Sure.
Image prompt:
A young woman as a zombie bride in a decayed urban setting with graffiti, in a dark, moody horror style.
Video prompt:
She screams in terror. The scream echoes, full of pain. Camera zooms out and reveals piles of dead bodies in front of her, decomposing
You are viewing a single comment's thread from:
Oh wow.. that means Grok has to be Multimodal since it can generate both images and audios. That’s interesting and thank you for sharing 🙏🏻
Yeah. It also does lip-sync quite well
https://grok.com/imagine/post/aaf1a0d9-a231-4aa6-9e56-fe1203e290b8