METHOD, APPARATUS, DEVICE AND MEDIUM FOR GENERATING A VIDEO

Abstract: provided are a method and an apparatus for generating a video, a device, and a medium. in one method, a first reference image and a second reference image are determined from a plurality of reference images in a reference video. a reference text for describing the reference video is received. a generation model is acquired based on the first reference image, the second reference image and the reference text. the generation model is configured to generate a target video based on a first image, a second image and a text. with example implementations of the present disclosure, the second reference image can serve as guiding data to determine a development direction of a story in the video. in this way, the generation model can clearly grasp changes of various image contents in the video, which is beneficial to generating richer and more realistic videos.

Inventor(s): Yan Zeng, Guoqiang Wei, Jiaxin Zou, Yuchen Zhang, Hang Li

CPC Classification: G11B27/036 (INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer ; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards ; transferring data from one type of record carrier to another ; circuits for coupling output of reproducer to radio receiver ; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor ))

Search for rejections for patent application number 20250166666