提升图像生成中内容与风格的平衡，扩大可调节范围。
Expanding the Content-Style Frontier: a Balanced Subspace Blending Approach for Content-Style LoRA Fusion
- 通过子空间混合与平衡损失，动态调节内容与风格权重。
- 在不同风格强度下均保持更高内容相似度，降低IGD与GD指标。
- 适合需要精细控制风格强度的个性化图像生成场景。
近期文本到图像扩散模型在个性化与风格化生成方面取得显著进展。然而，以往研究仅在单一风格强度下评估内容相似性。实验发现，提高风格强度会导致内容特征严重丢失，从而形成次优的内容-风格边界。为此，我们提出一种新方法，通过内容-风格子空间混合与内容-风格平衡损失，拓展内容-风格边界。该方法在不同风格强度下均显著提升内容相似度，大幅扩展了内容-风格可调范围。大量实验证明，本方法在定性和定量评估中均优于现有技术，实现更优的内容-风格权衡，显著降低逆生成距离（IGD）与生成距离（GD）评分。
原文摘要 · Abstract (English)
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.
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。