I already prepared a few source videos from Youtube for a deepfake. When I started extracting I got the error "cannot read meta information" with a few videos. I know the reason, but that's another story.
The main topic here is that I should do the built-in ffmpeg video to png conversion so that I have image source for extracting (instead of a video). But the conversion speed was very slow compared to when I use a 3rd party software for video to img conversion, like "Free Video to JPG Converter". Can I just convert the video into img-frames instead of using the built-in ffmpeg tool without screwing up anything later on in the process?
Use 3rd party software for video to img extraction
Read the FAQs and search the forum before posting a new topic.
This forum is for discussing tips and understanding the process involved for Extracting and preparing face sets for training a model in Faceswap.
If you have found a bug are having issues with the Extraction process not working, then you should post in the Extract Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
Use 3rd party software for video to img extraction
Re: Use 3rd party software for video to img extraction
Yes, you can do it however you want. The built in version is just a convenience tool.
I don't recommend outputting to jpeg though (use pngs).
My word is final