cebstudios
patreon
Audio2face + Deeplabcut in blender Test
🕑 Added 2021-06-10 08:09:41 +0000 UTCHere is a test done in Blender joining audio2face and deeplabcut.
The first loop is only with audio2face, and the second loop is audio2face + deeplabcut.
This test was done in less than 1h, so you can see that when deeplabcut enters, it get very distorted. Its because I still have to fix the amount of movement and the weightpaint.
This will be lots of work, maybe in some weeks we will have more stable version to show.
Comments
It looks very interesting. But from what i saw, it is aimed for full body.. My problem here is the lack of knowledge on weight painting and face rigging. I think there is no other way, we have to study it... Because, after this initial stage of setting up the face with weight paint and skeleton, we will have to see a way to transfer the information to another model. This way, we make a sample head, and creat a button to transfer it, like audio2face does. This is going to be a long time work, for sure. Thanks a lot for the tip
Maybe you could try rigNet, there an implémentation of the code for Blender, but not sure it could work with facial features. https://zhan-xu.github.io/rig-net/ https://www.youtube.com/watch?v=ueLlS3IoeGY&ab_channel=BallsAndNinjas
