A method for generating a wrinkle-removed face
By constructing a large-scale face image dataset and multi-threshold edge detection, combined with the ControlNet controlled diffusion model, the problems of wrinkles and uneven skin tone in face images in AIGC technology were solved, generating high-quality wrinkle-free and fair face images, thus improving the aesthetics of the images.
CN122156357APending Publication Date: 2026-06-05KAIYU DIGITAL INFORMATION TECHNOLOGY (BEIJING) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- KAIYU DIGITAL INFORMATION TECHNOLOGY (BEIJING) CO LTD
- Filing Date
- 2026-01-16
- Publication Date
- 2026-06-05
AI Technical Summary
Technical Problem
Existing AIGC technology suffers from wrinkles and uneven skin tone when generating facial images, affecting the aesthetics of the images.
Method used
By constructing a large-scale facial image dataset, employing multi-threshold edge detection and ControlNet controlled diffusion model, combined with facial landmark detection and skin color classification, we can achieve accurate detection and removal of wrinkles, and generate high-quality wrinkle-free, fair facial images through an end-to-end joint training framework.
Benefits of technology
It achieves efficient and accurate facial wrinkle removal and skin whitening effects, generating more natural and delicate images that meet users' aesthetic needs for high-quality facial images.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122156357A_ABST
Abstract
The application provides a method for removing wrinkles when generating a human face. The method includes constructing a large-scale human face image dataset; using a multi-scale edge detection method to extract edge features and fuse them into a single composite image; positioning the facial contour area based on a human face key point detection technology to generate a human face wrinkle feature map; inputting text description information and an original human face image into a human face diffusion model, and simultaneously inputting the wrinkle feature map as a conditional constraint into a ControlNet module; guiding the generation process of the diffusion model through the ControlNet module to realize an end-to-end joint training framework; generating a preliminary human face image output in an initial generation stage; constructing a comprehensive edge representation through multi-scale edge feature fusion; constructing a feature image representing wrinkle distribution through a wrinkle feature map; and generating an optimization through a double guidance mechanism to generate a beautification effect. In the finally generated picture, the human face is whiter, wrinkles are removed, and the overall aesthetic sense is obviously improved.
Need to check novelty before this filing date? Find Prior Art