REVIEW 4 cited by
K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent studies have explored combining different LoRAs to jointly generate learned style and content. However, existing methods either fail to effectively preserve both the original subject and style simultaneously or require additional training. In this paper, we argue that the intrinsic properties of LoRA can effectively guide diffusion models in merging learned subject and style. Building on this insight, we propose K-LoRA, a simple yet effective training-free LoRA fusion approach. In each attention layer, K-LoRA compares the Top-K elements in each LoRA to be fused, determining which LoRA to select for optimal fusion. This selection mechanism ensures that the most representative features of both subject and style are retained during the fusion process, effectively balancing their contributions. Experimental results demonstrate that the proposed method effectively integrates the subject and style information learned by the original LoRAs, outperforming state-of-the-art training-based approaches in both qualitative and quantitative results.
Forward citations
Cited by 4 Pith papers
-
DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement
Decoupled dual cross-attention plus style/content augmentations let a TRELLIS-based model inject image style into 3D assets in ~10s while better preserving geometry than prior 2D-to-3D pipelines.
-
TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models
TARA adds token-focused masking and a token alignment loss to LoRA adapters, allowing several independently trained personalized adapters to be composed with less identity loss and feature leakage.
-
FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization
A method for multi-subject image personalization that fuses independently trained LoRA modules at inference time on visual autoregressive models.
-
LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion
LiON-LoRA adds a learned scaling token to video-diffusion LoRA adapters, enabling linear and independent control of camera trajectory and object motion strength.
Discussion (0). Sign in to comment.