Methods and systems are disclosed for generating high resolution images using lower resolution machine learning models. The system receives one or more images depicting a real-world object in a real-world scene and receives a source image depicting a fashion item comprising a target. The system processes, using one or more machine learning models, the one or more images together with the source image to generate a new image depicting the real-world object wearing the fashion item depicted in the source image, the new image having a lower image resolution than an image resolution of the source image. The system selectively blends pixels of the new image with pixels of the source image to generate a virtual extended reality (XR) experience.