An image processing apparatus generates a plurality of virtual viewpoint images being temporally consecutive, and includes a data acquisition unit, a parameter acquisition unit, a viewpoint acquisition unit, and a generation unit. The data acquisition unit is configured to acquire image data that is obtained by capturing images in a plurality of directions by a plurality of image capturing devices. The parameter acquisition unit is configured to acquire a parameter related to the acquired image data and related to quality of the plurality of virtual viewpoint images. The viewpoint acquisition unit is configured to acquire viewpoint information representing a moving path of a virtual viewpoint. The generation unit is configured to generate the plurality of virtual viewpoint images according to a virtual viewpoint having a moving speed based on the acquired image data. The moving speed being determined based on the acquired parameter and the acquired viewpoint information.