Chris Remington@beehaw.orgM to Technology@beehaw.org · 9 months agoMicrosoft’s VASA-1 can deepfake a person with one photo and one audio trackarstechnica.comexternal-linkmessage-square32fedilinkarrow-up16arrow-down10cross-posted to: technology@lemmy.worldartificial_intel@lemmy.mltechnology@lemmy.ziptechnology@lemmy.ml
arrow-up16arrow-down1external-linkMicrosoft’s VASA-1 can deepfake a person with one photo and one audio trackarstechnica.comChris Remington@beehaw.orgM to Technology@beehaw.org · 9 months agomessage-square32fedilinkcross-posted to: technology@lemmy.worldartificial_intel@lemmy.mltechnology@lemmy.ziptechnology@lemmy.ml
minus-squareP03 Locke@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up4·9 months agoSigh, not this article again. No, they can’t “deepfake a person with one photo”. They can create a bad uncanny-valley 75% accurate version of one.
minus-squarethingsiplay@beehaw.orglinkfedilinkarrow-up5·9 months ago a bad uncanny-valley 75% accurate version of one Actually a perfect description of what a deepfake is.
Sigh, not this article again. No, they can’t “deepfake a person with one photo”. They can create a bad uncanny-valley 75% accurate version of one.
Actually a perfect description of what a deepfake is.