Starstruk Logo MarkStarstruk

v2.0

NVIDIA/Audio2Face-3D-Samplesv2.0Mar 11, 2026by agmohare

AI Summary

This release updates the Audio2Face-3D sample client to version 2.0, introducing new diffusion model configurations, updated regression models, and a redesigned config structure. It also adds specific blendshape capabilities to enhance facial animation.

Key Highlights

  • Add configs for diffusion models
  • Update regression models to v2.3.1 (Claire & James)
  • Add 17 tongue blendshapes
  • Update config structure

New Features

  • Diffusion model configuration support
  • 17 new tongue blendshapes

Full Release Notes

Update configs for Audio2Face-3D v2.0 sample client

- Add configs for diffusion models
- Update regression models to v2.3.1 (Claire & James)
- Add 17 tongue blendshapes
- Update config structure