扩展内容-风格边界：一种用于内容-风格 LoRA 融合的平衡子空间混合方法
Expanding the Content-Style Frontier: a Balanced Subspace Blending Approach for Content-Style LoRA Fusion
AI总结：
针对文本到图像扩散模型中风格增强导致内容特征丢失的问题，提出内容-风格子空间混合与平衡损失方法，有效拓宽内容-风格边界，在定性和定量评估中均实现更优的内容-风格权衡。
摘要：
文本到图像扩散模型的最新进展显著提升了生成图像的个性化与风格化能力。然而，以往的研究仅在单一风格强度下评估内容相似度。在我们的实验中，我们观察到增加风格强度会导致内容特征显著丢失，从而导致次优的内容-风格边界。为了解决这一问题，我们提出了一种新方法，通过利用内容-风格子空间混合和内容-风格平衡损失来扩展内容-风格边界。我们的方法提高了在不同风格强度下的内容相似度，显著拓宽了内容-风格边界。大量实验表明，我们的方法在定性和定量评估中均优于现有技术，与当前方法相比，以显著更低的 Inverted Generational Distance (IGD) 和 Generational Distance (GD) 分数实现了更优的内容-风格权衡。
英文摘要：
Recent advancements in text-to-image diffusion models have significantly improved the personalization and stylization of generated images. However, previous studies have only assessed content similarity under a single style intensity. In our experiments, we observe that increasing style intensity leads to a significant loss of content features, resulting in a suboptimal content-style frontier. To address this, we propose a novel approach to expand the content-style frontier by leveraging Content-Style Subspace Blending and a Content-Style Balance loss. Our method improves content similarity across varying style intensities, significantly broadening the content-style frontier. Extensive experiments demonstrate that our approach outperforms existing techniques in both qualitative and quantitative evaluations, achieving superior content-style trade-off with significantly lower Inverted Generational Distance (IGD) and Generational Distance (GD) scores compared to current methods.
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。
