Personalized Text-to-Image Generation with Auto-Regressive Models

Kaiyue Sun, Xian Liu, Yao Teng, Xihui Liu

Personalized Text-to-Image Generation with Auto-Regressive Models: 7 upvotes on Hugging Face Daily Papers, #11 of 21 papers on 2025-04-23. Day-by-day upvote history. It lost 12 votes when the Hub removed votes in bulk.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.