DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching

Emanuele Aiello, Umberto Michieli, Diego Valsesia, Mete Ozay, Enrico Magli

DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching: 12 upvotes on Hugging Face Daily Papers, #12 of 22 papers on 2024-11-28. Day-by-day upvote history.

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.

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.