Abstract: Described herein is a computer implemented method for generating a new deck format design based on a source design.

Abstract: Described herein is a computer implemented method for automatically generating a design. The method includes receiving an input prompt for generating the design and generating a design outline based on the input prompt. The design outline includes a style descriptor for the design. The method further includes retrieving a design template based on the design outline. The design template includes a placeholder design element. The method further includes retrieving at least one design element for the placeholder element. The design is generated by populating the placeholder element with the design element.

Abstract: Described herein is a computer implemented method. The method includes accessing a set of one or more source objects, wherein each source object is associated with a source content segment of a document-format design. The method further includes generating a first pagination candidate that includes a first candidate page associated with a first subset of source objects and a second candidate page associated with a second subset of source objects from the one or more source objects and splitting the first candidate page by: determining a first split level; determining a third subset of source objects based on the first split level; determining a fourth subset of source objects based on the first split level; generating a third candidate page that is associated with the third subset of source objects; and generating a fourth candidate page that is associated with the fourth subset of source objects.

Abstract: A method for assigning a personalized aesthetic score to an image is provided. The method includes providing a base neural network for generating learned features. The base neural network is trained on a first set of training images and the base neural network includes two or more layers comprising one or more initial layers and one or more final layers. The method further includes receiving a second set of training images and updating the base neural network to generate a personalized neural network based on the received second set of training images. Updating the base neural network comprises re-training the final layers of the base neural network with the second set of images and keeping the initial layers of the base neural network, such that the personalized neural network includes two or more layers comprising one or more initial layers and one or more final layers.

Abstract: A method for assigning a personalized aesthetic score to an image is provided. The method includes providing a base neural network for generating learned features. The base neural network is trained on a first set of training images and the base neural network includes two or more layers comprising one or more initial layers and one or more final layers. The method further includes receiving a second set of training images and updating the base neural network to generate a personalized neural network based on the received second set of training images. Updating the base neural network comprises re-training the final layers of the base neural network with the second set of images and keeping the initial layers of the base neural network, such that the personalized neural network includes two or more layers comprising one or more initial layers and one or more final layers.