ControlNet model based on MediaPipe

Prototype ControlNet model based on MediaPipe detections with the idea to base not only on pose but also the hand placement.

At this point, pose estimation works very well, hands are still underdeveloped.

Integration with Automatic1111's Web GUI is planned but for now you must use external preprocessor (python script).

Usage:
1. Install requirements - run pip install -r requirements.txt command (in folder where you have downloaded file)
2. Prepare folder with images that you want to preprocess
3. Run command python preprocess.py -mh -mp -s C:\path\to\your\folder - mh is for hands detection, mp for pose (you can try with just the pose which works great!)
4. Inside selected folder will appear detection folder (C:\path\to\your\folder\detection)
5. Download model/models from https://civitai.com/models/16409/pototype-controlnet-models-based-on-mediapipe
6. Copy downloaded models (.ckpt files) to ...\stable-diffusion-webui\extensions\sd-webui-controlnet\models - higger "e" numer is better estimation but also greater impact on image
7. Inside Automatic1111 GUI select ControlNet enabled, preprocessor to None, one of the downloaded models and put image from earlier detection
8. Generate!