Alibaba’s new EMO AI one-upped OpenAI by making ‘Sora lady’ sing like Dua Lipa

[Trendingger]

Image: GitHub

 

Alibaba’s new AI has made OpenAI’s Sora sing, and the internet can’t get enough of it. This groundbreaking development has set a new benchmark in the realm of AI video generation, pushing the boundaries of realism in animating subjects.

 

Alibaba’s EMO, short for Emote Portrait Alive, is an advanced AI video generator that transforms static images into expressive actors and singers. It’s a leap forward in audio-driven video generation, a field that has long challenged AI experts. EMO surpasses traditional methods that often struggle to recreate the complexities and nuances of human expressions.

 

In a stunning demonstration of its capabilities, EMO made Sora’s virtual counterpart belt out a Dua Lipa song. This feat was achieved by converting audio waves directly into video frames, resulting in remarkably natural animations that capture subtle mannerisms and individual quirks unique to each person.

 

Source: GitHub

 

This development has sparked a flurry of online discussions, with many marveling at the lifelike quality of the animations. The ability of EMO to convey complex emotions and preserve the identity of the animated subject has been particularly praised.

 

As we marvel at this technological marvel, one can’t help but wonder: What does this mean for the future of AI in entertainment and beyond? How will this change our interaction with digital content? We’d love to hear your thoughts on this. Do you think this is the next big thing in AI, or just a passing trend?

 

 

Read more:

• https://humanaigc.github.io/emote-portrait-alive/
• https://interestingengineering.com/innovation/emo-alibaba-researchers-breathe-life-into-portraits-with-new-ai-tool
• https://says.com/my/tech/alibaba-s-ai-video-generator-is-so-good-it-can-make-still-images-sing