Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training
Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training
Deep Dive
Computer Science > Computer Vision and Pattern Recognition arXiv:2609.13239 (cs) [Submitted on 3 Sep 2026] Title: Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training Authors: Xinglin Hu View a PDF of the paper titled Abstract-LoRA: Unlocking Single-Image Style