AI Paper Atlas

Research map / Video / Video generation

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation

Zhengyao Lv, Chenyang Si, Tianlin Pan, Zhaoxi Chen, Kwan-Yee K. Wong, Yu Qiao, Ziwei Liu

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add optimization decoupling into semantic and detail experts (ablation)consistency distillation of HunyuanVideo · VBench ablation (HunyuanVideo, 4 steps)VBench total: 80.30 -> 83.08Improved
make dual expert parameter-efficient (time embeddings + LoRA) instead of two full experts (ablation)DCM · VBench ablation (HunyuanVideo, 4 steps)VBench total: 83.08 -> 83.03No clear effect
add Temporal Coherence loss to semantic expert (ablation)DCM (OD+PE) · VBench ablation (HunyuanVideo, 4 steps)VBench total: 83.03 -> 83.42Improved
add Temporal Coherence loss when GAN loss already used (ablation)DCM (OD+PE+GF) · VBench ablation (HunyuanVideo, 4 steps)VBench total: 83.71 -> 83.80Improved
add GAN and Feature Matching loss to detail expert (ablation)DCM (OD+PE) · VBench ablation (HunyuanVideo, 4 steps)VBench total: 83.03 -> 83.71Improved
add GAN and Feature Matching loss when TC already used (ablation)DCM (OD+PE+TC) · VBench ablation (HunyuanVideo, 4 steps)VBench total: 83.42 -> 83.80Improved
add full DCM (all components) over vanilla consistency distillation (ablation)HunyuanVideo 4 steps · VBench ablation (HunyuanVideo, 4 steps)VBench semantic: 78.36 -> 78.62Improved
move switch step kappa away from 37 (28, 35, 39, 46) (ablation)DCM · HunyuanVideo VBenchvideo qualityHurt
use DCM instead of LCM at 4 stepsHunyuanVideo · VBench (4 steps)VBench total: 80.33 -> 83.83Improved
use DCM instead of PCM at 4 stepsHunyuanVideo · VBench (4 steps)VBench total: 80.93 -> 83.83Improved
use DCM instead of PCM at 8 stepsCogVideoX-2B · VBench (8 steps)VBench total: 79.70 -> 80.26Improved
distill 50-step HunyuanVideo to 4 steps with DCMHunyuanVideo · VBenchVBench total / latency: 83.87 -> 83.83; latency 1504.5 -> 121.52No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy