将视频生成转化为网格布局，用旧模型高效完成图像与视频生成。
Grid: Omni Visual Generation
- 把时间序列当网格处理，复用现有图像生成模型能力。
- 推理速度提升67倍，计算资源消耗不足专用模型的千分之一。
- 适合需要兼顾图像和视频生成的开发者快速部署使用。
视觉生成在单图任务上已取得显著进展，但扩展到时序序列仍具挑战。现有方法要么从头构建专用视频模型（计算成本高），要么在图像生成器上附加独立运动模块，均需重新学习时序动态。我们发现现代图像生成模型具备未被充分利用的结构化布局处理能力及隐含的时间理解潜力。基于此，我们提出GRID，将时序序列重构成网格布局，实现对视觉序列的整体处理，同时利用现有模型能力。通过粗到细调度的并行流匹配训练策略，该方法实现最高67倍的推理加速，且计算资源消耗低于专用模型的1/1000。大量实验表明，GRID不仅在文本到视频、3D编辑等时序任务中表现优异，同时保持了强大的图像生成性能，成为高效通用的视觉生成解决方案。
原文摘要 · Abstract (English)
Visual generation has witnessed remarkable progress in single-image tasks, yet extending these capabilities to temporal sequences remains challenging. Current approaches either build specialized video models from scratch with enormous computational costs or add separate motion modules to image generators, both requiring learning temporal dynamics anew. We observe that modern image generation models possess underutilized potential in handling structured layouts with implicit temporal understanding. Building on this insight, we introduce GRID, which reformulates temporal sequences as grid layouts, enabling holistic processing of visual sequences while leveraging existing model capabilities. Through a parallel flow-matching training strategy with coarse-to-fine scheduling, our approach achieves up to 67 faster inference speeds while using <1/1000 of the computational resources compared to specialized models. Extensive experiments demonstrate that GRID not only excels in temporal tasks from Text-to-Video to 3D Editing but also preserves strong performance in image generation, establishing itself as an efficient and versatile omni-solution for visual generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。