Method Overview
- T-LoRA tackles overfitting problem related to position and background in few-shot diffusion model personalization, enabling versatile and enriched generation;
- The method is based on the observation that higher (noisier) diffusion timesteps are more vulnerable to overfitting than lower ones;
- Key components:
- Timestep-dependent LoRA rank masking to restrict concept information injection;
- Orthogonal initialization for efficient exclusion of LoRA components.
FLUX.1 [dev] Results
SD-XL Results
BibTeX
1@article{soboleva2025t,
2 title={T-lora: Single image diffusion model customization without overfitting},
3 author={Soboleva, Vera and Alanov, Aibek and Kuznetsov, Andrey and Sobolev, Konstantin},
4 journal={arXiv preprint arXiv:2507.05964},
5 year={2025}
6}