The relationship between vitamin D levels and non-alcoholic fatty liver disease (NAFLD) remains unestablished. In this study, we aimed to explore the relationship between vitamin D levels and NAFLD based on population survey data. This cross-sectional study was conducted based on data from the National Health and Nutrition Examination Survey. Liver steatosis was diagnosed by ultrasonography. Binary logistic regression analyses were performed to determine the relationship between vitamin D status and NAFLD. A total of 9,782 participants were identified in this analysis, with 46.8% male and an average age of 44.41±0.16 y old. Among them, 6,047 (61.8%) cases were without NAFLD, 1,357 (13.9%) had mild NAFLD, 1,594 (16.3%) had moderate and 784 (8.0%) had severe NAFLD. Compared to those with non-NAFLD or mild NAFLD, patients in the moderate to severe NAFLD group had higher vitamin D deficiency or insufficiency rates (12.4% vs 11.5% and 36.8% vs 33.2%, respectively). After adjustment for male gender, older age, race, BMI, history of diabetes and vitamin D intake, vitamin D levels were independently associated with the severity of NAFLD (vitamin D deficiency group OR: 1.314, 95% CI: 1.129 to 1.529, vitamin D insufficiency group OR: 1.203, 95% CI: 1.090 to 1.328). Besides that, cold season was also found to be an independent factor for NAFLD (OR: 0.896, 95% CI: 0.820 to 0.979). Lower vitamin D level is an independent risk factor for NAFLD. Vitamin D levels are inversely associated with the severity of NAFLD. Cold season increases the risk of NAFLD independently.