How to combine pictures into video?
Please tell me how to combine pictures into video?
The place to discuss Faceswap and Deepfakes
https://forum.faceswap.dev/
Please tell me how to combine pictures into video?
The easiest way will be to use the "FFmpeg" writer in the Convert tab. But you can also use the Effmpeg tab in Tools if you have images already done. If you want to do it outside of FaceSwap you can use ffmpeg such as from here: http://hamelot.io/visualization/using-f ... o-a-video/ or any number of other tools.
Thanks so much!
Hello, I follow the guide for using faceswap until the "Converting video" part (https://github.com/deepfakes/faceswap/b ... ng-a-video). I have now my folder with swaped faces (only faces not the entire image with swaped faces). Now I need to put these swaped faces in the original video but I can't find the steps of how to proceed in the tutorial.
It seems that I have to use the Effmpeg convert tool but I don't find the rights settings, can someone show me the settings in GUI ?
You don't want to swap the "faces" at the convert stage..... You need to swap the faces in the frames....
For converting:
Select the video that you want to swap the faces onto as your "input"
Select a location for output.
Select "ffmpeg" as writer.
This will swap the faces straight onto the video.
Hum I don't really understand your answer, my video only has 1 person face and I want to replace it with an another person face from a trained model.
I have already trained my model. So now I have :
1) my extracted/sorted faces A from divers data videos / images
2) my extracted/sorted faces B from divers data videos / images
2) my trained model from A to B
3) my converted faces from A with my model (so I have a set of mix faces from A to B)
4) ???
I suppose the 4 is putting these faces in the original video ? But I can't find the settings. Or did I do something wrong ?
3) my converted faces from A with my model (so I have a set of mix faces from A to B)
This is wrong. You should not have converted faces.
You convert THE VIDEO, not THE FACES.
You convert THE VIDEO, not THE FACES.
Alright thanks ! I can see clearer now.
Select the video that you want to swap the faces onto as your "input"
Select a location for output.
Select "ffmpeg" as writer.
You just have to also add the Model Dir
Exactly