Thank you for your review. The .pth model file is included in the .zip file, so we don't need to download it separately. However, for greater transparency, the .pth file has been uploaded separately. (I added an explanation of .pth files to the GitHub release page.)
First, in VaM, under User Preferences > Security, please check that "Allow Plugins Network Access" is checked. Second try changing the port:
1. Edit target_ip.csv in the engine folder and change it to: 127.0.0.1:8742
2. Change 9998 to 8742 in the Plugin settings.
This engine is a standalone version and does not have any integration features. Due to the unexpectedly high number of downloads, i may release a version with integration capabilities.
grimes_AIVRLab submitted a new resource:
AI-Driven Skeleton Engine (BoneReceiver) - CVAE Machine Learning engine to drive VaM skeleton animations in real-time.
Read more about this resource...
This is an experimental project to drive Virt-A-Mate (VaM) skeleton animations using a Python-based CVAE Machine Learning engine.
[ Quick Start Guide ]
1. Download the ML Skeleton Engine (Python)
[ https://github.com/yuyaslabo/VaM_ML_Skeleton_Engine ] (Open "Releases")
2. Unzip the file and...
Hello Creators,
I’m excited to share a project I’ve been working on: a real-time skeleton-driving framework for VaM using a Variational Autoencoder (VAE).
Unlike traditional timeline animations or recorded loops, this system generates per-bone pose data in real-time based on the emotional...