AI RESEARCH

When to Lock Attention: Training-Free KV Control in Video Diffusion

arXiv CS.AI

ArXi:2603.09657v1 Announce Type: cross Maintaining background consistency while enhancing foreground quality remains a core challenge in video editing. Injecting full-image information often leads to background artifacts, whereas rigid background locking severely constrains the model's capacity for foreground generation. To address this issue, we propose KV-Lock, a