Method and system for generating images containing specific objects

Abstract

The present invention provides a method and system for generating an image containing a specific object. An image generation method according to one embodiment includes the steps of: receiving a specification regarding a base model pre-trained to generate an image; receiving a specification regarding prompts and parameters; generating a person image through a Text-to-Image conversion by the base model based on the prompts and parameters; generating a masked image by masking the face of the person image; receiving a specification regarding an additional model pre-trained to generate an image of the specific person using the base model and a set of images of the specific person; and generating a final image of the specific person through an Image-to-Image conversion based on the base model, adjusted by the additional model, using the person image and the masked image as input.

Images