Ala Sokolova

Hi, can SadTalker be applied for for face reenactment with no audio? To make one head (defined by src image) move as another one (defined by driver video sequence without...

Hi, may SadTalker be used just for face reenactment without any audio? Just for generation of talking head with appearance from source frame and motion from driver video (with no...

Hey, thank you for your amazing work! You write in the paper that Rave is adaptable to various pre-trained models including inpainting. How it can be done? Can I just...

Fine-tuning on a new subject

1

Hi, have you tried to fine-tune your pretrained model on a new subject? How much data is needed for this and how long does it take to fine-tune the model...

Distinguish face appearance and pose

1

Hey, can i somehow distinguish the appearance and the facial pose of the person? (get landmarks from input video, but the face itself from another source, so that it would...

Pose driven inference

4

Hi, how can i infer based on just pose, without audio at all (like face reenactment task)? Using all the landmarks, including mouth.

Transforms and Vocoder ralation

6

Hey, I am trying to run msanii for inpainting task on my data, and facing the issue that the result are extremely noisy. I noticed that even if I don't...

combining with neck and body

1

Hey, is it possible to add neck/torso/body to the trained dejavu model? So that it doesn't look like just floating head?

Headless avatar driving

4

Hey, thanks for amazing work, it really looks impressive! Do you have a script for driving the trained avatar not by webcam input, but by predefined sequence of landmarks or...