A collected overview on resources of different kinds, most interestingly free and open source software for experimenting.

• https://github.com/suno-ai/bark#-installation
  • Bark is a GPT-style model. As such, it may take some creative liberties in its generations, resulting in higher-variance model outputs than traditional text-to-speech approaches. Would be interesting to have this useable at the campus — Rainer M. Engel 2024/01/05 13:39
• https://github.com/neonbjb/tortoise-tts
• https://github.com/espeak-ng/espeak-ng?referral=top-free-text-to-speech-tools-apis-and-open-source-models

General tutorial regarding “Piper”: https://www.youtube.com/watch?v=b_we_jma220

Here the best case would be a complete AOV-Rendering like decribed in the Arnold Support Corner, which is not working properly even in Maya 2024 due to some exr-issues. Then using an updated script and use presets to get the wanted AOV-Output plus the desired denoising also for basic light-group AOVs and not “only” for the RGBA (Beauty).
The second best, but still good Option, maybe temporaly not that stable in comparison, is to use OIDN or Optix as aiImager Post-Effect for the desired Maya version.

• https://github.com/ChristopheMoreau/FiNE/tree/v3.33 (deprecated, but still interesting)
• https://github.com/DeclanRussell/IntelOIDenoiser (Intel Open Image Denoiser command line tool)

As it seems, there are no solid open source or freely available tools for this, that are working in regards of a non-destructive workflow. The best thing to watch is NukeCGDenoiser, but which throws an error at dll-loading — Rainer M. Engel 2024/01/15 11:31