AI RESEARCH
Free-Lunch Long Video Generation via Layer-Adaptive O.O.D Correction
arXiv CS.AI
•
ArXi:2603.25209v1 Announce Type: cross Generating long videos using pre-trained video diffusion models, which are typically trained on short clips, presents a significant challenge. Directly applying these models for long-video inference often leads to a notable degradation in visual quality. This paper identifies that this issue primarily stems from two out-of-distribution (O. O. D) problems: frame-level relative position O. D and context-length O. D. To address these challenges, we propose FreeLOC, a novel.