““But AI will never get good at motion and physics” VideoJAM: hold my beer… *Introduces motion priors, outperforms Runway, Sora & Kling* Oh and works on any video model with minimal tweaks
https://x.com/bilawalsidhu/status/1886874059503452234
“Many creators have custom GPTs and Claude projects to generate and refine prompts for their image & video generation workflows. But what if you could do it all in one blazing fast UI? Krea has answered that question:
https://x.com/bilawalsidhu/status/1884990130903212161
“I’m honestly kind of in awe of how good AI video is getting lately. This is Google Veo 2, and the output is nearly indistinguishable from reality.
https://x.com/bilawalsidhu/status/1886628547550183632
“Been generating impossibly dangerous stunts with veo 2 using text prompts. Still surprising how realistic they can look (though not perfect yet).
https://x.com/emollick/status/1885516907891110244
