LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories Paper • 2604.15311 • Published 13 days ago • 12
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation Paper • 2604.11804 • Published 16 days ago • 70
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation Paper • 2502.18364 • Published Feb 25, 2025 • 36
VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing Paper • 2502.17258 • Published Feb 24, 2025 • 79