Rectified Diffusion Guidance for Conditional Generation

• URL: http://arxiv.org/abs/2410.18737v2
• Date: Wed, 01 Oct 2025 08:09:18 GMT
• Title: Rectified Diffusion Guidance for Conditional Generation
• Authors: Mengfei Xia, Nan Xue, Yujun Shen, Ran Yi, Tieliang Gong, Yong-Jin Liu,
• Abstract summary: We revisit the theory behind CFG and rigorously confirm that the improper combination coefficients (textiti.e.) brings about expectation shift the generative distribution.<n>We show that our approach enjoys a textbftextitform solution given the strength.<n> Empirical evidence on real-world data demonstrate the compatibility of our design with existing state-of-the-art diffusion models.
• Score: 94.83538269086613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion model sampling. Theoretically, however, denoising with CFG \textit{cannot} be expressed as a reciprocal diffusion process, which may consequently leave some hidden risks during use. In this work, we revisit the theory behind CFG and rigorously confirm that the improper configuration of the combination coefficients (\textit{i.e.}, the widely used summing-to-one version) brings about expectation shift of the generative distribution. To rectify this issue, we propose ReCFG with a relaxation on the guidance coefficients such that denoising with \method strictly aligns with the diffusion theory. We further show that our approach enjoys a \textbf{\textit{closed-form}} solution given the guidance strength. That way, the rectified coefficients can be readily pre-computed via traversing the observed data, leaving the sampling speed barely affected. Empirical evidence on real-world data demonstrate the compatibility of our post-hoc design with existing state-of-the-art diffusion models, including both class-conditioned ones (\textit{e.g.}, EDM2 on ImageNet) and text-conditioned ones (\textit{e.g.}, SD3 on CC12M), without any retraining. Code is available at \href{https://github.com/thuxmf/recfg}{https://github.com/thuxmf/recfg}.

Related papers

• Diffusion Models: A Mathematical Introduction [3.8673630752805437]
  We present a self-contained derivation of diffusion-based generative models.<n>We construct denoising diffusion probabilistic models from first principles.<n>Readers can both follow the theory and implement the corresponding algorithms in practice.
  arXiv  Detail & Related papers  (2025-11-13T16:20:52Z)
• Score Distillation of Flow Matching Models [67.86066177182046]
  We extend Score identity Distillation (SiD) to pretrained text-to-image flow-matching models.<n>SiD works out of the box across these models, in both data-free and data-aided settings.<n>This provides the first systematic evidence that score distillation applies broadly to text-to-image flow matching models.
  arXiv  Detail & Related papers  (2025-09-29T17:45:48Z)
• Navigating Sparse Molecular Data with Stein Diffusion Guidance [48.21071466968102]
  optimal control (SOC) has emerged as a principled framework for fine-tuning diffusion models.<n>A class of training-free approaches has been developed that guides diffusion models using off-the-shelf classifiers on predicted clean samples.<n>We propose a novel training-free guidance framework based on a surrogate optimal control objective.
  arXiv  Detail & Related papers  (2025-07-07T21:14:27Z)
• Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance [19.83064246586143]
  CFG is a technique for improving conditional diffusion models by linearly combining the outputs of conditional and unconditional denoisers.<n>While CFG enhances visual quality and improves alignment with prompts, it often reduces sample diversity.<n>We propose a Gibbs-like sampling procedure to draw samples from the desired tilted distribution.
  arXiv  Detail & Related papers  (2025-05-27T12:27:33Z)
• Generalized Interpolating Discrete Diffusion [65.74168524007484]
  Masked diffusion is a popular choice due to its simplicity and effectiveness. We derive the theoretical backbone of a family of general interpolating discrete diffusion processes. Exploiting GIDD's flexibility, we explore a hybrid approach combining masking and uniform noise.
  arXiv  Detail & Related papers  (2025-03-06T14:30:55Z)
• The Superposition of Diffusion Models Using the Itô Density Estimator [46.03684204456143]
  We show that SuperDiff is scalable to large pre-trained diffusion models. We also show that SuperDiff is efficient during inference time, and mimics traditional composition operators. We empirically demonstrate the utility of using SuperDiff for generating more diverse images on CIFAR-10.
  arXiv  Detail & Related papers  (2024-12-23T18:18:07Z)
• Dual Conditional Diffusion Models for Sequential Recommendation [47.65610320825351]
  We propose a discrete-to-continuous sequential recommendation diffusion framework. Our framework introduces a complete Markov chain to model the transition from the reversed target item representation to the discrete item index. Building on this framework, we present the Dual Conditional Diffusion Transformer (DCDT) that incorporates the implicit conditional and the explicit conditional for diffusion-based SR.
  arXiv  Detail & Related papers  (2024-10-29T11:51:06Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional general score-mismatched diffusion samplers. We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions. This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving [83.56510119503267]
  This paper presents a novel method for addressing linear inverse problems by leveraging generative models based on discrete diffusion as priors.<n>We employ a star-shaped noise process to mitigate the drawbacks of traditional discrete diffusion models with absorbing states.
  arXiv  Detail & Related papers  (2024-10-09T06:18:25Z)
• Classifier-Free Guidance is a Predictor-Corrector [8.970133799609041]
  CFG is the dominant method of conditional sampling for text-to-image diffusion models. We disprove common misconceptions by showing that CFG interacts differently with DDPM and DDIM. We prove that in the SDE limit, CFG is actually equivalent to combining a DDIM predictor for the conditional distribution together with a Langevin dynamics corrector for a gamma-powered distribution.
  arXiv  Detail & Related papers  (2024-08-16T20:00:55Z)
• Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints [66.63250537475973]
  This paper introduces a diffusion-driven semantic communication framework with advanced VAE-based compression for bandwidth-constrained generative model.<n>Our experimental results demonstrate significant improvements in pixel-level metrics like peak signal to noise ratio (PSNR) and semantic metrics like learned perceptual image patch similarity (LPIPS)
  arXiv  Detail & Related papers  (2024-07-26T02:34:25Z)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• DiffEnc: Variational Diffusion with a Learned Encoder [14.045374947755922]
  We introduce a data- and depth-dependent mean function in the diffusion process, which leads to a modified diffusion loss. Our proposed framework, DiffEnc, achieves a statistically significant improvement in likelihood on CIFAR-10.
  arXiv  Detail & Related papers  (2023-10-30T17:54:36Z)
• Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems [64.29491112653905]
  We propose a novel and efficient diffusion sampling strategy that synergistically combines the diffusion sampling and Krylov subspace methods. Specifically, we prove that if tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG with the denoised data ensures the data consistency update to remain in the tangent space. Our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
  arXiv  Detail & Related papers  (2023-03-10T07:42:49Z)
• Generative Modeling with Flow-Guided Density Ratio Learning [12.192867460641835]
  Flow-Guided Density Ratio Learning (FDRL) is a simple and scalable approach to generative modeling. We show that FDRL can generate images of dimensions as high as $128times128$, as well as outperform existing gradient flow baselines on quantitative benchmarks.
  arXiv  Detail & Related papers  (2023-03-07T07:55:52Z)
• 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)
• Subspace Diffusion Generative Models [4.310834990284412]
  Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We restrict the diffusion via projections onto subspaces as the data distribution evolves toward noise. Our framework is fully compatible with continuous-time diffusion and retains its flexible capabilities.
  arXiv  Detail & Related papers  (2022-05-03T13:43:47Z)
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times [51.61278695776151]
  Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively. Recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks.
  arXiv  Detail & Related papers  (2021-01-11T19:43:12Z)

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.