Image generation method and device, computer device, storage medium and program product

By optimizing face restoration and prompt word optimization in the iterative process of the image generation model, the problems of misjudgment of human images and face collapse in the image generation model were solved, and efficient and accurate image generation was achieved.

CN121010661BActive Publication Date: 2026-03-03CHONGQING CHANGAN AUTOMOBILE CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202511545940.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-10-28
Publication Date
2026-03-03
Estimated Expiration
2045-10-28

AI Technical Summary

Technical Problem

Existing image generation models are prone to misjudging the type of prompt words when generating images of people, resulting in images that do not match user needs. Furthermore, they struggle to restore facial details during the decoding process, leading to quality issues such as facial distortion.

Method used

By acquiring the original prompt words input by the user, similar preset prompt words, potential classification lists, and confused category pairs are determined. Face restoration is performed during the iterative process of optimizing the image generation model. A large language model is used to identify scene types and add facial details to optimize prompt words, ensuring the accuracy and quality of image generation.

Benefits of technology

It improves the efficiency and quality of image generation, avoids face collapse, ensures that the generated images match user needs, and enhances the robustness of the image generation model and user satisfaction.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application relates to the technical field of intelligent model, and discloses an image generation method and device, computer equipment, storage medium and program product, the present application determines similar preset prompt words, potential classification list of to-be-generated images and confusion category pairs based on original prompt words, so as to utilize the confusion category pairs for classification correction, avoid misjudging the theme category of the to-be-generated images, and improve the accuracy of the theme category. If the theme category is a person theme, the original prompt word is optimized through the scene type of the to-be-generated images to obtain a target prompt word, so that the image generation model generates images by utilizing the target prompt word rich in details and the scene type. When the image generation model has not ended iteration, the intermediate image generated by the image generation model is subjected to face repair, so as to avoid image repair after the iteration ends, thereby prolonging the generation time, improving the image generation efficiency, avoiding the phenomenon of face collapse, and improving the image generation quality.
Need to check novelty before this filing date? Find Prior Art