GameCult/Vili
Watch
9
0
Fork
You've already forked Vili
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
Vili/README.md
Meta Vens e36fe0a7a8 Document Raven Hugging Face access
2026-06-12 14:05:12 +01:00

1.5 KiB
Raw Blame History

Vili

Vili is the GameCult Persona animation daemon.

It owns the bridge from Persona performance intent to body-motion generation. Its first backend is Kimodo on Raven, running through Docker Engine inside Ubuntu-24.04 WSL with NVIDIA GPU passthrough.

Authority

  • Vili owns animation job intake, Kimodo runtime checks, generated motion artifact references, and its operator/provider surface.
  • Personas and Weksa may propose performance intent, gesture prompts, and constraints.
  • Kimodo owns motion synthesis.
  • Future renderers own retargeting, playback, facial performance, camera, and lip sync.
  • Odin discovers Vili; Odin does not own Vili's state.
  • Idunn keeps Vili alive; Idunn does not own animation decisions.

Local Runtime

On Raven:

E:\Projects\Vili\scripts\restart-vili-daemon.cmd

Default compatibility endpoint:

http://10.77.0.4:8824

Important routes:

  • GET /health
  • GET /provider-advertisement
  • GET /operator-state
  • GET /eve/operator
  • GET /eve/deck/providers
  • WS /eve/deck/vili.animation
  • GET /smoke
  • POST /motion/generate

Current Runtime State

Raven has a Hugging Face token installed at /root/.cache/huggingface/token inside Ubuntu-24.04. Vili mounts that token read-only into Kimodo containers and passes the standard Hugging Face token environment variables.

Verified on 2026-06-12: the Kimodo container can read gated metadata for meta-llama/Meta-Llama-3-8B-Instruct. Full motion generation may still need a first-run model download/cache warmup.