Microsoft VASA brings static images to life

submitted by ZephirAWT from venturebeat.com

all 5 comments
sorted by:
top
newinsightfulfun

[–]ZephirAWT[S] 1 insightful - 1 fun1 insightful - 0 fun2 insightful - 1 fun -  (0 children)

Microsoft VASA brings static images to life about study VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time

The research arm of the Satya Nadella-led company presented VASA-1, an AI framework that can convert human headshots into talking and singing videos.

It takes a single portrait photo and speech audio and produces a hyper-realistic talking face video with precise lip-audio sync, lifelike facial behavior, and naturalistic head movements generated in real-time.

[–]ZephirAWT[S] 1 insightful - 1 fun1 insightful - 0 fun2 insightful - 1 fun -  (0 children)

Windows 11 Must Be Stopped - A Veteran PC Repair Shop Owner's Dire Warning

The requirements for Windows 11 include UEFI, Secure Boot, and a Trusted Platform Module (TPM). This is how Microsoft will make every piece of computing hardware submit to their whims within the next decade. Do you own your computer or not?

[–]ZephirAWT[S] 1 insightful - 1 fun1 insightful - 0 fun2 insightful - 1 fun -  (0 children)

This Realtime AI Deepfake Tool has gone too far

[–]ZephirAWT[S] 1 insightful - 1 fun1 insightful - 0 fun2 insightful - 1 fun -  (0 children)

New AI music generator Udio synthesizes realistic music on demand Although the Udio team has not revealed the specific details of its model or training data (which is likely filled with copyrighted material), it told Tom's Guide that the system has built-in measures to identify and block tracks that too closely resemble the work of specific artists, ensuring that the generated music remains original.

Did AI Just End Music? (Now it’s Personal)

[–]ZephirAWT[S] 1 insightful - 1 fun1 insightful - 0 fun2 insightful - 1 fun -  (0 children)

Stable Diffusion SDXL Turbo's real time image generation