We are not related to Loopy Avatar. We trained our own models. It's a coincidence that they launched yesterday.
In the AI/research community, people often try to use the same examples so that it's easier to compare performance across different models.
You should watch out for Hedra and Sync. Plus a bunch of Loopy activity on Discord.
Not seeing other possibilities isn't great though, right? Clearly there are other possibilities.
I know these guys in real life, they've been working on this for months and, unlike the ByteDance paper, have actually shipped something you can try yourself.