While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training samples are limited, compromising both generalization capability and output diversity. This paper tackles the challenging yet most impactful task of adapting a diffusion model using just a single concept image, as single-image customization holds the greatest practical potential. We introduce T-LoRA, a Timestep-Dependent Low-Rank Adaptation framework specifically designed for diffusion model personalization. In our work we show that higher diffusion timesteps are more prone to overfitting than lower ones, necessitating a timestep-sensitive fine-tuning strategy. T-LoRA incorporates two key innovations: (1) a dynamic fine-tuning strategy that adjusts rank-constrained updates based on diffusion timesteps, and (2) a weight parametrization technique that ensures independence between adapter components through orthogonal initialization. Extensive experiments show that T-LoRA and its individual components outperform standard LoRA and other diffusion model personalization techniques. They achieve a superior balance between concept fidelity and text alignment, highlighting the potential of T-LoRA in data-limited and resource-constrained scenarios.

This paper proposes a constrained canonical polyadic (CP) tensor decomposition method with low-rank factor matrices. In this way, we allow the CP decomposition with high rank while keeping the number of the model parameters small. First, we propose an algorithm to decompose the tensors into factor matrices of given ranks. Second, we propose an algorithm which can determine the ranks of the factor matrices automatically, such that the fitting error is bounded by a user- selected constant. The algorithms are verified on the decomposition of a tensor of the MNIST hand-written image dataset.

Abstract This study has developed a genetic algorithm (GA) approach to the problem of task scheduling for multiprocessor systems. The proposed GA implements the local repairing mechanism and the penalty method, and it does not need tuning of any parameters for high performance. Comparison with other scheduling methods, based on a GA approach, indicates that the proposed GA is competitive in solution quality and also computational cost.