The IC-Light project aims to manipulate lighting conditions of images using advanced machine learning techniques to achieve consistent lighting effects. It offers two types of models: text-based re-illumination models and background-based models, both of which take the foreground image as input. The significance of this technology lies in its ability to achieve precise control over image lighting without depending on complex prompts, simply through text descriptions or background conditions. This is of great importance for fields such as image editing, augmented reality, and virtual reality.