Introduction: For human, the resolution of images is important for diagnosis. Many clinical applications of artificial intelligence have been studied, however there are few reports on the difference in diagnosis between humans and artificial intelligence on the point of the renal pathological image resolution. Objectives: We examined whether the resolution of renal pathological images affects diagnosis of artificial intelligence and human. Patients and Methods: From 885 renal biopsy patients, we collected renal IgA immunofluorescent pathological images that resolution is 4, 16, 32, 64, 128, 256 and 512 pixels for each patient, and divided into training data set and validation data set, and created optimum deep learning models for each resolution. To compare with artificial intelligence nephrologist also tried to diagnose by using the same validation data set images. Results: We inputted IgA immunofluorescent pathological images into each optimum model. Human could not identify specific staining site with four pixels images, however, each resolution optimum model showed high accuracy, average over 80%. The each accuarcy was observed higher depending on the resolution. The area under the curve (AUC) showed higher diagnosis ratio depending on the resolution, too. Nephrologist performed high diagnosis sensitivity depending on resolution images as same as artificial intelligence. However, nephrologists’ diagnosis observed large variations in specificity depending on resolution. These results suggested that the resolution might affect specificity for human not artificial intelligence Conclusion: The resolution of images might be important for not AI but human on the point of specificity.