Visual short-term memory (VSTM) for simple objects, such as coloured shapes, has been extensively studied, yet objects in our visual environment are vastly richer, semantically loaded, and recognisable. Recognisability may boost VSTM capacity, recruit additional resources, or widen the representational space within which complex objects are encoded and maintained in VSTM. We used a novel stimulus generation method to parametrically warp photographic images along a continuum, allowing separate estimation of the precision of memory representations and the number of items retained. The stimulus generation method was also designed to create unrecognisable, though perceptually matched, stimuli, to investigate the impact of recognisability on VSTM. We adapted the widely used change detection and continuous report paradigms for use with complex, photographic images. Across three functional magnetic resonance imaging (fMRI) experiments, we demonstrate greater precision for recognisable objects in VSTM compared to unrecognisable objects. This clear behavioural advantage is not the result of recruitment of additional brain regions. Representational similarity analysis revealed greater variability across item repetitions in the representations of recognisable, compared to unrecognisable complex objects. We therefore propose that a richer range of neural representations support VSTM for complex recognisable objects.