Image generation method and device

The invention discloses an image generation method and device. An image generation method according to an embodiment includes the steps of: acquiring voice data, face image data including a face, and input data including an image purpose; determining a motion of a character based on a motion of a facial feature extracted from the facial image data and the voice data; determining a lens corresponding to the role based on the voice data and the purpose; and generating an image corresponding to the voice data based on the determined shot. 本发明公开了一种图像生成方法以及装置。根据一实施例的图像生成方法包括以下步骤：获取语音数据、包括面部的面部图像数据，以及包括图像目的的输入数据；基于从所述面部图像数据提取的面部特征的运动以及所述语音数据，确定角色的运动；基于所述语音数据与所述目的，确定与所述角色对应的镜头；以及基于所述确定的镜头，生成与所述语音数据对应的图像。