The paper presents the first generative photomosaic framework that synthesizes tiles via structure-aligned diffusion models and few-shot personalization instead of color-based matching from large tile collections.
Para: Personalizing text-to-image diffusion via parameter rank reduction
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.
citing papers explorer
-
Generative Phomosaic with Structure-Aligned and Personalized Diffusion
The paper presents the first generative photomosaic framework that synthesizes tiles via structure-aligned diffusion models and few-shot personalization instead of color-based matching from large tile collections.
-
Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.