On the Design of One-step Diffusion via Shortcutting Flow Paths

• URL: http://arxiv.org/abs/2512.11831v2
• Date: Tue, 16 Dec 2025 04:05:55 GMT
• Title: On the Design of One-step Diffusion via Shortcutting Flow Paths
• Authors: Haitao Lin, Peiyan Hu, Minsi Ren, Zhifeng Gao, Zhi-Ming Ma, Guolin ke, Tailin Wu, Stan Z. Li,
• Abstract summary: We propose a common design framework for representative shortcut models.<n>With our proposed improvements, the resulting one-step model achieves a new state-of-the-art FID50k of 2.85 on ImageNet-256x256.<n>Remarkably, the model requires no pre-training, distillation, or curriculum learning.
• Score: 78.72016001375935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in few-step diffusion models have demonstrated their efficiency and effectiveness by shortcutting the probabilistic paths of diffusion models, especially in training one-step diffusion models from scratch (\emph{a.k.a.} shortcut models). However, their theoretical derivation and practical implementation are often closely coupled, which obscures the design space. To address this, we propose a common design framework for representative shortcut models. This framework provides theoretical justification for their validity and disentangles concrete component-level choices, thereby enabling systematic identification of improvements. With our proposed improvements, the resulting one-step model achieves a new state-of-the-art FID50k of 2.85 on ImageNet-256x256 under the classifier-free guidance setting with one step generation, and further reaches FID50k of 2.52 with 2x training steps. Remarkably, the model requires no pre-training, distillation, or curriculum learning. We believe our work lowers the barrier to component-level innovation in shortcut models and facilitates principled exploration of their design space.

Related papers

• Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe [51.26601054313749]
  Recent efforts on Diffusion MoE models have primarily focused on developing more sophisticated routing mechanisms.<n>Inspired by the MoE design paradigms established in large language models (LLMs), we identify a set of crucial architectural factors for building effective Diffusion MoE models.<n>We present novel architectures that can be efficiently applied to both latent and pixel-space diffusion frameworks.
  arXiv  Detail & Related papers  (2025-12-01T03:52:31Z)
• 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)
• Improved Training Technique for Shortcut Models [12.527716901034694]
  Shortcut models are a promising, non-adversarial paradigm for generative modeling.<n>Shortcut models support one-step, few-step, and multi-step sampling from a single trained network.<n>This paper tackles the five core issues that held shortcut models back.
  arXiv  Detail & Related papers  (2025-10-24T08:35:04Z)
• Learning Diffusion Models with Flexible Representation Guidance [49.26046407886349]
  We present a systematic framework for incorporating representation guidance into diffusion models.<n>We introduce two new strategies for enhancing representation alignment in diffusion models.<n>Experiments across image, protein sequence, and molecule generation tasks demonstrate superior performance as well as accelerated training.
  arXiv  Detail & Related papers  (2025-07-11T19:29:02Z)
• Flow-Anchored Consistency Models [32.04797599813587]
  Continuous-time Consistency Models (CMs) promise efficient few-step generation but face challenges with training instability.<n>We argue this instability stems from a fundamental conflict: by training a network to learn only a shortcut across a probability flow, the model loses its grasp on the instantaneous velocity field that defines the flow.<n>We introduce the Flow-Anchored Consistency Model (FACM), a simple but effective training strategy that uses a Flow Matching task as an anchor for the primary CM shortcut objective.
  arXiv  Detail & Related papers  (2025-07-04T17:56:51Z)
• 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)
• 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)
• TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training [25.744324109042385]
  Diffusion models typically suffer from sample inefficiency and high training costs.<n>We show that TREAD reduces computational cost and simultaneously boosts model performance.<n>We achieve a competitive FID of 2.09 in a guided and 3.93 in an unguided setting.
  arXiv  Detail & Related papers  (2025-01-08T18:38:25Z)
• SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow [24.213303324584906]
  We develop small, efficient one-step diffusion models based on the powerful rectified flow framework. We train a one-step diffusion model with an FID of 5.02 and 15.7M parameters, outperforming the previous state-of-the-art one-step diffusion model.
  arXiv  Detail & Related papers  (2024-07-17T16:38:45Z)

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.