DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
Abstract
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.
Cite
Text
Aiello et al. "DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.01164Markdown
[Aiello et al. "DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/aiello2025cvpr-dreamcache/) doi:10.1109/CVPR52734.2025.01164BibTeX
@inproceedings{aiello2025cvpr-dreamcache,
title = {{DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching}},
author = {Aiello, Emanuele and Michieli, Umberto and Valsesia, Diego and Ozay, Mete and Magli, Enrico},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {12480-12489},
doi = {10.1109/CVPR52734.2025.01164},
url = {https://mlanthology.org/cvpr/2025/aiello2025cvpr-dreamcache/}
}