Image processing method, and training method and device of image processing model

The invention provides an image processing method and a training method and device of an image processing model, relates to the technical field of artificial intelligence, in particular to the technical fields of image processing, computer vision, augmented reality and deep learning, virtual digital humans and the like, and can be applied to scenes such as meta universe and the like. According to the implementation scheme, a target image is obtained, the target image comprises a target object, the target object corresponds to a target type, the target type corresponds to multiple key points, each key point in the multiple key points has corresponding structured information, and the structured information at least indicates at least one key point adjacent to the corresponding key point in the multiple key points; obtaining a key point feature corresponding to each key point in the plurality of key points based on the target image; and obtaining a corresponding position of each key point in the plurality of key