US 11,714,849 B2
Image generation system and method
Huiling Zhou, Hangzhou (CN); Jinbao Xue, Hangzhou (CN); Zhikang Li, Hangzhou (CN); Jie Liu, Hangzhou (CN); Shuai Bai, Beijing (CN); Chang Zhou, Hangzhou (CN); Hongxia Yang, Hangzhou (CN); and Jingren Zhou, West Lafayette, IN (US)
Assigned to Alibaba Damo (Hangzhou) Technology Co., Ltd., Hangzhou (CN)
Filed by Alibaba Damo (Hangzhou) Technology Co., Ltd., Zhejiang (CN)
Filed on Aug. 23, 2022, as Appl. No. 17/894,090.
Claims priority of application No. 202111015905.2 (CN), filed on Aug. 31, 2021.
Prior Publication US 2023/0068103 A1, Mar. 2, 2023
Int. Cl. G06F 16/583 (2019.01); G06F 16/58 (2019.01); G06F 18/22 (2023.01)
CPC G06F 16/583 (2019.01) [G06F 16/5866 (2019.01); G06F 18/22 (2023.01)] 20 Claims
OG exemplary drawing
 
19. A computer-implemented method, comprising:
generating, according to user behavior data associated with a specified object category and object description information of the specified object category in a manufacturing industry, a style description text for the specified object category, wherein the style description text reflects a style requirement of the specified object category;
inputting the style description text into a text prediction-based first image generation model for image generation, to obtain a plurality of initial object images, wherein the first image generation model comprises an encoder-decoder structure implemented based on a vector quantization generative adversarial network (VQGAN) and a sparse attention mechanism;
inputting the plurality of initial object images and the style description text into a second image-text matching model for matching, to obtain at least one candidate object image of which a matching degree meets a threshold requirement; and
displaying the at least one candidate object image to an evaluation system, obtaining a selected target object image in response to selection of the evaluation system, and using the target object image for a subsequent manufacturing link.