Picture generation method and device, storage medium and electronic device

Abstract

The invention discloses a picture generation method and device, a storage medium and an electronic device. The method comprises the following steps of obtaining a source portrait picture displaying atarget object; clipping a source portrait image to obtain a face region image corresponding to a face of a target object; inputting the facial region picture into a picture generation model, wherein the picture generation model is obtained after machine training by using a plurality of sample pictures through an antagonistic neural network model; using the output result of the picture generation model to generate a target portrait picture, wherein a target hairstyle matching the face of the target object is displayed in the target portrait picture. The invention solves the technical problem that the picture generated in the related art is low in accuracy.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a method and device for generating a picture, a storage medium and an electronic device. Background technique [0002] In many terminal applications for editing pictures, corresponding adjustments are often made to the image elements contained in the pictures, such as adjusting the combination of different image elements to synthesize a new picture. In order to simplify the compositing steps, different image elements are usually simply combined and stitched directly. For example, editing hairstyles in a portrait picture can generate pictures with different hairstyles for that subject by pasting different types of hairstyles directly near the same subject's face. [0003] However, in the picture generation method provided by the above-mentioned related technologies, the user often manually selects the hairstyle to be replaced for the object in the picture according to his own aes...

AI Technical Summary

Problems solved by technology

[0003] However, in the picture generation method provided by the above-mentioned related technologies, the user often manually selects the hairstyle to be replaced for the object in the picture according to his own aesthetics, and there is no guarantee that the object in the generated picture matches the hairstyle after replacement. , which leads to the problem of low accuracy of generating pictures

[0004] For the above problems, no effective solution has been proposed

Images