The tech giant Microsoft launched an AI application, VASA-1, which is capable of generating lifelike talking faces of virtual characters using just still images or pictures.
The firm said the newly introduced VASA-1 aims to create moving pictures with lip movements which synchronize with the audio and also capture facial nuances as well as head motions that contribute to the acuity of authenticity and liveliness.
In recent times AI-based tech companies like OpenAI and Adobe have launched prompt-based AI photo or video generators like Sora, which can create realistic and imaginative scenes from text instructions.
Technology pioneer said it aims to achieve holistic facial dynamics and a head movement generation model that works in a face latent space. Additionally, the firm has employed a set of new metrics which outperformed previous methods along various dimensions comprehensively.
Previous week Oversight Board, independent body overseeing AI-generated content on Meta platforms said it would evaluate the two cases, which involved deepfake pornography circulated on Facebook and Instagram to review Meta’s policies.
Microsoft’s research teamx said it aims for a positive implementation of the AI avatars and does not intend to mislead or deceive any individual.
Earlier this month Microsoft and ChatGPT owner OpenAI were planning for a data centre project called Stargate, worth about $100 billion that would contain a supercomputer with millions of specialized server chips to power OpenAI’s artificial intelligence, based on a report of The Information.
To read more on Technology, head to the link.
