Abstract: The application describes method of modifying an image. The method may include a step of receiving, via an user interface of a service, a reference image and an input including text associated with the reference image. The method may also include a step of determining, via a trained machine learning (ML) model, one or more features of the reference image. The method may further include a step of modifying, via one or more trained latent diffusion models (LDMs), the reference image based upon the determined features and the received input. Any one or more of a background of the reference image, an area of the reference image or a style of the reference image may be modified. The method may even further include a step of causing to display, via the user interface of the service, the modified image.

Abstract: An inflatable sleeper including an inflatable support skeleton of spaced apart parallel tubular arches and an inflatable mattress having an air inlet-outlet valve and further including a waterproof cover, which has an arched door parallel to the arches, removably attached to and covering the entire support skeleton when the support skeleton is in an inflated condition. Each arch has a pair of outer ends attached to and in fluid communication with a bottom edge of the mattress. Spaced apart fasteners, such as hook and loop fasteners, on the arches secure the cover and the support skeleton together. Spaced apart tie down eyelets on the cover are configured to receive a tie down fastener, such as a rope, therethrough to secure the cover and support skeleton to one of a pickup truck bend interior side and a ground stake. The mattress rests atop a separate foldable floor provided.