Object combination image generation method and device, electronic equipment and storage medium

The embodiment of the invention provides an object combination image generation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a description text of an input object combination and a mask image and a first draft image of each target object in the object combination, obtaining a display position relationship set for the object combination, determining a second line draft image corresponding to each target object according to the display position relationship and the first line draft image, and drawing each target object in a drawing area corresponding to the mask image one by one by adopting a text generation image model based on the description text, the mask image and the second line draft image, and obtaining a combined image of the object. The highly controllable object combination image is generated through image-text joint guidance, and the image effect and the manufacturing efficiency of the object combination image are improved. 本申请实施例提供一种对象组