2024/03/04 by Jiaxiang Cheng, Cheng, Jiaxiang, Pan Xie +17 · 1 voice · 8 citations
Decision Sciences · Mathematics · Medicine · #Adapter (computing) #Artificial intelligence #Computer hardware #Computer science #Diffusion #Domain (mathematical analysis) #Mathematical analysis #Mathematics #Medical Imaging Techniques and Applications #Physics #Resolution (logic) #Simulation Techniques and Applications
paper · pdf · doi:10.48550/arxiv.2403.02084
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2024/03/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Recent advancement in text-to-image models (e.g., Stable Diffusion) and corresponding personalized technologies (e.g., DreamBooth and LoRA) enables individuals to generate high-quality and imaginative images. However, they often suffer from limitations when generating images with resolutions outside of their trained domain. To overcome this limitation, we present the Resolution Adapter (ResAdapter), a domain-consistent adapter designed for diffusion models to generate images with unrestricted resolutions and aspect ratios. Unlike other multi-resolution generation methods that process images of static resolution with complex post-process operations, ResAdapter directly generates images with the dynamical resolution. Especially, after learning a deep understanding of pure resolution priors, ResAdapter trained on the general dataset, generates resolution-free images with personalized diffusion models while preserving their original style domain. Comprehensive experiments demonstrate that ResAdapter with only 0.5M can process images with flexible resolutions for arbitrary diffusion models. More extended experiments demonstrate that ResAdapter is compatible with other modules (e.g., ControlNet, IP-Adapter and LCM-LoRA) for image generation across a broad range of resolutions, and can be integrated into other multi-resolution model (e.g., ElasticDiffusion) for efficiently generating higher-resolution images. Project link is https://res-adapter.github.io