Warm Starts Accelerate Conditional Diffusion

• URL: http://arxiv.org/abs/2507.09212v2
• Date: Mon, 29 Sep 2025 14:09:38 GMT
• Title: Warm Starts Accelerate Conditional Diffusion
• Authors: Jonas Scholz, Richard E. Turner,
• Abstract summary: Generative models like diffusion and flow-matching create high-fidelity samples by progressively refining noise.<n>We introduce Warm-Start Diffusion (WSD), a method that uses a simple, deterministic model to dramatically accelerate conditional generation.<n>WSD substantially outperforms standard diffusion in the efficient sampling regime.
• Score: 20.22808227772002
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models like diffusion and flow-matching create high-fidelity samples by progressively refining noise. The refinement process is notoriously slow, often requiring hundreds of function evaluations. We introduce Warm-Start Diffusion (WSD), a method that uses a simple, deterministic model to dramatically accelerate conditional generation by providing a better starting point. Instead of starting generation from an uninformed $N(\boldsymbol{0}, I)$ prior, our deterministic warm-start model predicts an informed prior $N(\hat{\boldsymbol{\mu}}_C, \text{diag}(\hat{\boldsymbol{\sigma}}^2_C))$, whose moments are conditioned on the input context $C$. This warm start substantially reduces the distance the generative process must traverse, and therefore the number of diffusion steps required, particularly when the context $C$ is strongly informative. WSD is applicable to any standard diffusion or flow matching algorithm, is orthogonal to and synergistic with other fast sampling techniques like efficient solvers, and is simple to implement. We test WSD in a variety of settings, and find that it substantially outperforms standard diffusion in the efficient sampling regime, generating realistic samples using only 4-6 function evaluations, and saturating performance with 10-12.

Related papers

• Diffusion Tree Sampling: Scalable inference-time alignment of diffusion models [13.312007032203857]
  Adapting a pretrained diffusion model to new objectives at inference time remains an open problem in generative modeling.<n>We introduce a tree-based approach that samples from the reward-aligned target density by propagating terminal rewards back through the diffusion chain.<n>By reusing information from previous generations, we get an anytime algorithm that turns additional compute into steadily better samples.
  arXiv  Detail & Related papers  (2025-06-25T17:59:10Z)
• Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts [64.34482582690927]
  We provide an efficient and principled method for sampling from a sequence of annealed, geometric-averaged, or product distributions derived from pretrained score-based models.<n>We propose Sequential Monte Carlo (SMC) resampling algorithms that leverage inference-time scaling to improve sampling quality.
  arXiv  Detail & Related papers  (2025-03-04T17:46:51Z)
• Distributional Diffusion Models with Scoring Rules [83.38210785728994]
  Diffusion models generate high-quality synthetic data.<n> generating high-quality outputs requires many discretization steps.<n>We propose to accomplish sample generation by learning the posterior em distribution of clean data samples.
  arXiv  Detail & Related papers  (2025-02-04T16:59:03Z)
• 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)
• Truncated Consistency Models [57.50243901368328]
  Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints.<n>We empirically find that this training paradigm limits the one-step generation performance of consistency models.<n>We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
  arXiv  Detail & Related papers  (2024-10-18T22:38:08Z)
• One Step Diffusion via Shortcut Models [109.72495454280627]
  We introduce shortcut models, a family of generative models that use a single network and training phase to produce high-quality samples.<n>Shortcut models condition the network on the current noise level and also on the desired step size, allowing the model to skip ahead in the generation process.<n>Compared to distillation, shortcut models reduce complexity to a single network and training phase and additionally allow varying step budgets at inference time.
  arXiv  Detail & Related papers  (2024-10-16T13:34:40Z)
• Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting [43.951394031702016]
  We introduce TSFlow, a conditional flow matching (CFM) model for time series combining Gaussian processes, optimal transport paths, and data-dependent prior distributions.<n>We show that both conditionally and unconditionally trained models achieve competitive results across multiple forecasting benchmarks.
  arXiv  Detail & Related papers  (2024-10-03T22:12:50Z)
• Accelerating Convergence of Score-Based Diffusion Models, Provably [44.11766377798812]
  Score-based diffusion models often suffer from low sampling speed due to extensive function evaluations needed during the sampling phase. We design novel training-free algorithms to accelerate popular deterministic (i.e., DDIM) and (i.e., DDPM) samplers. Our theory accommodates $ell$-accurate score estimates, and does not require log-concavity or smoothness on the target distribution.
  arXiv  Detail & Related papers  (2024-03-06T17:02:39Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• A Hybrid GNN approach for predicting node data for 3D meshes [0.0]
  Currently, we predict the best parameters using the finite element method. We introduce a hybrid approach that helps in processing and generating new data simulations. New models have outperformed existing PointNet and simple graph neural network models when applied to produce the simulations.
  arXiv  Detail & Related papers  (2023-10-23T08:47:27Z)
• Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner [112.99126045081046]
  A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed.<n>We propose a textbftimestep tuner that helps find a more accurate integral direction for a particular interval at the minimum cost.<n>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)
• Score Mismatching for Generative Modeling [4.413162309652114]
  We propose a new score-based model with one-step sampling. We train a standalone generator to compress all the time steps with the gradient backpropagated from the score network. In order to produce meaningful gradients for the generator, the score network is trained to simultaneously match the real data distribution and mismatch the fake data distribution.
  arXiv  Detail & Related papers  (2023-09-20T03:47:12Z)
• Diffusion Models with Deterministic Normalizing Flow Priors [21.24885597341643]
  We propose DiNof ($textbfDi$ffusion with $textbfNo$rmalizing $textbff$low priors), a technique that makes use of normalizing flows and diffusion models.<n>Experiments on standard image generation datasets demonstrate the advantage of the proposed method over existing approaches.
  arXiv  Detail & Related papers  (2023-09-03T21:26:56Z)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)
• Minimizing Trajectory Curvature of ODE-based Generative Models [45.89620603363946]
  Recent generative models, such as diffusion models, rectified flows, and flow matching, define a generative process as a time reversal of a fixed forward process. We present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.
  arXiv  Detail & Related papers  (2023-01-27T21:52:03Z)
• 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.