September 19thquick workerItsKeLing AI Launch NewDigital Humanfunction to generate 1080p / 48FPS for up to 1 minute by adding a text or audio to a role pictureDigital Human VideoI don't know. The product is now open。
It is understood by 1AI that the digital function is based on a multimodular understanding combined with the depth of the video generation model, which achieves precision synchronization of oral and emotional actions. The DiT structure, based on Transformer, has a unique advantage in processing time-series information and fine-particle control, and is capable of finely deciphering facial features, understanding audio semantics and extrapolating appropriate facial expressions and micro-actions based on voice content, thus ensuring that the digital person generated remains consistent throughout the video。
IN TERMS OF ROLE AND LANGUAGE SUPPORT, THE AI DIGITAL PERSON FUNCTIONS WELL. IT SUPPORTS A WIDE RANGE OF ROLE TYPES, INCLUDING REALITY, ANIMATED ROLE AND EVEN ANIMAL IMAGES, AND COVERS A VARIETY OF LANGUAGES, INCLUDING CHINESE, ENGLISH, JAPANESE AND KOREAN, WHICH CAN MEET THE DIVERSE NEEDS OF DIFFERENT USERS. IN TERMS OF PRICE STRATEGIES, TOGETHER WITH MEMBERS ' PREFERENCES, THE COST OF USE FOR THE CLINT AID IS AT LEAST 0.12/S。
AT PRESENT, THE VISO AI DIGITAL PERSON FUNCTION IS IN THE PUBLIC-DETECTION PHASE AND THE PRODUCT IS BEING MADE AVAILABLE TO USERS. USERS CAN EXPERIENCE IT THROUGH THE CLIN AI OFFICIAL NETWORK. IN THE FUTURE, AS TECHNOLOGY CONTINUES TO MATURE AND API IS OPENED UP, THE CLIN AI DIGITAL POPULATION IS EXPECTED TO INTEGRATE WITH MORE THIRD-PARTY PLATFORMS AND APPLICATIONS TO BUILD BETTER ECOSYSTEMS。