None of these are real.
A new and very successful strategy for realistic video is combining the FLUX.1 image model with a good video model (I've been using Runway Gen-3). And then to top that off you can add Live Portrait into the mix and act out the facial expressions or dialogue to graft onto the video... the tools just keep flying in and getting better every single time.
https://v.nostr.build/BBnoRaa4mIrhVq2y.mp4
https://v.nostr.build/1FOaDHeOByQRQ8M8.mp4
https://v.nostr.build/LiquPKh8s8g5roPT.mp4
As a deaf lip-reader, the uncanny valley in lip movements for speech comprehension is still obvious. But once that gets improved, gg everyone
But you’re right. We are leaps and bounds from where we were a few years ago. Crazy to think we are just getting started!
No replies yet.
