It was posted to hacker news as well within the last day.

https://news.ycombinator.com/item?id=41463726

Examples are very impressive, here's hoping we get an implementation of it on huggingface soon so we can try it out, and even potentially self-host it later.

No, not related. We just took some of Loopy's demo images + audios since they came out 2 days ago and people were aware of them. We want to do an explicit side-by-side at some point, but in the meantime people can make their own comparisons, i.e. compare how the two models perform on the same inputs.

Loopy is a Unet-based diffusion model, ours is a diffusion transformer. This is our own custom foundation model we've trained.

This took me a minute - your output demos are your own, but you included some of their inputs, to make for an easy comparison? Definitely thought you copied their outputs at first and was baffled.

Exactly. Most talking avatar papers re-use each others images + audios in their demo clips. It's just a thing everyone does... we never thought that people would think it means we didn't train our own model!

For whoever wants to, folks can re-make all the videos themselves with our model by extracting the 1st frame and audio.

Yes, exactly! We just wanted to make it easy to compare. We also used some inputs from other famous research papers for comparison (EMO and VASA). But all videos we show on our website/blog are our own. We don't host videos from any other model on our website.

Also, Loopy is not available yet (they just published the research paper). But you can try our model today, and see if it lives up to the examples : )

So, you're saying you took Loopy's work and tried to pass it off as your own, "because people were aware of it" ?

No

Holy shit loopy is good, i imagine another closed model, opensource never gets good shit like that :(

Either this is the commercialization of the work of that project, by authors or collaborators,

or it is appears to be a straight up grift, wrapping someone else's work with a SPA website.

I don't see other possibilities.

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.

These papers are simply using each other's examples to make performance comparisons possible.

This is EMO from 6 months ago: https://humanaigc.github.io/emote-portrait-alive/

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.

Not seeing other possibilities isn't great though, right? Clearly there are other possibilities.