arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.14280cs.CVcs.AI
收藏

如何在扩散模型中混合概念

How to Blend Concepts in Diffusion Models

University of Milano-Bicocca(米兰比可卡大学)

Lorenzo Olearo, Giorgio Longari, Simone Melzi, Alessandro Raganato, Rafael Peñaloza

AI总结:

本文旨在理解潜在空间操作如何影响底层概念,通过扩散模型探索概念混合任务,尝试多种基于文本的组合策略并进行视觉评估,发现通过空间操作混合概念可行但最佳策略取决于上下文。

摘要:

过去十年里,人们一直致力于使用多维(潜在)空间来表示概念;然而,如何操纵这些概念或用它们进行推理在很大程度上仍不清楚。一些近期方法利用了多个潜在表示及其连接,使这一研究问题变得更加复杂。我们的目标是理解潜在空间中的操作如何影响底层概念。为此,我们通过扩散模型探索了概念混合任务。扩散模型基于文本提示的潜在表示与潜在空间之间的连接,从而实现图像重建和生成。该任务允许我们尝试不同的基于文本的组合策略,并通过视觉分析轻松进行评估。我们的结论是,通过空间操作进行概念混合是可行的,尽管最佳策略取决于混合的上下文。

英文摘要:

For the last decade, there has been a push to use multi-dimensional (latent) spaces to represent concepts; and yet how to manipulate these concepts or reason with them remains largely unclear. Some recent methods exploit multiple latent representations and their connection, making this research question even more entangled. Our goal is to understand how operations in the latent space affect the underlying concepts. To that end, we explore the task of concept blending through diffusion models. Diffusion models are based on a connection between a latent representation of textual prompts and a latent space that enables image reconstruction and generation. This task allows us to try different text-based combination strategies, and evaluate easily through a visual analysis. Our conclusion is that concept blending through space manipulation is possible, although the best strategy depends on the context of the blend.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑