PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution 事件

PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution arXiv:2605.25801v1 Announce Type: new Abstract: High-resolution video generation faces a coupled bottleneck of optimization instability and prohibitive computational costs. The massive expansion of the token sequence not only biases optimization toward local textures at the expense of global coherence, leading to structural collapse, but also imposes prohibitive training costs and severe inference la