Dockerfile.markdiffusion

# Optional local Docker image for the MarkDiffusion image-watermark harness.
#
# Build from the repository root:
#   docker build -f Dockerfile.markdiffusion -t watermark-remover-markdiffusion .
#
# The upstream package is installed from PyPI at build time (pinned in
# requirements-markdiffusion.txt) and is NOT redistributed by this repository.
# Upstream is Apache-2.0.
#
# Vendored fork hardening:
#   - base image pinned by digest (no moving tag drift)
#   - package version pinned exactly in requirements-markdiffusion.txt
#   - pip itself pinned (no unpinned bootstrap step)
#   - runs as an unprivileged user (a parser bug in a crafted image can no
#     longer write files as root inside the container)

# python:3.14-slim linux/amd64 digest.
FROM python:3.14-slim@sha256:ce40764625a4ff50df3548277632e7f96c4e77fe75fa848aae9885476e7df5a4

RUN apt-get update \
    && apt-get install -y --no-install-recommends \
        libgl1 \
        libglib2.0-0 \
        passwd \
    && rm -rf /var/lib/apt/lists/*

COPY skills/remove-ai-marks/scripts/requirements-markdiffusion.txt /app/requirements-markdiffusion.txt
COPY skills/remove-ai-marks/scripts/markdiffusion_harness.py /app/markdiffusion_harness.py
COPY skills/remove-ai-marks/scripts/common.py /app/common.py

# torch is installed first from the CPU index so the pinned package resolves
# against it; the CPU index keeps the image small. No GPU wheel index inside
# the image — CUDA users should run setup_markdiffusion.sh on the host instead.
RUN python3 -m pip install --no-cache-dir "pip==26.2.1" \
    && python3 -m pip install --no-cache-dir --index-url https://download.pytorch.org/whl/cpu "torch>=2.4,<2.11" \
    && python3 -m pip install --no-cache-dir -r /app/requirements-markdiffusion.txt

# Unprivileged runtime user. The harness only reads input files and writes to
# stdout/tmp, so nothing under /opt, /app, or the mounted data dir needs root.
RUN useradd --create-home --uid 10001 --shell /usr/sbin/nologin markdiffusion
USER markdiffusion

ENV HOME=/home/markdiffusion \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    HF_HOME=/home/markdiffusion/.cache/huggingface

WORKDIR /app
ENTRYPOINT ["python3", "/app/markdiffusion_harness.py"]