ali-vilab/dreamtalk

How do I use 512 X 512

Opened this issue · 0 comments

I don't understand the readme on this.It states

The second option is to employ the Temporal Super-Resolution Model from MetaPortrait, which attains a resolution of
, offers a faster performance of 10 frames per second, and maintains temporal coherence. However, these super-resolution modules may reduce the intensity of facial emotions.

Do I use that to create a 515 X 512 then process in dreamtalk ? What options do I use ?