让扩散模型的潜在空间可操控，实现创意艺术中的概念融合与动态生成。
Latent Diffusion : Multi-Dimension Stable Diffusion Latent Space Explorer
- 在扩散过程中嵌入可定制的潜在空间操作，支持对语义和空间特征的直接编辑。
- 通过两件艺术作品验证框架效果，实现概念混搭与动态运动生成。
- 揭示潜在空间中存在语义区与无意义区，为理解扩散模型结构提供新视角。
潜在空间是生成式AI的核心概念，通过向量操作可实现强大的创意探索。然而，如Stable Diffusion这类扩散模型缺乏像GAN那样直观的潜在向量控制能力，限制了其在艺术表达中的灵活性。本文提出 extit{Latent Diffusion}，一个将可定制潜在空间操作融入扩散过程的框架。通过直接操纵概念与空间表征，该方法拓展了生成艺术的创作可能性。我们以两件作品 extit{Infinitepedia}和 extit{Latent Motion}展示其应用，分别体现概念融合与动态运动生成。研究发现潜在空间中存在具有语义的区域与无意义区域，揭示了扩散模型潜在空间的几何特性，为后续探索提供了基础。
原文摘要 · Abstract (English)
Latent space is one of the key concepts in generative AI, offering powerful means for creative exploration through vector manipulation. However, diffusion models like Stable Diffusion lack the intuitive latent vector control found in GANs, limiting their flexibility for artistic expression. This paper introduces \workname, a framework for integrating customizable latent space operations into the diffusion process. By enabling direct manipulation of conceptual and spatial representations, this approach expands creative possibilities in generative art. We demonstrate the potential of this framework through two artworks, \textit{Infinitepedia} and \textit{Latent Motion}, highlighting its use in conceptual blending and dynamic motion generation. Our findings reveal latent space structures with semantic and meaningless regions, offering insights into the geometry of diffusion models and paving the way for further explorations of latent space.
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。