Personalize Anything for Free with Diffusion Transformer
Personalize Anything for Free with Diffusion Transformer
计算技术、计算机技术
Zehuan Huang,Haoran Feng,Lin Li,Hairong Lv,Lu Sheng.Personalize Anything for Free with Diffusion Transformer[EB/OL].(2025-03-16)[2025-10-25].https://arxiv.org/abs/2503.12590.点此复制
Personalized image generation aims to produce images of user-specified
concepts while enabling flexible editing. Recent training-free approaches,
while exhibit higher computational efficiency than training-based methods,
struggle with identity preservation, applicability, and compatibility with
diffusion transformers (DiTs). In this paper, we uncover the untapped potential
of DiT, where simply replacing denoising tokens with those of a reference
subject achieves zero-shot subject reconstruction. This simple yet effective
feature injection technique unlocks diverse scenarios, from personalization to
image editing. Building upon this observation, we propose \textbf{Personalize
Anything}, a training-free framework that achieves personalized image
generation in DiT through: 1) timestep-adaptive token replacement that enforces
subject consistency via early-stage injection and enhances flexibility through
late-stage regularization, and 2) patch perturbation strategies to boost
structural diversity. Our method seamlessly supports layout-guided generation,
multi-subject personalization, and mask-controlled editing. Evaluations
demonstrate state-of-the-art performance in identity preservation and
versatility. Our work establishes new insights into DiTs while delivering a
practical paradigm for efficient personalization.
展开英文信息
评论