无需训练即可融合多个LoRA，通过频域引导实现更精准的图像合成。
MultLFG: Training-free Multi-LoRA composition using Frequency-domain Guidance
- 利用频域引导动态选择不同时间步和频带的LoRA
- 在多概念组合任务中显著提升图像质量和一致性
- 适合需要灵活控制视觉元素组合的研究者
低秩适配（LoRA）因其计算高效性，已成为微调生成模型的主流方法，可在极小开销下实现不同视觉概念的合成。然而，现有方法在不经过训练的情况下难以有效融合多个LoRA适配器，尤其在包含多样视觉元素的复杂组合中表现不佳。本文提出MultLFG，一种无需训练的多LoRA融合框架，通过频域引导实现自适应融合。与统一聚合概念相关LoRA的方法不同，MultLFG采用时间步与频带自适应融合策略，根据内容相关性在特定时间步和频带中选择性激活相关LoRA。该频域敏感引导不仅提升了空间一致性，还实现了对多LoRA组合的精细控制，从而获得更准确、更一致的结果。在ComposLoRA基准上的实验表明，MultLFG在多种风格和概念组合下显著提升了组合保真度与图像质量，优于当前最先进基线。代码将公开。
原文摘要 · Abstract (English)
Low-Rank Adaptation (LoRA) has gained prominence as a computationally efficient method for fine-tuning generative models, enabling distinct visual concept synthesis with minimal overhead. However, current methods struggle to effectively merge multiple LoRA adapters without training, particularly in complex compositions involving diverse visual elements. We introduce MultLFG, a novel framework for training-free multi-LoRA composition that utilizes frequency-domain guidance to achieve adaptive fusion of multiple LoRAs. Unlike existing methods that uniformly aggregate concept-specific LoRAs, MultLFG employs a timestep and frequency subband adaptive fusion strategy, selectively activating relevant LoRAs based on content relevance at specific timesteps and frequency bands. This frequency-sensitive guidance not only improves spatial coherence but also provides finer control over multi-LoRA composition, leading to more accurate and consistent results. Experimental evaluations on the ComposLoRA benchmark reveal that MultLFG substantially enhances compositional fidelity and image quality across various styles and concept sets, outperforming state-of-the-art baselines in multi-concept generation tasks. Code will be released.
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。