Systems, methods, and computer-readable media are disclosed for identifying a set of images of child variants of a parent item, identifying a set of colors in the set of images, categorizing the set of colors into color subgroups, identifying a set of representative color(s) for the color subgroups, generating a color value distribution representation for an image of a child variant that indicates a respective number of pixels in the child variant image corresponding to each of one or more representative colors, identifying a color cluster in the color value distribution representation, scoring the color cluster, and selecting a particular color from the color cluster for inclusion in a sample image of the child variant if the color cluster score meets or exceeds a threshold value.