CRAFT-LoRA: 通过秩约束适应与无训练融合实现内容-风格个性化
CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion
AI总结：
CRAFT-LoRA通过秩约束适应与无训练融合实现内容-风格个性化，提升生成稳定性与语义控制灵活性。
摘要：
个性化图像生成需要在基于文本和参考示例合成图像时有效平衡内容保真度与风格一致性。低秩适应（LoRA）提供了一种高效的个性化方法，通过结合不同概念的LoRA权重，有可能实现精确控制。然而，现有组合技术面临持续挑战：内容与风格表示之间的纠缠，对控制元素影响的指导不足，以及不稳定的权重融合，通常需要额外训练。我们通过CRAFT-LoRA解决这些限制，互补组件包括：（1）秩约束的主干微调，通过注入低秩投影残差来鼓励学习解耦的内容和风格子空间；（2）一种受提示引导的方法，具有专门分支的专家编码器，通过选择性适配器聚合实现语义扩展和精确控制；（3）一种无训练、时间步依赖的分类器自由引导方案，通过在扩散步骤中战略性地调整噪声预测来增强生成稳定性。我们的方法显著提高了内容-风格解耦程度，使LoRA模块组合的语义控制更加灵活，并在不增加额外重训练开销的情况下实现了高保真生成。
英文摘要：
Personalized image generation requires effectively balancing content fidelity with stylistic consistency when synthesizing images based on text and reference examples. Low-Rank Adaptation (LoRA) offers an efficient personalization approach, with potential for precise control through combining LoRA weights on different concepts. However, existing combination techniques face persistent challenges: entanglement between content and style representations, insufficient guidance for controlling elements' influence, and unstable weight fusion that often require additional training. We address these limitations through CRAFT-LoRA, with complementary components: (1) rank-constrained backbone fine-tuning that injects low-rank projection residuals to encourage learning decoupled content and style subspaces; (2) a prompt-guided approach featuring an expert encoder with specialized branches that enables semantic extension and precise control through selective adapter aggregation; and (3) a training-free, timestep-dependent classifier-free guidance scheme that enhances generation stability by strategically adjusting noise predictions across diffusion steps. Our method significantly improves content-style disentanglement, enables flexible semantic control over LoRA module combinations, and achieves high-fidelity generation without additional retraining overhead.
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。
