cs.CVNov 19, 2026

Frequency-Synchronized Boundary Coupling for Training-Free Multi-Prompt Long Video Generation

Authors: Yipan Xu, Shuyong Gao, Jiyuan Fu, Keliang Yin, Jiayu Chen, Qianyu Guo, Yang Liu, Wenqiang Zhang

Organizations: Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University · Naval Medical Center of PLA, Second Military Medical University · Shanghai Institute of Virology, Shanghai Jiao Tong University · College of Electronic and Information Engineering, Tongji University

Abstract

Text-to-video generation has made remarkable progress with diffusion models and transformer-based video architectures, yet generating coherent long videos from evolving textual descriptions remains challenging. Training long-video models from scratch requires substantial computation and large-scale multi-event data, while training-free multi-prompt generation must activate new prompt semantics without breaking temporal continuity. We identify a frequency-agnostic boundary coupling problem in existing transition strategies: weak coupling causes abrupt changes, flicker, and background jumps, whereas overly strong or coarse coupling may over-preserve source semantics and produce ghosting or duplicated subjects around prompt boundaries. To address this problem, we propose FreqSync, a training-free framework that formulates prompt transitions as frequency-selective boundary coupling. FreqSync combines Frequency-Synchronized Source-Conditioned Attention (FS-SCA) with Residual-Clipped Spectral Stitching (RCSS), enabling adjacent segments to share stable low- and mid-frequency structure and motion cues while keeping high-frequency prompt-specific details target-dominant under explicit residual constraints. Extensive experiments show that FreqSync achieves state-of-the-art transition smoothness and prompt alignment while maintaining strong perceptual video quality, demonstrating its effectiveness for coherent multi-prompt long video generation.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ViDE: Tuning-Free Video Coherence via Temporal Attention Reweighting and Prompt Blending

    Dec 23, 2024Xingyao Li, Hao Zhang, Fengzhuo Zhang +4Video GenerationTemporal Consistency in Video Generation

  2. SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

    Feb 27, 2026Qianxun Xu, Chenxi Song, Yujun Cai +1Video GenerationControllable Video Generation

  3. SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation

    May 10, 2026Shanwen Tan, Hao Li, Jingtao Zhang +4Long Video GenerationMemory-Augmented Video Generation