MotionTracker VS mediapipe

Source Code For Motion Tracker: https://github.com/JackhammerYT/MotionTracker :)

Today, we announce MediaPipe diffusion plugins, which enable controllable text-to-image generation to be run on-device. Expanding upon our prior work on GPU inference for on-device large generative models, we introduce new low-cost solutions for controllable text-to-image generation that can be plugged into existing diffusion models and their Low-Rank Adaptation (LoRA) variants.

You can just grab the TFLite version! https://github.com/google/mediapipe/blob/master/docs/solutions/models.md

I was going to say that I like the MediaPipe Selfie Segmentation model for doing this sort of thing in a web page, but I've just noticed (when getting the GitHub link[1]) that Google have marked the code as legacy[2] ... no idea if the new solution is better/easier to use[3].

For what it's worth, my CodePen using the old model is here: https://codepen.io/kaliedarik/pen/PopBxBM

[1] - https://github.com/google/mediapipe/blob/master/docs/solutio...

[2] - "Attention: Thank you for your interest in MediaPipe Solutions. As of April 4, 2023, this solution was upgraded to a new MediaPipe Solution."

[3] - https://developers.google.com/mediapipe/solutions/vision/ima...

I found MediaPipe's Face Mesh and was impressed with how simple it was to get going, but it just gives you the landmark points and I've not gone any further yet.

We've trained ControlNet on a subset of the LAION-Face dataset using modified output from MediaPipe's face mesh annotator to provide a new level of control when generating images of faces.

Medipaipe library link: https://mediapipe.dev/

If you're looking for the differences in terms of how inference is done, I recommend you take a look at MediaPipe's source code. MediaPipe doesn't use raw code, but uses a "graph" instead (eg. pose_landmark_cpu.pbtxt), which can be visualised using MediaPipe Viz. I also used axinc-ai/ailia-models as the base (preprocessing, inference, postprocessing, etc...) which I further built upon (keypoint refinement, roi from keypoints, filtering / smoothing, etc...)

I thought of doing that but unfortunately medipipe requires a RGB input and performs better with it more on that here