How to build a consistency model: Learning flow maps via self-distillation

• URL: http://arxiv.org/abs/2505.18825v2
• Date: Sun, 05 Oct 2025 20:24:27 GMT
• Title: How to build a consistency model: Learning flow maps via self-distillation
• Authors: Nicholas M. Boffi, Michael S. Albergo, Eric Vanden-Eijnden,
• Abstract summary: Flow-based generative models achieve state-of-the-art sample quality, but require the expensive solution of a differential equation at inference time.<n>These models lack a unified description that clearly explains how to learn them efficiently in practice.<n>We present a systematic algorithmic framework for directly learning the flow map associated with a flow or diffusion model.
• Score: 18.299322342860517
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow-based generative models achieve state-of-the-art sample quality, but require the expensive solution of a differential equation at inference time. Flow map models, commonly known as consistency models, encompass many recent efforts to improve inference-time efficiency by learning the solution operator of this differential equation. Yet despite their promise, these models lack a unified description that clearly explains how to learn them efficiently in practice. Here, building on the methodology proposed in Boffi et. al. (2024), we present a systematic algorithmic framework for directly learning the flow map associated with a flow or diffusion model. By exploiting a relationship between the velocity field underlying a continuous-time flow and the instantaneous rate of change of the flow map, we show how to convert any distillation scheme into a direct training algorithm via self-distillation, eliminating the need for pre-trained teachers. We introduce three algorithmic families based on different mathematical characterizations of the flow map: Eulerian, Lagrangian, and Progressive methods, which we show encompass and extend all known distillation and direct training schemes for consistency models. We find that the novel class of Lagrangian methods, which avoid both spatial derivatives and bootstrapping from small steps by design, achieve significantly more stable training and higher performance than more standard Eulerian and Progressive schemes. Our methodology unifies existing training schemes under a single common framework and reveals new design principles for accelerated generative modeling. Associated code is available at https://github.com/nmboffi/flow-maps.

Related papers

• FlowConsist: Make Your Flow Consistent with Real Trajectory [99.22869983378062]
  We argue that current fast-flow training paradigms suffer from two fundamental issues.<n> conditional velocities constructed from randomly paired noise-data samples introduce systematic trajectory drift.<n>We propose FlowConsist, a training framework designed to enforce trajectory consistency in fast flows.
  arXiv  Detail & Related papers  (2026-02-06T03:24:23Z)
• SoFlow: Solution Flow Models for One-Step Generative Modeling [10.054000663262618]
  Flow Models (SoFlow) is a framework for one-step generation from scratch.<n>Flow Matching loss allows our models to provide estimated velocity fields during training.<n>Our models achieve better FID-50K scores than MeanFlow models on the ImageNet 256x256 dataset.
  arXiv  Detail & Related papers  (2025-12-17T18:10:17Z)
• Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling [68.76215229126886]
  We introduce Decoupled MeanFlow, a simple decoding strategy that converts flow models into flow map models without architectural modifications.<n>Our method conditions the final blocks of diffusion transformers on the subsequent timestep, allowing pretrained flow models to be directly repurposed as flow maps.<n>On ImageNet 256x256 and 512x512, our models attain 1-step FID of 2.16 and 2.12, respectively, surpassing prior art by a large margin.
  arXiv  Detail & Related papers  (2025-10-28T14:43:48Z)
• Flows and Diffusions on the Neural Manifold [0.0]
  Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling.<n>We extend these advances to weight space learning by leveraging recent techniques to incorporate structural priors derived from optimization dynamics.
  arXiv  Detail & Related papers  (2025-07-14T02:26:06Z)
• Align Your Flow: Scaling Continuous-Time Flow Map Distillation [63.927438959502226]
  Flow maps connect any two noise levels in a single step and remain effective across all step counts.<n>We extensively validate our flow map models, called Align Your Flow, on challenging image generation benchmarks.<n>We show text-to-image flow map models that outperform all existing non-adversarially trained few-step samplers in text-conditioned synthesis.
  arXiv  Detail & Related papers  (2025-06-17T15:06:07Z)
• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation [51.110607281391154]
  FlowMo is a training-free guidance method for enhancing motion coherence in text-to-video models.<n>It estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling.
  arXiv  Detail & Related papers  (2025-06-01T19:55:33Z)
• Mean Flows for One-step Generative Modeling [64.4997821467102]
  We propose a principled and effective framework for one-step generative modeling.<n>A well-defined identity between average and instantaneous velocities is derived and used to guide neural network training.<n>Our method, termed the MeanFlow model, is self-contained and requires no pre-training, distillation, or curriculum learning.
  arXiv  Detail & Related papers  (2025-05-19T17:59:42Z)
• Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries [10.947094609205765]
  Diffusion-based generative models have become the standard for image generation. ODE-based samplers and flow matching models improve efficiency, in comparison to diffusion models, by reducing sampling steps through learned vector fields.<n>We advance the theory of flow matching models through a comprehensive analysis of sample trajectories, centered on the denoiser that drives ODE dynamics.<n>Our analysis reveals how trajectories evolve from capturing global data features to local structures, providing the geometric characterization of per-sample behavior in flow matching models.
  arXiv  Detail & Related papers  (2024-12-25T01:17:15Z)
• Flow Map Matching [15.520853806024943]
  Flow map matching is an algorithm that learns the two-time flow map of an underlying ordinary differential equation. We show that flow map matching leads to high-quality samples with significantly reduced sampling cost compared to diffusion or interpolant methods.
  arXiv  Detail & Related papers  (2024-06-11T17:41:26Z)
• FlowIE: Efficient Image Enhancement via Rectified Flow [71.6345505427213]
  FlowIE is a flow-based framework that estimates straight-line paths from an elementary distribution to high-quality images. Our contributions are rigorously validated through comprehensive experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-06-01T17:29:29Z)
• 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)
• Training-free Linear Image Inverses via Flows [17.291903204982326]
  We propose a training-free method for solving linear inverse problems by using pretrained flow models. Our approach requires no problem-specific tuning across an extensive suite of noisy linear inverse problems on high-dimensional datasets.
  arXiv  Detail & Related papers  (2023-09-25T22:13:16Z)
• DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling [49.46842536813477]
  We propose a novel data augmentation approach, DistractFlow, for training optical flow estimation models. We combine one of the frames in the pair with a distractor image depicting a similar domain, which allows for inducing visual perturbations congruent with natural objects and scenes. Our approach allows increasing the number of available training pairs significantly without requiring additional annotations.
  arXiv  Detail & Related papers  (2023-03-24T15:42:54Z)
• 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)
• Learned Turbulence Modelling with Differentiable Fluid Solvers [23.535052848123932]
  We train turbulence models based on convolutional neural networks. These models improve under-resolved low resolution solutions to the incompressible Navier-Stokes equations at simulation time.
  arXiv  Detail & Related papers  (2022-02-14T19:03:01Z)
• Generative Flows with Invertible Attentions [135.23766216657745]
  We introduce two types of invertible attention mechanisms for generative flow models. We exploit split-based attention mechanisms to learn the attention weights and input representations on every two splits of flow feature maps. Our method provides invertible attention modules with tractable Jacobian determinants, enabling seamless integration of it at any positions of the flow-based models.
  arXiv  Detail & Related papers  (2021-06-07T20:43:04Z)
• Model-Augmented Actor-Critic: Backpropagating through Paths [81.86992776864729]
  Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator. We show how to make more effective use of the model by exploiting its differentiability.
  arXiv  Detail & Related papers  (2020-05-16T19:18:10Z)

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.