lzanardos9's picture
Upload 16 files
45132f0 verified
|
Raw
History Blame Contribute Delete
2.07 kB
---
title: GravityLLM Studio
emoji: 🌌
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.8.0
python_version: "3.10"
app_file: app.py
fullWidth: true
header: default
suggested_hardware: cpu-basic
short_description: Spatial9 immersive scene generation with branded GravityLLM UI, schema validation, and spatial preview.
tags:
- gravityllm
- spatial-audio
- immersive-audio
- spatial9
- iamf
- gradio
- json
- demo
- music-tech
---
![GravityLLM banner](assets/gravityllm_space_banner.png)
# GravityLLM Studio
A branded Hugging Face Space for **constraint-conditioned immersive scene generation**.
This Space accepts a **music-constraint payload** and returns a **Spatial9Scene JSON** scene. It includes:
- a polished GravityLLM studio UI
- your Spatial9 logo in the hero section
- remote inference through Hugging Face `InferenceClient`
- optional JSON-schema grammar constraints
- built-in validation against `schemas/scene.schema.json`
- a live top-down spatial preview
- a deterministic fallback rules engine so the demo still works before the trained model is online
## How to connect your model
Set the following Space secrets or variables:
- `GRAVITYLLM_MODEL_ID` β†’ your model repo id, for example `your-org/GravityLLM-AutoPosition`
- `HF_TOKEN` β†’ only required if the model is gated or private
- `GRAVITYLLM_BACKEND` β†’ optional default: `hybrid`, `remote-model`, or `rules-engine demo`
## Files
- `app.py` β€” the Gradio app
- `schemas/scene.schema.json` β€” the contract used for validation and optional grammar guidance
- `examples/` β€” ready-to-run sample payloads
- `assets/` β€” logo and banner assets
- `utils/scene_tools.py` β€” validation, heuristics, JSON extraction, plotting
## Recommended workflow
1. Upload your GravityLLM **Model repo**
2. Train and push the final weights
3. Upload this **Space repo**
4. Set `GRAVITYLLM_MODEL_ID`
5. Launch the Space
## Notes
This Space is designed to be usable in two states:
- **before model launch** β†’ rules-engine fallback
- **after model launch** β†’ remote GravityLLM inference