version: '3.8'

# TRELLIS 1 - 3D Model Generation (Low-VRAM Fork)
# Purpose: Generate 3D meshes with UV mappings for game asset pipeline
# Ports: 11510 (Gradio Web UI)
# GPU: YES - Optimized for 11GB VRAM (RTX 2080 Ti)
# Storage: SSD for model cache, HDD for GLB outputs
# Image: Built locally from /home/jpmschweitzer/docker-data/trellis/

services:
  trellis:
    image: trellis:local
    container_name: trellis
    restart: unless-stopped
    ports:
      - "11510:7860"  # Gradio Web UI
    volumes:
      # SSD: HuggingFace model cache (~5GB)
      - /home/jpmschweitzer/docker-data/trellis/hf-cache:/root/.cache/huggingface
      # HDD: Generated GLB files
      - /mnt/media/trellis/outputs:/app/outputs
      # Entrypoint script (patches Gradio bugs without rebuilding image)
      - /home/jpmschweitzer/docker-data/trellis/entrypoint.sh:/app/entrypoint.sh:ro
    command: ["bash", "/app/entrypoint.sh"]
    environment:
      - TZ=Europe/Amsterdam
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      # VRAM Optimization (for 11GB card)
      - ATTN_BACKEND=xformers
      - SPCONV_ALGO=native
      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
      # Gradio must bind to 0.0.0.0 inside Docker
      - GRADIO_SERVER_NAME=0.0.0.0
      # HuggingFace token for model downloads (set in Portainer)
      - HF_TOKEN=${HF_TOKEN:-}
    healthcheck:
      test: ["CMD-SHELL", "curl -fSs http://localhost:7860/ || exit 1"]
      interval: 60s
      timeout: 30s
      retries: 3
      start_period: 300s  # Model download + load time
    memswap_limit: 20G
    deploy:
      resources:
        limits:
          memory: 20G
        reservations:
          memory: 4G
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    labels:
      - "com.centurylinklabs.watchtower.enable=false"  # Manual updates for local builds
    networks:
      - docker-dataplane

networks:
  docker-dataplane:
    external: true
    name: docker-dataplane

# =============================================================================
# PREREQUISITES
# =============================================================================
#
# 1. Build the Docker image first:
#    cd /home/jpmschweitzer/docker-data/trellis
#    docker build -t trellis:local .
#    (Takes ~20-30 minutes for CUDA compilation)
#
# 2. Directories are already created:
#    /home/jpmschweitzer/docker-data/trellis/hf-cache (SSD - model cache)
#    /mnt/media/trellis/outputs (HDD - generated GLB files)
#
# =============================================================================
# AFTER DEPLOYMENT
# =============================================================================
#
# 1. Verify GPU access:
#    docker exec trellis nvidia-smi
#
# 2. Check logs:
#    docker logs trellis
#
# 3. Access Web UI:
#    http://tower-of-joy:11510
#    http://192.168.86.149:11510
#
# 4. Monitor VRAM during generation:
#    watch -n 1 nvidia-smi
#
# =============================================================================
# USAGE - GAME ASSET PIPELINE
# =============================================================================
#
# 1. Open Gradio UI at http://tower-of-joy:11510
# 2. Upload reference image or enter text prompt
# 3. Generate 3D model (uses 6-8GB VRAM)
# 4. Download GLB file from outputs
# 5. Import GLB into Blender (File > Import > glTF)
# 6. Apply custom textures, set up isometric camera
# 7. Render at 1024x1024, downsample to 64x64 tile sprites
#
# =============================================================================
# GPU CONTENTION NOTE
# =============================================================================
#
# TRELLIS shares the RTX 2080 Ti with Ollama and Jellyfin.
# For best results during complex generations:
#   docker stop ollama
#   # Run TRELLIS generation
#   docker start ollama
#
# =============================================================================