Diffusion Models have achieved remarkable results in video synthesis but require iterative denoising steps, leading to substantial computational overhead. Consistency Models have made significant progress in accelerating diffusion models. However, directly applying them to video diffusion models often results in severe degradation of temporal consistency and appearance details. In this paper, by analyzing the training dynamics of Consistency Models, we identify a key conflicting learning dynamics during the distillation process: there is a significant discrepancy in the optimization gradients and loss contributions across different timesteps. This discrepancy prevents the distilled student model from achieving an optimal state, leading to compromised temporal consistency and degraded appearance details. To address this issue, we propose a parameter-efficient \textbf{Dual-Expert Consistency Model~(DCM)}, where a semantic expert focuses on learning semantic layout and motion, while a detail expert specializes in fine detail refinement. Furthermore, we introduce Temporal Coherence Loss to improve motion consistency for the semantic expert and apply GAN and Feature Matching Loss to enhance the synthesis quality of the detailthis http URLapproach achieves state-of-the-art visual quality with significantly reduced sampling steps, demonstrating the effectiveness of expert specialization in video diffusion model distillation. Our code and models are available at \href{this https URL}{this https URL}.
View on arXiv@article{lv2025_2506.03123,
title={ DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation },
author={ Zhengyao Lv and Chenyang Si and Tianlin Pan and Zhaoxi Chen and Kwan-Yee K. Wong and Yu Qiao and Ziwei Liu },
journal={arXiv preprint arXiv:2506.03123},
year={ 2025 }
}