LoL: Longer than Longer, Scaling Video Generation to Hour
This work solves the sink-collapse issue in long-form video generation for AI and multimedia applications, representing an incremental improvement over existing methods.
The paper tackles the problem of error accumulation and loss of long-term coherence in autoregressive long-form video generation, specifically addressing sink-collapse caused by conflicts between Rotary Position Embedding and multi-head attention, and achieves real-time, streaming, infinite-length video generation with demonstrated robustness up to 12 hours.
Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been introduced to mitigate this performance decay, they often induce a critical failure mode we term sink-collapse: the generated content repeatedly reverts to the sink frame, resulting in abrupt scene resets and cyclic motion patterns. Our analysis reveals that sink-collapse originates from an inherent conflict between the periodic structure of Rotary Position Embedding (RoPE) and the multi-head attention mechanisms prevalent in current generative models. To address it, we propose a lightweight, training-free approach that effectively suppresses this behavior by introducing multi-head RoPE jitter that breaks inter-head attention homogenization and mitigates long-horizon collapse. Extensive experiments show that our method successfully alleviates sink-collapse while preserving generation quality. To the best of our knowledge, this work achieves the first demonstration of real-time, streaming, and infinite-length video generation with little quality decay. As an illustration of this robustness, we generate continuous videos up to 12 hours in length, which, to our knowledge, is among the longest publicly demonstrated results in streaming video generation.