Systems, methods and non-transitory computer readable media for generating and modifying synthetic visual content using textual input are provided. One or more keywords may be received from a user. The one or more keywords may be used to generate a plurality of textual descriptions. Each generated textual description may correspond to a possible visual content. The generated plurality of textual descriptions may be presented to the user through a user interface that enables the user to modify the presented textual descriptions. A modification to at least one of the plurality of textual descriptions may be received from the user, therefore obtaining a modified plurality of textual descriptions. A selection of one textual description of the modified plurality of textual descriptions may be received from the user. A plurality of visual contents corresponding to the selected textual description may be presented to the user.