Recent work within neuroimaging consortia have aimed to identify reproducible, and often subtle, brain signatures of psychiatric or neurological conditions. To allow for highâpowered brain imaging analyses, it is often necessary to pool MR images that were acquired with different protocols across multiple scanners. Current retrospective harmonization techniques have shown promise in removing siteârelated image variation. However, most statistical approaches may overâcorrect for technical, scanningârelated, variation as they cannot distinguish between confounded imageâacquisition based variability and siteârelated population variability. Such statistical methods often require that datasets contain subjects or patient groups with similar clinical or demographic information to isolate the acquisitionâbased variability. To overcome this limitation, we consider siteârelated magnetic resonance (MR) imaging harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deepâlearning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a single reference image, without knowing their site/scanner labels a priori. We trained our model using data from five largeâscale multisite datasets with varied demographics. Results demonstrated that our styleâencoding model can harmonize MR images, and match intensity profiles, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. We highlight the effectiveness of our method for clinical research by comparing extracted cortical and subcortical features, brainâage estimates, and caseâcontrol effect sizes before and after the harmonization. We showed that our harmonization removed the siteârelated variances, while preserving the anatomical information and clinical meaningful patterns. We further demonstrated that with a diverse training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising tool for ongoing collaborative studies. Source code is released in USCâIGC/style_transfer_harmonization (github.com).