CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908861066117120 |
|---|---|
| author | Li, Yu Cai, Yujun Zhang, Chi |
| author_facet | Li, Yu Cai, Yujun Zhang, Chi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18936 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion Li, Yu Cai, Yujun Zhang, Chi Computer Vision and Pattern Recognition 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. |
| title | CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.18936 |