Abstract Aims Obesity is a major risk factor for atrial fibrillation (AF). Compared with stable weight, gaining weight was associated with a higher risk of incident AF in observational studies. The results, however, are conflicting regarding weight loss and risk of AF. This study aimed to assess the association between 5-year weight changes and risk of incident AF. Methods and results The study was based on participants from the Danish Diet, Cancer, and Health Cohort. Body mass index (BMI) was assessed at a baseline examination and at a second examination 5 years later. Diagnoses of AF and co-morbidities were retrieved from the Danish National Patient Registry. In total, 43 758 participants without prior AF were included. The median age was 61 years and 54% were female. During a median follow-up of 15.7 years, 5312 individuals had incident AF (incidence rate 8.6/1000 person-years). Compared with stable weight, weight gain between 2.5 and 5 BMI units (kg/m2) was associated with a higher risk of AF [hazard ratio (HR) 1.24, 95% confidence interval (CI) 1.09–1.41]. Weight gain of 5 or more BMI units (kg/m2) was associated with a HR of 1.95 (95% CI 1.48–2.56) of incident AF. However, there was no statistically significant association between weight loss and risk of AF. Conclusion Five-year weight gain was associated with greater risk of AF compared with stable weight in the Danish Diet, Cancer, and Health Cohort. There was no statistically significant association between weight loss and risk of AF.