Pith. sign in

REVIEW 11 cited by

LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models

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

arxiv 2403.11627 v2 pith:56K7E4SD submitted 2024-03-18 cs.CV

classification cs.CV
keywords conceptlora-composerconceptscustomizationconfusionconstraintsenhancinglatent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a fusion matrix of multiple Low-Rank Adaptations (LoRAs) to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, where the model struggles to preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through concept injection constraints, enhancing concept visibility via an expanded cross-attention mechanism. To combat concept confusion, concept isolation constraints are introduced, refining the self-attention computation. Furthermore, latent re-initialization is proposed to effectively stimulate concept-specific latent within designated regions. Our extensive testing showcases a notable enhancement in LoRA-Composer's performance compared to standard baselines, especially when eliminating the image-based conditions like canny edge or pose estimations. Code is released at \url{https://github.com/Young98CN/LoRA_Composer}

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem

    cs.CR 2026-06 unverdicted novelty 7.0 of 10

    PoisonLoRA demonstrates ~100% attack success rates for stealthy LoRA poisoning via concept hijacking and task injection on real platforms, with robustness to base model transfer and multiple remixes.

  2. Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

    cs.CV 2025-12 unverdicted novelty 7.0 of 10

    LivingSwap is the first video reference-guided face swapping model that uses keyframe conditioning and temporal stitching to preserve source video realism with high fidelity across long sequences.

  3. ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing

    cs.CV 2025-07 unverdicted novelty 7.0 of 10

    ChangeBridge introduces a drift-asynchronous diffusion bridge with composed initialization, pixel-wise drift maps, and drift-aware denoising to produce spatially and temporally coherent post-event remote sensing images.

  4. Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    CCDM uses attribute-decoupled LoRA with relevance-guided aggregation and controllable regional context synthesis to support incremental concept customization in diffusion models while mitigating catastrophic forgettin...

  5. NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion

    cs.CV 2025-11 unverdicted novelty 6.0 of 10

    NP-LoRA fuses subject and style LoRAs via null-space projection of the content update onto the orthogonal complement of the style subspace, with a soft variant controlled by one parameter.

  6. AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    AutoLoRA uses a learned encoder to map LoRA weights and text prompts into one embedding space for retrieval, and then fuses the retrieved LoRAs with per-dimension learned gates during generation.

  7. FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A method for multi-subject image personalization that fuses independently trained LoRA modules at inference time on visual autoregressive models.

  8. FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    FREE-Switch dynamically switches LoRA adapters using frequency importance per diffusion step and adds semantic alignment to reduce content drift when merging specialized image generators.

  9. From Wardrobe to Canvas: Wardrobe Polyptych LoRA for Part-level Controllable Human Image Generation

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Wardrobe Polyptych LoRA lets a single diffusion model compose a person's face and clothing from multiple reference photos into new full-body images, generalizing to unseen identities without inference-time fine-tuning.

  10. LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion

    cs.CV 2025-07 conditional novelty 5.0 of 10

    LiON-LoRA adds a learned scaling token to video-diffusion LoRA adapters, enabling linear and independent control of camera trajectory and object motion strength.

  11. Low-Rank Adaptation Redux for Large Models

    cs.LG 2026-04 unverdicted novelty 3.0 of 10

    An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.

Pith tools