通过内禀维数透镜的稳定扩散的表示流形探索
Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
摘要：
摘要已成为一种重要的机制，通过它用户可以更有效地与多种风格的基础模型进行交互。事实上，过去几年已经表明，精心打磨的提示有时可以在这些模型中释放紧急功能。虽然已经有大量的经验性的探索，在社区内的提示，相对较少的作品研究了在数学水平上的提示。在这项工作中，我们的目标是采取的第一步，了解基本的几何属性诱导的提示稳定扩散，专注于模型内的内部表示的内在维度。我们发现，提示的选择有很大的影响，在这两个层次的模型，我们探讨的内在维度的代表性，但这种影响的性质取决于层被认为是。例如，在模型的某些瓶颈层中，表示的内在维度与提示困惑（使用代理模型测量）相关，而这种相关性在潜在层中并不明显。我们的证据表明，内在维度可能是一个有用的工具，为未来的研究不同的提示对文本到图像模型的影响。
英文摘要：
Prompting has become an important mechanism by which users can more effectively interact with many flavors of foundation model. Indeed, the last several years have shown that well-honed prompts can sometimes unlock emergent capabilities within such models. While there has been a substantial amount of empirical exploration of prompting within the community, relatively few works have studied prompting at a mathematical level. In this work we aim to take a first step towards understanding basic geometric properties induced by prompts in Stable Diffusion, focusing on the intrinsic dimension of internal representations within the model. We find that choice of prompt has a substantial impact on the intrinsic dimension of representations at both layers of the model which we explored, but that the nature of this impact depends on the layer being considered. For example, in certain bottleneck layers of the model, intrinsic dimension of representations is correlated with prompt perplexity (measured using a surrogate model), while this correlation is not apparent in the latent layers. Our evidence suggests that intrinsic dimension could be a useful tool for future studies of the impact of different prompts on text-to-image models.
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。
