2025/04/17 by Kaiyue Sun, Xian Liu, Sun, Kaiyue +5 · 7 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis #Computer Graphics and Visualization Techniques #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2504.13162
Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain, auto-regressive models, with their unified architecture for text and image modeling, remain underexplored for personalized image generation. This paper investigates the potential of optimizing auto-regressive models for personalized image synthesis, leveraging their inherent multimodal capabilities to perform this task. We propose a two-stage training strategy that combines optimization of text embeddings and fine-tuning of transformer layers. Our experiments on the auto-regressive model demonstrate that this method achieves comparable subject fidelity and prompt following to the leading diffusion-based personalization methods. The results highlight the effectiveness of auto-regressive models in personalized image generation, offering a new direction for future research in this area.