I recorded some footage of an actress talking straight to camera, and wanted to track the facial data and apply it to a photo, a still photo, to simulate talking.
is that possible with mocha pro? would it be a helpful tool?
I can’t find a similar tutorial, but would love a few tips. I used the power mesh tool to track the face but can’t quite figure out how to apply it to a still image.
Similar to the “Mug Life” app on the App store, I’d just like more customization.
Without seeing the exact setup here, the key thing would be to make sure you have a split for the mouth and eyes otherwise using another spline or it’s just going to look like a latex mask.
Generally, you want the still and the first position of your mesh to be aligned. Start with a closed or slightly open mouth and make sure the still image matches in terms of head tilt etc otherwise it will look weird. You can scale the surface to get a general position then use Grid Warp to match the rest.
Just keep in mind if you use a still, it will only be warping from that angle of the image. If the person tilts their head, it may look strange.
You can see an example here from artist CM de La VEGA: How to Face Swap with Mocha Pro Power Mesh - YouTube