# ComfyUI — node-based Stable Diffusion / Flux inference UI.
#
# Runs on irv-ml1 (dual GPU: RTX 3090 + RTX A6000). PINNED to the A6000
# (device 1) via NVIDIA_VISIBLE_DEVICES=1 — the 3090 hosts the audio/TTS
# zoo (chatterbox, parakeet, vibevoice, ytvc, kokoro) so ComfyUI gets the
# full 48 GB A6000 to itself (operator consolidation 2026-06-18).
#
# All user state — models, workflows, custom_nodes, input, output —
# lives under a single BASE_DIRECTORY tree on /worktank (462 GB
# dedicated), owned by lkraven:lkraven (1000:1000) so external
# tooling can read and write workflow files directly on the host.
#
# Runtime state (ComfyUI source, venv, pip cache) lives in a bind
# mount at ${COMFYUI_RUNDIR} — disposable (can be wiped on version
# bumps to force re-bootstrap), but owned by the host user so no
# sudo dance is needed. (Named volumes would be created root-owned
# and the image refuses to chown a mounted path.)
#
# First-run prerequisite: both ${COMFYUI_BASEDIR} and ${COMFYUI_RUNDIR}
# must exist on the host with ownership matching COMFYUI_UID:COMFYUI_GID
# before `up`. See README for the bootstrap command.
#
# All tunables live in .env — edit that, not this file.

services:
  comfyui:
    image: mmartial/comfyui-nvidia-docker:${COMFYUI_VERSION}
    container_name: comfyui
    restart: unless-stopped
    runtime: nvidia
    ports:
      - "${COMFYUI_BIND:-0.0.0.0}:${COMFYUI_PORT}:8188"
    environment:
      - NVIDIA_VISIBLE_DEVICES=1
      # Pin torch at the current 2.12.1+cu129 so the boot script stops
      # auto-upgrading it — compiled SageAttention kernels must not drift
      # (comfy-dev torch-pin, operator-approved 2026-06-18).
      - DISABLE_UPGRADES=true
      - WANTED_UID=${COMFYUI_UID}
      - WANTED_GID=${COMFYUI_GID}
      - BASE_DIRECTORY=/basedir
      - SECURITY_LEVEL=${COMFYUI_SECURITY_LEVEL:-normal}
      - USE_UV=true
      # Extra ComfyUI launch flags (image appends these to main.py, then adds
      # --base-directory + --enable-manager itself):
      #  --fp8_e4m3fn-text-enc — load the FLUX.2 Qwen3-8B text encoder as fp8
      #    (~8.7 GB) instead of upcasting the fp8 file to fp16 (~16 GB). Matches
      #    the box's Ampere-fp8 posture; the encoder runs once per gen so the
      #    upcast-on-compute cost is negligible.
      #  --use-sage-attention — 0.24.1's NATIVE attention selection (the node-based
      #    BlehGlobalSageAttention is dead on 0.24.1: "does not support the new
      #    ComfyUI attention changes"). Binds the in-image sageattention v2.2.0
      #    sm_86 build (rebuilt against the pinned torch 2.12.1). Global speedup
      #    across Flux/SDXL/Wan (comfy-dev benchmarking, 2026-06-18).
      #
      # ALLOCATOR (2026-07-19 — comfy-dev A/B, operator-run — cudaMallocAsync WON).
      # We deliberately DO NOT pass --disable-cuda-malloc, so ComfyUI keeps CUDA's
      # default async allocator (cudaMallocAsync). History: --disable-cuda-malloc +
      # PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True were added when the A6000 was
      # SHARED with the TTS zoo (the native allocator dodged a cudaMallocAsync
      # phantom-OOM). TTS moved to the 3090 (2026-06-18), removing that trigger; the
      # LTX-2.3 v1.5.0 LoRA stack (DMD+OmniNFT+act LoRAs patching the DiT + the 12B
      # Gemma text-encoder) then began hitting the 48 GB ceiling under the native
      # allocator, which fragments/over-reserves (~45 GB allocated+reserved-but-
      # unallocated) and OOMs at TE load. cudaMallocAsync packs tighter + promptly
      # returns freed blocks, so the same job now FITS: the operator's previously-
      # OOMing stress test peaks ~82% VRAM (~40/48 GB) with headroom, 0 OOM/errors.
      # COUPLING: PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True is native-allocator-
      # only, so it is REMOVED here (inert/invalid under cudaMallocAsync) — revert BOTH
      # together. If the TTS zoo ever moves back onto the A6000, re-evaluate the pair.
      - COMFY_CMDLINE_EXTRA=--fp8_e4m3fn-text-enc --use-sage-attention
    volumes:
      - ${COMFYUI_BASEDIR}:/basedir
      # models/ overlaid from storetank. The ~325 GB model tree was migrated
      # off the near-full worktank NVMe (2026-06-13) to /storetank/arbo (roomy
      # SATA SSD). This nested mount shadows the models subdir of /basedir;
      # everything else (custom_nodes, output, input, user, workflows) stays on
      # worktank. Inventory: docs/arbo-comfyui-model-catalog.md.
      - ${COMFYUI_MODELS_DIR:-/storetank/arbo/models}:/basedir/models
      - ${COMFYUI_RUNDIR}:/comfy/mnt
    healthcheck:
      test: ["CMD-SHELL", "curl -fsS http://localhost:8188/ >/dev/null || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      # First boot installs ~5 GB of Python packages; allow generous
      # start_period so the container isn't marked unhealthy during
      # bootstrap. Subsequent starts are fast.
      start_period: 600s
    networks:
      - tnet
    labels:
      - homepage.group=AI - Image & Media
      - homepage.name=ComfyUI
      - homepage.icon=mdi-image-auto-adjust
      - homepage.description=Node-based SD/Flux inference (irv-ml1)
      - homepage.href=http://10.100.79.3:${COMFYUI_PORT}

networks:
  tnet:
    name: traefik-net
    external: true