catculation@lemmy.zip to Technology@lemmy.worldEnglish · edit-211 个月前OpenAI introduces Sora, its text-to-video AI modelwww.theverge.comexternal-linkmessage-square142fedilinkarrow-up1450arrow-down121file-text
arrow-up1429arrow-down1external-linkOpenAI introduces Sora, its text-to-video AI modelwww.theverge.comcatculation@lemmy.zip to Technology@lemmy.worldEnglish · edit-211 个月前message-square142fedilinkfile-text
minus-squarearchomrade [he/him]@midwest.sociallinkfedilinkEnglisharrow-up9·11 个月前For the limitations visual AI tends to have, this is still better than what I’ve seen. Objects and subjects seem pretty stable from Frame to Frame, even if those objects are quite nightmarish I think “will Smith eating spaghetti” was only like a year ago
For the limitations visual AI tends to have, this is still better than what I’ve seen. Objects and subjects seem pretty stable from Frame to Frame, even if those objects are quite nightmarish
I think “will Smith eating spaghetti” was only like a year ago