Imagination-to-learn is a specific learning strategy that has been studied in many academic fields. The present study investigated whether imagination is beneficial overall for learning compared to conventional study strategies, while also identifying moderator factors affecting the global effect. A meta-analysis was conducted by scientifically rigorous experiments comparing the learning outcomes of students who were asked to form a mental image of the events described in learning material while reading (imagination condition) or were given no imagination instructions (control condition). A total of 21 experimental studies published on the PsycINFO, Web of Science, ProQuest Dissertations and Theses, ERIC and Google Scholar databases were included, yielding 70 pair-wise comparisons with N = 2625 participants. An overall positive effect of imagination-to-learn was found for both retention (g[superscript +] = 0.40, 95% CI [0.23, 0.58], z = 4.63, p < 0.001) and transfer (g[superscript +] = 0.51, 95% CI [0.22, 0.43, z = 3.43, p < 0.001]) performance. However, analysis of the funnel plots showed that publication bias was present in the reporting of learning outcomes. Analysis of the moderators indicated that the effect sizes differed significantly only with respect to learners' prior knowledge for transfer performance and their educational level for retention scores. Based on these findings, the present study provides important directions for future research and practices.