood under the data distribution captured by a diffusion model. We propose DiffusionES, a method that combines gradient-free optimization with trajectory denoising. We show that DiffusionES achieves state-of-the-art performance on nuPlan, an established closed-loop planning benchmark for autonomous driving.
  arXiv  Detail & Related papers  (2024-02-09T17:18:33Z)
• Manifold Preserving Guided Diffusion [121.97907811212123]
  Conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. We propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework.
  arXiv  Detail & Related papers  (2023-11-28T02:08:06Z)
• Global Structure-Aware Diffusion Process for Low-Light Image Enhancement [64.69154776202694]
  This paper studies a diffusion-based framework to address the low-light image enhancement problem. We advocate for the regularization of its inherent ODE-trajectory. Experimental evaluations reveal that the proposed framework attains distinguished performance in low-light enhancement.
  arXiv  Detail & Related papers  (2023-10-26T17:01:52Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• Diffusion-GAN: Training GANs with Diffusion [135.24433011977874]
  Generative adversarial networks (GANs) are challenging to train stably. We propose Diffusion-GAN, a novel GAN framework that leverages a forward diffusion chain to generate instance noise. We show that Diffusion-GAN can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs.
  arXiv  Detail & Related papers  (2022-06-05T20:45:01Z)

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.