Khürt WilliamsI like that Microsoft is being responsible and will not release any API or software until they are certain that the technology will be used responsibly. #GenerativeAI #vasa1
https://www.microsoft.com/en-us/research/project/vasa-1/
(wp.me pn73N-tjT)
kurtshFrom Microsoft Research: The woman in this video is not real. VASA-1 is capable of not only producing lip movements that are exquisitely synchronized with the audio, but also capturing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity & liveliness.
kaiserkiwi 
Oof. This is a horrible deep fake nightmare…
Bill LoguidiceMicrosoft's VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time #vasa #vasa1 #microsoft #ai #research #artificialintelligence
Microsoft's VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time - fullSTEAMahead365
Single portrait photo + speech audio = hyper-realistic talking face video with precise lip-audio sync, lifelike facial behavior, and naturalistic head movements, generated in real time.
Erik JonkerAs noted in this video from AI Explained ( https://youtu.be/pal-dMJFU6Q?si=Y2qE8S35zvO_i742 ) If you see what a company like Hippocratic AI is doing, https://www.hippocraticai.com/linda
combine this with the human-style interaction VASA-1 from Microsoft will make possible, interaction with real human-like assistants may not be far away and that could really change things, even without a dramatic increase in the capabilities of current LLMs.
#AI #hippocraticAI #VASA1 #Microsoft #LLM #generativeAI
combine this with the human-style interaction VASA-1 from Microsoft will make possible, interaction with real human-like assistants may not be far away and that could really change things, even without a dramatic increase in the capabilities of current LLMs.
#AI #hippocraticAI #VASA1 #Microsoft #LLM #generativeAI
‘Her’ AI, Almost Here? Llama 3, Vasa-1, and Altman ‘Plugging Into Everything You Want To Do’
PrivacyDigestMicrosoft’s VASA-1 can #deepfake a person with one photo and one audio track
#privacy #Microsoft #vasa1
FortuitousOn Tuesday, Microsoft Research Asia unveiled VASA-1, an AI model that can create a synchronized animated video of a person talking or singing from a single photo and an existing audio track. In the future, it could power virtual avatars that render locally and don't require video feeds—or allow anyone with similar tools to take a photo of a person found online and make them appear to say whatever they want.
Here we go again... What they are capable of creating with AI tech is incredible. I do enjoy the development of AI and all its uses that can be of help or entertainment for us.
Though it come with challenges. When general trust goes out the window some gatekeepers will take up the role to enforce trust and present themselves as the keeper and judge of truth, that worries me greatly. AI used extensively in the wrong way can lead to so much mistrust that someone has to come inn and enforce monopoly on trust. With that much power, temptations arise.
On the other hand, maybe we will learn to go back to analog for truth.
In any case, the need to learn how to be skeptical of any digital content only grow. Separating fake from real is a most needed skill set.
#AI #VASA1 #Deepfake
Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
Technoholic.meMicrosoft introduces VASA-1, an AI framework that animates human headshots to talk and sing. #Microsoft #AI #VASA1
Looking at technologies like VASA-1 from Microsoft i think people and society are not fully prepared for the impact of this technology. Many possibilities for fraud, disinformation and criminal activities. But also i can imagine it will be very tempting in the near future for film studios to fill or alter some dialogue after the actors already have left using AI ?
https://www.microsoft.com/en-us/research/project/vasa-1/?utm_source=www.theaivalley.com&utm_medium=newsletter&utm_campaign=boston-dynamics-new-robot-is-insane
#AI #movies #films #Microsoft #VASA1
https://www.microsoft.com/en-us/research/project/vasa-1/?utm_source=www.theaivalley.com&utm_medium=newsletter&utm_campaign=boston-dynamics-new-robot-is-insane
#AI #movies #films #Microsoft #VASA1
ComputerBaseMicrosoft: VASA-1 erzeugt lebensechte Videos aus einem Bild plus Ton https://www.computerbase.de/2024-04/microsoft-vasa-1-erzeugt-lebensechte-videos-aus-einem-bild-plus-ton/ #VASA1 #Microsoft
