定制化生成再构想：保真度与可编辑性的协调
Customized Generation Reimagined: Fidelity and Editability Harmonized
AI总结：
针对定制化生成中概念保真度与提示可编辑性难以兼顾的问题，提出 DCI 框架解耦并选择性整合冲突目标，并用 ICO 优化微调，实现二者协调。
摘要：
定制化生成旨在将一个新概念融入预训练的文本到图像模型中，从而在文本提示的引导下，在新颖语境中生成该概念的新图像。然而，定制化生成存在概念保真度与可编辑性之间的内在权衡，即在精确建模概念与忠实地遵循提示之间进行取舍。以往方法只能勉强寻求折中，难以同时实现高概念保真度和理想的提示对齐。本文提出一种“分治再整合”（Divide, Conquer, then Integrate，DCI）框架，在去噪早期进行手术式调整，使微调模型在推理时摆脱保真度—可编辑性权衡。该权衡中的两个相互冲突的组成部分被解耦，并由两个协作分支分别攻克，随后被选择性整合，以在保持高概念保真度的同时实现忠实的提示遵循。为获得更好的微调模型，我们引入图像特定上下文优化（Image-specific Context Optimization，ICO）策略用于模型定制。ICO 用可学习的图像特定上下文取代人工提示模板，提供自适应且精确的微调方向，以提升整体性能。大量实验证明了我们的方法在调和保真度—可编辑性权衡方面的有效性。
英文摘要：
Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts. However, customized generation suffers from an inherent trade-off between concept fidelity and editability, i.e., between precisely modeling the concept and faithfully adhering to the prompts. Previous methods reluctantly seek a compromise and struggle to achieve both high concept fidelity and ideal prompt alignment simultaneously. In this paper, we propose a Divide, Conquer, then Integrate (DCI) framework, which performs a surgical adjustment in the early stage of denoising to liberate the fine-tuned model from the fidelity-editability trade-off at inference. The two conflicting components in the trade-off are decoupled and individually conquered by two collaborative branches, which are then selectively integrated to preserve high concept fidelity while achieving faithful prompt adherence. To obtain a better fine-tuned model, we introduce an Image-specific Context Optimization} (ICO) strategy for model customization. ICO replaces manual prompt templates with learnable image-specific contexts, providing an adaptive and precise fine-tuning direction to promote the overall performance. Extensive experiments demonstrate the effectiveness of our method in reconciling the fidelity-editability trade-off.
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。
