วีดีโอ

0:30 bro they whitewashed obama

That's all cool but how do you do this? What's the site or the app?

This is amazing work. Is the goal to replace the previous techniques? Where you take photos of your face from 3 sides and a generated 3d head with blendshapes will be created. The head attached to a body is the result so that it can be used in games / experiences. Do you think that will be a possibility? Will blendshapes be possible with this technique?

Hey. Read that you were able to achieve over 200fps in some cases, this being on one a100 gpu. Would multiple gpus make a difference in the speed? It's plenty fast right now for real time generation for low quality images, but it still hits a limit at let's say 1024 by 1024.

This sounds very promising! <3 I'm an artist playing around with LivePortrait at the moment and while I'm loving the results I am very aware of the limitations, and your method looks even more powerful, congrats! Any idea when we'll be able to try out your tech?

it's what i'm searching for to reconstruct face of deceased relatives which we need on gravestone, there's a problem when only one photo from person saved which can be damaged/bad/one sided, the problem will be global and worse because of mass decay of digital media by time, i mentioned example with physical photo sample, really don't know what people could save in future about their relatives looking

you should check out Deferred Diffusion for High-fidelity 3D Head Avatars it would be amazing to see the comparison

i want dataset. how to download that dataset, can u help me?

when will you release the code?

Any update on the source code?

When will the source code released

hi can u share D3GA code or links to provide it ?? and thank u

Where can we find source code please

I showed this to my cat. Now he thinks he's the star of the show

Can anyone successfully run the code provided on github?

Will you release the code

So how do I get my face into this system? Just download the code and upload my picture then wait? Also, how can I get it to speak my recorded voiceovers?

Where can I get this software?

Hi, I'm very interested by your solution for a theater company show. Is this possible to get your code or soft somewhere ? Thanks in advance. Camille COTINEAU

Brilliant! Just brilliant. Great work as always, Thies

4:33 can you generalize the mouth position but be Person-specific in expressions? it seems in your method after generalizing, A.I. fear to open mouth enough. it average mouth movements and delete expression and feelings. because every person may have specific feeling in words that others don't have... person specific had better expression but it jitters in the mouth section a lot.

Code?

is it on github codes ?? thanks

this is literally the definition of putting words in my mouth lol. keep it up!

umm, this is history right here guys. just letting you know lmao.

Pl tell how to approach u