Personalized image generation requires text-to-image generative models that capture the core features of a reference subject to allow for controlled generation across different contexts. Existing methods face challenges due to complex training requirements, high inference costs, limited flexibility, or a combination of these issues. In this paper, we introduce DreamCache, a scalable approach for efficient and high-quality personalized image generation. By caching a small number of reference image features from a subset of layers and a single timestep of the pretrained diffusion denoiser, DreamCache enables dynamic modulation of the generated image features through lightweight, trained conditioning adapters. DreamCache achieves state-of-the-art image and text alignment, utilizing an order of magnitude fewer extra parameters, and is both more computationally effective and versatile than existing models.
@article{arxiv.2411.17786,
title = {DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching},
author = {Emanuele Aiello and Umberto Michieli and Diego Valsesia and Mete Ozay and Enrico Magli},
journal= {arXiv preprint arXiv:2411.17786},
year = {2024}
}