Dual-End Consistency Model

TL;DR

The paper introduces the Dual-End Consistency Model (DE-CM), a novel approach to improve the stability and flexibility of diffusion models by selecting critical sub-trajectories and employing a noise-to-noisy mapping.

Contribution

It proposes DE-CM, which stabilizes training and enhances sampling flexibility by decomposing trajectories and using a new noise-to-noisy mapping for diffusion models.

Findings

Achieves a state-of-the-art FID score of 1.70 in one-step ImageNet generation.

Addresses training instability with flow matching regularization.

Reduces error accumulation through noise-to-noisy mapping.

Abstract

The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While consistency models (CMs) represent a state-of-the-art distillation-based approach for efficient generation, their large-scale application is still limited by two key issues: training instability and inflexible sampling. Existing methods seek to mitigate these problems through architectural adjustments or regularized objectives, yet overlook the critical reliance on trajectory selection. In this work, we first conduct an analysis on these two limitations: training instability originates from loss divergence induced by unstable self-supervised term, whereas sampling inflexibility arises from error accumulation. Based on these insights and analysis, we propose the Dual-End Consistency Model (DE-CM) that selects vital sub-trajectory clusters to achieve stable and effective training. DE-CM decomposes the PF-ODE trajectory and selects three critical sub-trajectories as optimization targets. Specifically, our approach leverages continuous-time CMs objectives to achieve few-step distillation and utilizes flow matching as a boundary regularizer to stabilize the training process. Furthermore, we propose a novel noise-to-noisy (N2N) mapping that can map noise to any point, thereby alleviating the error accumulation in the first step. Extensive experimental results show the effectiveness of our method: it achieves a state-of-the-art FID score of 1.70 in one-step generation on the ImageNet 256x256 dataset, outperforming existing CM-based one-step approaches.