NP-LoRA: Null Space Projection Unifies Subject and Style in LoRA Fusion

TL;DR

NP-LoRA introduces a null-space projection method for LoRA fusion that effectively separates subject and style representations, improving controllable generation quality without retraining.

Contribution

It reformulates LoRA fusion as a null-space projection problem, enabling interference-free combination of subject and style representations.

Findings

Outperforms strong baselines in experiments

Generalizes across pretrained LoRA pairs

Provides continuous control over subject-style trade-off

Abstract

Low-Rank Adaptation (LoRA) fusion enables the composition of learned subject and style representations for controllable generation without retraining. However, existing methods rely on weight-based merging within a shared adaptation space, where independently trained LoRAs interfere and degrade fidelity. We show that this interference is fundamentally geometric: content and style LoRAs occupy overlapping, non-orthogonal low-rank subspaces, making weight-based fusion inherently flawed. Analyzing LoRA internal structure, we find that generative behavior is dominated by a few principal directions that must be preserved during fusion. Based on this insight, we reformulate LoRA fusion as a null-space projection problem and propose Null Space Projection LoRA (NP-LoRA), a projection-based framework that enforces subspace separation by construction. NP-LoRA extracts principal style directions via singular value decomposition (SVD) and projects the subject LoRA into the orthogonal complement of the style subspace, preventing interference. We further introduce a soft projection mechanism that provides continuous control over the trade-off between subject fidelity and style preservation. Experiments show that NP-LoRA consistently outperforms strong baselines and generalizes well across pretrained LoRA pairs without retraining.