4 ms·
I've been using ffmpeg's xgrid filter (similar to hstack and vstack, but allows for arbitrary grids) to produce virtual choir videos for my church choir during
by caryme 6y ago
I've been using ffmpeg's xgrid filter (similar to hstack and vstack, but allows for arbitrary grids) to produce virtual choir videos for my church choir during covid. Here's an example: https://www.youtube.com/watch?v=Oeg9w8X6hrA https://www.youtube.com/watch?v=Oeg9w8X6hrA.
A lot of people are producing virtual choir videos right now, but I suspect few use a process similar to mine. I use Audacity to edit the audio separately, then crop the input videos using a face-aware cropping script (which uses https://github.com/ageitgey/face_recognition https://github.com/ageitgey/face_recognition), then generate a video grid using ffmpeg + xgrid.
- iamstef 6y agoI would be interested in seeing your script if you don’t mind sharing
- caryme 6y agoSure! Here's the face-aware crop script (somewhat quick and dirty - I haven't moved the output dimensions to CLI arguments yet): https://gist.github.com/carylee/62dbe19579ed9fa1714a3635ff0bdec7 https://gist.github.com/carylee/62dbe19579ed9fa1714a3635ff0b... Here's an example script for stitching the output video: https://gist.github.com/carylee/a13ae1a1ecb2f81c6536476f6dfbe895 https://gist.github.com/carylee/a13ae1a1ecb2f81c6536476f6dfb... And here's the resulting video (text was added later by a different editor): https://www.youtube.com/watch?v=f7Pm4nLPslY https://www.youtube.com/watch?v=f7Pm4nLPslY
- iamstef 6y agoNice, this was super timely as I was literally building the same thing. And I had just reached the part where I was annoyed that all the submitted videos had different shapes and sizes which as you know would be tedious to correct manually. You for sure saved me some time!