Hello everyone. I’d love your opinion on a topic. I’ve been experimenting with facial recognition so
Hello everyone. I’d love your opinion on a topic. I’ve been experimenting with facial recognition softwares like roop, reactor, wav2lip, etc. Something I notice though is that the outputs are almost always significantly lower resolution than the beginning input. I’ve tried several up scalers to mitigate this, including doing frame by frame upscale to no avail. Do any of you know a good upscale tie a method I can try by chance? Thanks!!!
