Any way to convert not using a model but with provided faces?

Got questions or tips about the Conversion process? This is the place to discuss them.


Forum rules

Read the FAQs and search the forum before posting a new topic.

This forum is for discussing tips and understanding the process involved with Converting faces from your trained model.

If you are having issues with the Convert process not working as you would expect, then you should post in the Convert Support forum.

Please mark any answers that fixed your problems so others can find the solutions.

Locked
User avatar
ConcernedNoob
Posts: 1
Joined: Fri Aug 07, 2020 4:11 pm

Any way to convert not using a model but with provided faces?

Post by ConcernedNoob »

I was thinking of using the First Order Motion Model by Aliaksandr Siarohin with the Vox checkpoint to animate an image but it requires cropping the target video to be roughly centered on the face. Manually doing that seems like a pain for anything with varying camera angles so it would be really convenient if I could use FaceSwap to generate the cropped faces and just feed that in. Is there some way I can use the alignment file to then just take the swapped faces generated by the First Order Motion Model and swap them back into the target video?

by bryanlyon » Fri Aug 07, 2020 6:15 pm

No, we don't provide any way to restore aligned faces back to the video except when going through a convert. But our source is available and you can add that functionality if you wish.

Go to full post
User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Any way to convert not using a model but with provided faces?

Post by bryanlyon »

No, we don't provide any way to restore aligned faces back to the video except when going through a convert. But our source is available and you can add that functionality if you wish.

Locked