compose.yaml

# Whole-infra bring-up for watermarks-remover.
#
#   docker compose up --build -d            # core HTTP service only
#   docker compose --profile harness up --build -d   # + markllm / markdiffusion harnesses
#   docker compose --profile heavy up --build -d     # + ctrlregen / synthid (local builds)
#
# The skill and any web app talk to the wr-core service at http://127.0.0.1:8765
# (loopback-only host mapping). The heavy/harness images are one-shot CLIs:
# `up` starts them with `--help` to confirm the image, and real jobs run via
# `docker compose run`, e.g.:
#   docker compose run --rm wr-ctrlregen /data/shot.png -o /data/out.png
#
# ctrlregen and synthid bake in upstream code that is not publicly
# redistributable (all-rights-reserved / non-commercial Research License), so
# they build from source locally and are never pushed to GHCR.

name: watermarks-remover

services:
  wr-core:
    build:
      context: service
      dockerfile: Dockerfile
    image: ghcr.io/guillaumemeyer/watermarks-remover:latest
    ports:
      - "127.0.0.1:8765:8765"
    environment:
      # Empty by default (no auth). Set to require `Authorization: Bearer <key>`.
      WATERMARKS_SERVER_API_KEY: ${WATERMARKS_SERVER_API_KEY:-}
      # Optional SynthID image scorer sidecar (heavy profile).
      WATERMARKS_SYNTHID_SCORER_URL: ${WATERMARKS_SYNTHID_SCORER_URL:-}
      WATERMARKS_SYNTHID_SCORER_API_KEY: ${WATERMARKS_SYNTHID_SCORER_API_KEY:-}
      # Optional SynthID text watermark generator sidecar (harness profile).
      WATERMARKS_SYNTHID_TEXT_URL: ${WATERMARKS_SYNTHID_TEXT_URL:-}
      WATERMARKS_SYNTHID_TEXT_API_KEY: ${WATERMARKS_SYNTHID_TEXT_API_KEY:-}
      WATERMARKS_SYNTHID_TEXT_TIMEOUT: ${WATERMARKS_SYNTHID_TEXT_TIMEOUT:-120}
    read_only: true
    tmpfs:
      - /tmp
    init: true
    user: "10001:10001"
    restart: unless-stopped

  wr-markllm:
    profiles: [harness]
    build:
      context: service
      dockerfile: Dockerfile.markllm
    image: ghcr.io/guillaumemeyer/watermarks-remover:markllm-latest
    # One-shot CLI: `up` just confirms the image; run real jobs with
    # `docker compose run --rm wr-markllm detect /data/wm.txt --scheme kgw`.
    command: ["--help"]
    read_only: true
    tmpfs:
      - /tmp
    init: true
    user: "10001:10001"
    environment:
      HF_TOKEN: ${HF_TOKEN:-}
      HF_HOME: /home/markllm/.cache/huggingface
      # Layer B rewrite backend (openai-compatible / ollama).
      WATERMARKS_REWRITE_BACKEND: ${WATERMARKS_REWRITE_BACKEND:-}
      WATERMARKS_REWRITE_MODEL: ${WATERMARKS_REWRITE_MODEL:-}
      WATERMARKS_REWRITE_BASE_URL: ${WATERMARKS_REWRITE_BASE_URL:-}
      WATERMARKS_REWRITE_API_KEY: ${WATERMARKS_REWRITE_API_KEY:-}
      WATERMARKS_REWRITE_ALLOW_REMOTE: ${WATERMARKS_REWRITE_ALLOW_REMOTE:-}
      WATERMARKS_REWRITE_REASONING_EFFORT: ${WATERMARKS_REWRITE_REASONING_EFFORT:-}
    volumes:
      - markllm-cache:/home/markllm/.cache/huggingface
      # Writable output for the benchmark + the bundled seed corpus (the
      # build context is service/, so the corpus is mounted at runtime):
      #   docker compose run --rm wr-markllm \
      #     /app/bench_synthid_text.py --markllm-dir /opt/markllm \
      #     --corpus /bench-corpus --out-dir /data ...
      - bench-out:/data
      - ./benchmarks/corpus:/bench-corpus:ro

  # HTTP SynthID text watermarking sidecar: lets wr-core generate watermarked
  # text for benchmarks without bundling heavy ML dependencies in the published
  # core image. Reach it via WATERMARKS_SYNTHID_TEXT_URL on wr-core (see .env.example)
  # and require the same bearer key on both sides.
  wr-synthid-text:
    profiles: [harness]
    build:
      context: service
      dockerfile: Dockerfile.markllm
    image: ghcr.io/guillaumemeyer/watermarks-remover:markllm-latest
    entrypoint: ["python3"]
    command: ["/app/synthid_text_server.py", "--host", "0.0.0.0", "--port", "8767"]
    read_only: true
    tmpfs:
      - /tmp
    init: true
    user: "10001:10001"
    environment:
      WATERMARKS_SYNTHID_TEXT_API_KEY: ${WATERMARKS_SYNTHID_TEXT_API_KEY:-}
      MARKLLM_DIR: /opt/markllm
      HF_TOKEN: ${HF_TOKEN:-}
      HF_HOME: /home/markllm/.cache/huggingface
    volumes:
      - markllm-cache:/home/markllm/.cache/huggingface

  wr-markdiffusion:
    profiles: [harness]
    build:
      context: service
      dockerfile: Dockerfile.markdiffusion
    image: ghcr.io/guillaumemeyer/watermarks-remover:markdiffusion-latest
    command: ["--help"]
    read_only: true
    tmpfs:
      - /tmp
    init: true
    user: "10001:10001"
    environment:
      HF_TOKEN: ${HF_TOKEN:-}
      HF_HOME: /home/markdiffusion/.cache/huggingface
    volumes:
      - markdiffusion-cache:/home/markdiffusion/.cache/huggingface

  wr-ctrlregen:
    profiles: [heavy]
    build:
      context: service
      dockerfile: Dockerfile.ctrlregen
    # Local-only tag: upstream `noai-watermark` ships no LICENSE (all-rights-
    # reserved), so this image is never published.
    image: watermarks-remover-ctrlregen:local
    command: ["--help"]
    read_only: true
    tmpfs:
      - /tmp
    init: true
    user: "10001:10001"
    environment:
      HF_TOKEN: ${HF_TOKEN:-}
      NOAI_WATERMARK_DIR: /opt/noai-watermark
    volumes:
      - ctrlregen-cache:/home/remover/.cache/huggingface

  wr-synthid:
    profiles: [heavy]
    build:
      context: service
      dockerfile: Dockerfile.synthid
    # Local-only tag: upstream `reverse-SynthID` is under a non-commercial
    # Research License, so this image is never published.
    image: watermarks-remover-synthid-scorer:local
    command: ["--help"]
    read_only: true
    tmpfs:
      - /tmp
    init: true
    user: "10001:10001"
    volumes:
      - synthid-cache:/home/scorer/.cache/huggingface

  # HTTP SynthID scorer sidecar: lets wr-core score images before/after
  # cleaning without bundling the non-commercial reverse-SynthID code in the
  # published core image. Reach it via WATERMARKS_SYNTHID_SCORER_URL on
  # wr-core (see .env.example) and require the same bearer key on both sides.
  wr-synthid-score:
    profiles: [heavy]
    build:
      context: service
      dockerfile: Dockerfile.synthid
    image: watermarks-remover-synthid-scorer:local
    entrypoint: ["python3"]
    command: ["/app/synthid_score_server.py", "--host", "0.0.0.0", "--port", "8766"]
    read_only: true
    tmpfs:
      - /tmp
    init: true
    user: "10001:10001"
    environment:
      WATERMARKS_SYNTHID_SCORER_API_KEY: ${WATERMARKS_SYNTHID_SCORER_API_KEY:-}
      REVERSE_SYNTHID_DIR: /opt/reverse-synthid
    volumes:
      - synthid-cache:/home/scorer/.cache/huggingface

volumes:
  markllm-cache:
  bench-out:
  markdiffusion-cache:
  ctrlregen-cache:
  synthid-cache: