Rich

Instead of using the Mediapipe Camera tools, use your own html video element and call the predict function on every frame. ``` video.requestVideoFrameCallback(async()=>{ await holistic.send({ image: video }); ); ```

Sorry for the super delayed response. I have yet to check this. I may have misread the facemesh point map that TFJS provided.

Hi! Please refer to the [pixi-live2d-display](https://github.com/guansss/pixi-live2d-display) library for any questions about how to work with Live2D models on the web. Other live2D models can be loaded by [URL](https://github.com/guansss/pixi-live2d-display#basic). You will...

This is sometime I'm actively exploring as well so I don't really have a solution for this. Maybe you can ask the Tensorflow JS/Mediapipe community since most of the processing...

Unfortunately, that is outside the scope of this repo, which only handles the calculations from ML results. If you have any rendering questions, please ask the owners of pixijs or...

This seems like an incompatibility of Mediapipe on your device specifically. I am unable to reproduce that error on MacOS. You could also try other browsers like Edge or Firefox...

That repo can be run using a local server like http-server. It's a static site

@Bersaelor Unfortunately, the 3D mesh only gives normalized coordinates. So when constructing a mask using those landmarks, there really isn't any Z space being applied as it is just the...