The field of human image and animation generation is rapidly advancing, with a focus on improving the quality and controllability of generated images and videos. Recent developments have led to the creation of more realistic and detailed digital humans, with applications in fields such as entertainment, education, and healthcare. A key trend in this area is the use of machine learning models, such as diffusion models and Gaussian splatting, to generate high-quality images and videos. These models are able to capture complex details and nuances of human appearance and movement, allowing for more realistic and engaging digital characters. Another important area of research is the development of methods for controlling and manipulating generated images and videos, such as pose alignment and facial animation. Noteworthy papers in this area include StableAnimator++, which introduces a learnable pose alignment module to improve the quality of generated videos, and GeoAvatar, which proposes a framework for adaptive geometrical Gaussian Splatting to balance identity preservation and novel poses and expressions. Additionally, Dream, Lift, Animate is a novel framework that reconstructs animatable 3D human avatars from a single image, and CartoonAlive is an innovative method for generating high-quality Live2D digital humans from a single input portrait image.