7 papers
DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data
Wonjoon Jin, Jiyun Won, Janghyeok Han +4
Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A c…
ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
Zihan Yang, Shuyuan Tu, Licheng Zhang +3
Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivati…
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
Shuyuan Tu, Yueming Pan, Yinming Huang +6
Current diffusion-based acceleration methods for long-portrait animation struggle to ensure identity (ID) consistency. This paper presents FlashPortrait, an end-to-end video diffus…
MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
Quanhao Li, Zhen Xing, Rui Wang +3
Recent advances in video generation have led to remarkable improvements in visual quality and temporal coherence. Upon this, trajectory-controllable video generation has emerged to…
Downscaling Extreme Precipitation with Wasserstein Regularized Diffusion
Yuhao Liu, James Doss-Gollin, Qiushi Dai +2
Understanding the risks posed by extreme rainfall events requires analysis of precipitation fields with high resolution (to assess localized hazards) and extensive historical cover…
StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation
Shuyuan Tu, Yueming Pan, Yinming Huang +6
Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper present…