6 papers · 1 filter
Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation
Gordon Chen, Ziqi Huang, Ziwei Liu
Video diffusion models have achieved remarkable progress in generating high-quality videos. However, these models struggle to represent the temporal succession of multiple events i…
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
Haonan Qiu, Shikun Liu, Zijian Zhou +10
High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, making practical infere…
FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
Haonan Qiu, Shiwei Zhang, Yujie Wei +5
Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resou…
FreeInit: Bridging Initialization Gap in Video Diffusion Models
Tianxing Wu, Chenyang Si, Yuming Jiang +2
Though diffusion-based video generation has witnessed rapid progress, the inference results of existing models still exhibit unsatisfactory temporal consistency and unnatural dynam…
FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
Haonan Qiu, Zhaoxi Chen, Zhouxia Wang +3
Diffusion model has demonstrated remarkable capability in video generation, which further sparks interest in introducing trajectory control into the generation process. While exist…
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
Haonan Qiu, Menghan Xia, Yong Zhang +4
With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress. However, existing video ge…