EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation

Documenti analoghi

• MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling
  di: Xu, Jiaqi, et al.
  Pubblicazione: (2023)
• VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
  di: Wang, Jiapeng, et al.
  Pubblicazione: (2024)
• UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
  di: Wang, Xiang, et al.
  Pubblicazione: (2025)
• Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
  di: Li, Yunxin, et al.
  Pubblicazione: (2024)
• EvAnimate: Event-conditioned Image-to-Video Generation for Human Animation
  di: Qu, Qiang, et al.
  Pubblicazione: (2025)