There have been many attempts to leverage multiple diffusion models for collaborative generation, extending beyond the original domain. A prominent approach involves synchronizing multiple diffusion trajectories by mixing the estimated scores to artificially correlate the generation processes. However, existing methods rely on naive heuristics, such as averaging, without considering task specificity. These approaches do not clarify why such methods work and often fail when a heuristic suitable for one task is blindly applied to others. In this paper, we present a probabilistic framework for analyzing why diffusion synchronization works and reveal where heuristics should be focused - modeling correlations between multiple trajectories and adapting them to each specific task. We further identify optimal correlation models per task, achieving better results than previous approaches that apply a single heuristic across all tasks without justification.

翻译：已有许多尝试利用多个扩散模型进行协作生成，以扩展原始领域。一种主流方法通过混合估计分数来同步多个扩散轨迹，从而人为关联生成过程。然而，现有方法依赖于简单启发式策略（如平均法），未考虑任务特异性。这些方法未能阐明其工作原理，且当适用于某一任务的启发式策略被盲目应用于其他任务时常常失效。本文提出一个概率框架来分析扩散同步的有效性原理，并揭示启发式策略应关注的核心——对多轨迹间相关性的建模及其针对具体任务的适应性调整。我们进一步确定了各任务的最优相关性模型，相较于以往未经论证就在所有任务中应用单一启发式策略的方法，取得了更优的结果。