jpmschweitzerandClaude Opus 4.6
bc1574b36e
- Stable Audio Open: AI audio generation on port 11500 (~6GB VRAM) - TRELLIS: 3D model generation on port 11510 (~6-8GB VRAM, low-VRAM fork) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
91 lines
3.1 KiB
YAML
91 lines
3.1 KiB
YAML
version: '3.8'
|
|
|
|
# Stable Audio Open - AI Audio Generation
|
|
# Phase: ML Infrastructure
|
|
# Ports: 8000 (Gradio Web UI)
|
|
# GPU: YES - Requires NVIDIA Container Toolkit (8GB+ VRAM)
|
|
# Storage: SSD recommended for model cache
|
|
# Image: Built locally from https://github.com/SaladTechnologies/stable-audio-open
|
|
|
|
services:
|
|
stable-audio:
|
|
image: stable-audio-open:local
|
|
container_name: stable-audio
|
|
restart: unless-stopped
|
|
ports:
|
|
- "11500:8000" # Gradio Web UI (internal only)
|
|
volumes:
|
|
# HuggingFace cache for model weights (~6GB)
|
|
- /home/jpmschweitzer/docker-data/stable-audio/hf-cache:/root/.cache/huggingface
|
|
environment:
|
|
- TZ=Europe/Amsterdam
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- NVIDIA_DRIVER_CAPABILITIES=compute,utility
|
|
- HF_TOKEN=${HF_TOKEN}
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "curl -fSs http://localhost:8000/ || exit 1"]
|
|
interval: 60s
|
|
timeout: 30s
|
|
retries: 3
|
|
start_period: 300s # Model download + load takes time
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 16G
|
|
reservations:
|
|
memory: 8G
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
networks:
|
|
- docker-dataplane
|
|
|
|
networks:
|
|
docker-dataplane:
|
|
external: true
|
|
name: docker-dataplane
|
|
|
|
# GPU Requirements:
|
|
# - RTX 2080 Ti (11GB VRAM) - minimum viable, may struggle with long generations
|
|
# - Recommended: 16GB+ VRAM for reliable 47s audio generation
|
|
# - NVIDIA Container Toolkit must be installed
|
|
#
|
|
# IMPORTANT: GPU Contention
|
|
# - This service shares GPU with Ollama and Jellyfin
|
|
# - Consider stopping Ollama when generating audio for better VRAM availability
|
|
# - Monitor with: watch -n 1 nvidia-smi
|
|
#
|
|
# Prerequisites:
|
|
# 1. Build image: cd /home/jpmschweitzer/docker-data/stable-audio-open && docker build -t stable-audio-open:local .
|
|
# 2. Create HuggingFace token: https://huggingface.co/settings/tokens (read access)
|
|
# 3. Accept model license: https://huggingface.co/stabilityai/stable-audio-open-1.0
|
|
# 4. Create data directories:
|
|
# mkdir -p /home/jpmschweitzer/docker-data/stable-audio/{hf-cache,output}
|
|
#
|
|
# After Deployment:
|
|
# 1. Set HF_TOKEN in Portainer environment variables
|
|
# 2. Deploy stack via Portainer
|
|
# 3. First run downloads model weights (~6GB) - be patient
|
|
# 4. Verify GPU access: docker exec stable-audio nvidia-smi
|
|
# 5. Access Web UI: http://tower-of-joy:11500 or http://audio.schweitz.internal (via NPM)
|
|
#
|
|
# NPM Configuration (audio.schweitz.internal):
|
|
# - Domain: audio.schweitz.internal
|
|
# - Scheme: http
|
|
# - Forward Hostname: stable-audio (or tower-of-joy)
|
|
# - Forward Port: 11500
|
|
# - Block Common Exploits: Yes
|
|
# - Websockets Support: Yes (required for Gradio)
|
|
#
|
|
# API Usage (Gradio API):
|
|
# curl -X POST http://audio.schweitz.internal/api/predict \
|
|
# -H "Content-Type: application/json" \
|
|
# -d '{"data": ["epic orchestral music, cinematic", 30, 100, 7]}'
|
|
# Parameters: [prompt, duration_seconds, diffusion_steps, cfg_scale]
|
|
#
|
|
# Rebuilding Image:
|
|
# cd /home/jpmschweitzer/docker-data/stable-audio-open
|
|
# git pull
|
|
# docker build -t stable-audio-open:local .
|