Author Topic: Ai getting better and better  (Read 2474 times)

obsidian

  • Getbig V
  • *****
  • Posts: 8094
Re: Ai getting better and better
« Reply #50 on: October 30, 2025, 01:39:37 PM »
I have made several vids but i dont think Getbig is ready for them yet :D
Getbig is ready! Post it!  ;D

Humble Narcissist

  • Getbig V
  • *****
  • Posts: 33892
Re: Ai getting better and better
« Reply #51 on: Today at 01:16:27 AM »
I have made several vids but i dont think Getbig is ready for them yet :D
We are ready for anything.

obsidian

  • Getbig V
  • *****
  • Posts: 8094
Re: Ai getting better and better
« Reply #52 on: Today at 05:35:44 AM »
Here’s another AI tool: LivePortrait. It lets you drive a source video using a driving video. In this example, I use a 3D animation as the source and drive its head movement, eyes, and mouth with a video of Ashley Judd. Both videos have the same number of frames. The 3D video’s angle isn’t identical by design, so it’s not a perfect match — but it effectively conveys the concept.

Edit: I just noticed the hair shifts slightly due to the AI adjustment. That can be fixed with masking — I’ll check it out later, just out of curiosity..  ;D

https://liveportrait.org/




obsidian

  • Getbig V
  • *****
  • Posts: 8094
Re: Ai getting better and better
« Reply #53 on: Today at 06:07:16 AM »
Duly noted, ai CAN handle rain physics today, it just takes so much longer time

I will show you some good rain physics and bodily interaction soon
Yes, I’ve seen some AI videos that mimic fluid physics quite convincingly. It’s going to get wild once raytracing-level fidelity is integrated into AI generative models.

Kwon

  • Getbig V
  • *****
  • Posts: 53680
  • PRONOUNS: Ze/Zir
Re: Ai getting better and better
« Reply #54 on: Today at 07:08:17 AM »
Here’s another AI tool: LivePortrait. It lets you drive a source video using a driving video. In this example, I use a 3D animation as the source and drive its head movement, eyes, and mouth with a video of Ashley Judd. Both videos have the same number of frames. The 3D video’s angle isn’t identical by design, so it’s not a perfect match — but it effectively conveys the concept.

Edit: I just noticed the hair shifts slightly due to the AI adjustment. That can be fixed with masking — I’ll check it out later, just out of curiosity..  ;D

https://liveportrait.org/





Do a similar one, but with Bhanks or Goodrum instead of Ashley Judd :D
Q