Tianyancha's intellectual property information shows that recently, the patent application for the "Tusheng video model generation method, video generation method, and device" submitted by Kwai's affiliated company, Beijing Dajia Internet Information Technology Co., Ltd., has been published. The abstract reveals that the video generation method of this patent includes: inputting sample images and sample text descriptions into a preset text-to-video model; performing spatial feature extraction on the sample images and sample text descriptions based on a spatial module, obtaining the first sample feature processing result; processing the first sample feature processing result based on a temporal self-attention module to obtain the second sample feature processing result; controlling motion information on the first sample feature processing result based on a motion adapter module to obtain the third sample feature processing result; generating predicted video data based on the second sample feature processing result and the third sample feature processing result; updating the parameters of the spatial module and motion adapter module based on the preset video data and sample video data to obtain the Tusheng video model. This disclosure can control the motion information of the generated videos and reduce the consumption of system resources.