Three experiments are presented that investigate the two-dimensional valence/trustworthiness by dominance model of social inferences from faces (Oosterhof & Todorov, 2008). Experiment 1 used image averaging and morphing techniques to demonstrate that consistent facial cues subserve a range of social inferences, even in a highly variable sample of 1000 ambient images (images that are intended to be representative of those encountered in everyday life, see Jenkins, White, Van Montfort, & Burton, 2011). Experiment 2 then tested Oosterhof and Todorov's two-dimensional model on this extensive sample of face images. The original two dimensions were replicated and a novel 'youthful-attractiveness' factor also emerged. Experiment 3 successfully cross-validated the three-dimensional model using face averages directly constructed from the factor scores. These findings highlight the utility of the original trustworthiness and dominance dimensions, but also underscore the need to utilise varied face stimuli: with a more realistically diverse set of face images, social inferences from faces show a more elaborate underlying structure than hitherto suggested.