VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation

• URL: http://arxiv.org/abs/2508.20646v1
• Date: Thu, 28 Aug 2025 10:47:50 GMT
• Title: VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
• Authors: Leyang Wang, Mingtian Zhang, Zijing Ou, David Barber,
• Abstract summary: Recently, diffusion distillation methods have compressed thousand-step teacher diffusion models into one-step student generators.<n>Most existing approaches train the student model using a diffusive divergence whose gradient is approximated via the student's score function.<n>We propose VarDiU, a Variational Diffusive Upper Bound that admits an unbiased gradient estimator and can be directly applied to diffusion distillation.
• Score: 16.15071476996734
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, diffusion distillation methods have compressed thousand-step teacher diffusion models into one-step student generators while preserving sample quality. Most existing approaches train the student model using a diffusive divergence whose gradient is approximated via the student's score function, learned through denoising score matching (DSM). Since DSM training is imperfect, the resulting gradient estimate is inevitably biased, leading to sub-optimal performance. In this paper, we propose VarDiU (pronounced /va:rdju:/), a Variational Diffusive Upper Bound that admits an unbiased gradient estimator and can be directly applied to diffusion distillation. Using this objective, we compare our method with Diff-Instruct and demonstrate that it achieves higher generation quality and enables a more efficient and stable training procedure for one-step diffusion distillation.

Related papers

• ReDiF: Reinforced Distillation for Few Step Diffusion [21.686373820429736]
  Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps.<n>We propose a reinforcement learning based distillation framework for diffusion models.
  arXiv  Detail & Related papers  (2025-12-28T06:27:24Z)
• Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis [65.77083310980896]
  We propose Adrial Distribution Matching (ADM) to align latent predictions between real and fake score estimators for score distillation.<n>Our proposed method achieves superior one-step performance on SDXL compared to DMD2 while consuming less GPU time.<n>Additional experiments that apply multi-step ADM distillation on SD3-Medium, SD3.5-Large, and CogVideoX set a new benchmark towards efficient image and video synthesis.
  arXiv  Detail & Related papers  (2025-07-24T16:45:05Z)
• Mean-Shift Distillation for Diffusion Mode Seeking [29.341453176830225]
  Mean-shift distillation provides a proxy for the gradient of the diffusion output distribution.<n>We show that it exhibits superior mode alignment as well as improved convergence in both synthetic and practical setups.
  arXiv  Detail & Related papers  (2025-02-21T22:58:56Z)
• Inference-Time Diffusion Model Distillation [59.350789627086456]
  We introduce Distillation++, a novel inference-time distillation framework.<n>Inspired by recent advances in conditional sampling, our approach recasts student model sampling as a proximal optimization problem.<n>We integrate distillation optimization during reverse sampling, which can be viewed as teacher guidance.
  arXiv  Detail & Related papers  (2024-12-12T02:07:17Z)
• DDIL: Diversity Enhancing Diffusion Distillation With Imitation Learning [57.3467234269487]
  Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes.<n>Progressive distillation or consistency distillation have shown promise by reducing the number of passes.<n>We show that DDIL consistency improves on baseline algorithms of progressive distillation (PD), Latent consistency models (LCM) and Distribution Matching Distillation (DMD2)
  arXiv  Detail & Related papers  (2024-10-15T18:21:47Z)
• Relational Diffusion Distillation for Efficient Image Generation [27.127061578093674]
  Diffusion model's high delay hinders its wide application in edge devices with scarce computing resources.<n>We propose Diffusion Distillation (RDD), a novel distillation method tailored specifically for distilling diffusion models.<n>Our proposed RDD leads to 1.47 FID decrease under 1 sampling step compared to state-of-the-art diffusion distillation methods and achieving 256x speed-up.
  arXiv  Detail & Related papers  (2024-10-10T07:40:51Z)
• Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminator [81.81748032199813]
  Diffusion models have demonstrated excellent performance for real-world image super-resolution (Real-ISR)<n>We propose a new One-Step textbfDiffusion model with a larger-scale textbfDiscriminator for SR.<n>Our discriminator is able to distill noisy features from any time step of diffusion models in the latent space.
  arXiv  Detail & Related papers  (2024-10-05T16:41:36Z)
• Diffusion State-Guided Projected Gradient for Inverse Problems [82.24625224110099]
  We propose Diffusion State-Guided Projected Gradient (DiffStateGrad) for inverse problems.<n>DiffStateGrad projects the measurement gradient onto a subspace that is a low-rank approximation of an intermediate state of the diffusion process.<n>We highlight that DiffStateGrad improves the robustness of diffusion models in terms of the choice of measurement guidance step size and noise.
  arXiv  Detail & Related papers  (2024-10-04T14:26:54Z)
• EM Distillation for One-step Diffusion Models [65.57766773137068]
  We propose a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of quality.<n>We develop a reparametrized sampling scheme and a noise cancellation technique that together stabilizes the distillation process.
  arXiv  Detail & Related papers  (2024-05-27T05:55:22Z)

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.