Tencent Cloud intelligently publishes a small sample Homo sapiens production platform
Thank you, Mr. Air, a netizen of CTOnews.com, for your clue delivery! CTOnews.com, April 25, Tencent Cloud Intelligent small sample Homo sapiens production platform has been released for the first time. The platform has the characteristics of small training samples, high production efficiency and automatic production.
CTOnews.com obtained from the Tencent official that it only takes 3 minutes for real people to broadcast video and 100 sentences of voice material, and the platform can model and generate high-definition portraits in real time through multi-modal data input of audio and text, and produce "digital Homo sapiens" similar to real people within 24 hours.
Small samples of intelligent people support half-body, full-body image display, gestures will be flexibly adjusted according to the content, but also support arbitrary change of recording background. Compared with 2D real-life high-quality digital people, small-sample Homo sapiens does not need professional studio recording material, and costs less; compared with digital people who can only show facial shape, small-sample Homo sapiens can design gestures according to the text. Lip movement, mouth shape, facial expression to reproduce human style.
Chen Lei, general manager of Tencent Cloud Intelligent Digital Homo sapiens products, said Tencent Cloud Intelligent is working to build an automated "AI + Digital Homo sapiens factory" to achieve "self-service" purchase, production and application of Digital Homo sapiens with an one-stop platform for "production, sales and service". At present, dozens of partners have relied on the platform to provide digital Homo sapiens live SaaS and knowledge oral SaaS applications to the industry, covering medical, media and financial industries.
