[SIGGRAPH 2023] DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance

[@steluste]

That's awesome. It's like metahuman and stable diffusion had a baby

[@myelinsheathxd]

Amazing progress

[@saemranian]

Perfect 👌

[@FrenchDigitalProduction]

Any way get access to test or it is only a student project looking for investor to keep developing?

[@bruhager]

This could revolutionize police identity sketch work.

[@yunankkays3901]

How can i use my face 2d face

[@char_art]

After testing I can say that it's terribly bad.... Quality, accuracy of the shapes compared to the reference, everything is bad. Classic character artists are not about to be laid off ^^ All this development for that... While we really need high-performance retopology or automatic UV tools as a priority.

[@3rdDim3nsn3D]

So far it looks like garbage but i think in a fee years this might be an option or alternative to metahuman or modelling. So far its unusable for Professional Produktion

[@apollovacademy6066]

Well before now it was not possibe so from "nothing" to this is a big jump.

[@jensenraylight8011]

​@@apollovacademy6066 not possible? this is literally FaceGen 2.0.
now modern AAA game will be get even Sh*ttier because everything will be generic,
and developer will avoid any non-standard face rig, which will makes game even more bland.