remove-ai-watermarks/pyproject.toml

[project]
# This name is the published PyPI distribution, not a local label: changing it
# strands every `pip install remove-ai-watermarks` and every pinned dependency
# on it, including the ComfyUI node package. The console script below carries
# the same weight, since users have it on PATH.
name = "remove-ai-watermarks"
version = "0.36.0"
description = "AI watermark remover for visible, invisible, and provenance marks in images and video"
readme = "README.md"
requires-python = ">=3.11,<3.15"
license = {text = "Apache-2.0"}
keywords = [
    "ai-watermark",
    "ai-watermark-remover",
    "watermark-remover",
    "watermark-removal",
    "remove-watermark",
    "synthid",
    "c2pa",
    "content-credentials",
    "nano-banana",
    "gemini",
    "gemini-watermark",
    "ai-metadata",
    "metadata-removal",
    "provenance",
    "exif",
    "stable-diffusion",
    "comfyui",
    "ai-detection",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Environment :: Console",
    "Intended Audience :: Developers",
    "Intended Audience :: End Users/Desktop",
    "License :: OSI Approved :: Apache Software License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3 :: Only",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3.14",
    "Topic :: Multimedia :: Graphics",
    "Topic :: Multimedia :: Graphics :: Graphics Conversion",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Scientific/Engineering :: Image Processing",
    "Topic :: Security",
    "Topic :: Utilities",
]
dependencies = [
    "pillow>=10.0.0",
    "piexif>=1.1.3",
    "click>=8.0.0",
    "python-dotenv>=1.0.0",
    # Official C2PA reader (Content Authenticity Initiative, MIT/Apache-2.0). The
    # primary, spec-tracking manifest parser for the identify/metadata path; the
    # hand-rolled caBX/CBOR scanner in _internal/c2pa.py is kept only as a fallback for
    # synthetic/partial blobs the validator rejects. Binary wheel (Rust), but the
    # import is light (no torch/numpy) so it fits the dependency-light identify
    # host. Prebuilt wheels cover the full CI matrix (linux/macos/windows).
    "c2pa-python>=0.35.0",
]

[project.optional-dependencies]
pixels = [
    "numpy>=1.24.0; python_version < '3.13'",
    # NumPy 1.x has no CPython 3.13+ wheels. Requiring 2.x prevents installers
    # from attempting an unsupported source build on the newer Python lines.
    "numpy>=2; python_version >= '3.13'",
    "opencv-python-headless>=4.8.0",
]
# Optional HEIC/AVIF pixel decode. Metadata scanning handles these containers
# without this plugin; combine `heif` with any pixel feature only when needed.
heif = [
    "pillow-heif>=0.13.0",
]
visible = ["remove-ai-watermarks[pixels]"]
# Video visible removal uses the shared pixel runtime. PyAV packetizes processed
# VFR frames with explicit PTS before system ffmpeg encodes them.
video = [
    "remove-ai-watermarks[visible]",
    "av>=18,<19",
]
# Open DWT-DCT watermarks used by Stable Diffusion / SDXL / FLUX. The in-tree
# decoder avoids the upstream invisible-watermark package's mandatory torch and
# non-headless OpenCV dependencies.
detect = [
    "remove-ai-watermarks[pixels]",
    "PyWavelets>=1.1.1",
]
diffusion = [
    "remove-ai-watermarks[pixels]",
    # A CUDA-enabled torch build is required: invisible-watermark removal has no
    # CPU, MPS or XPU path. The default PyPI wheel carries CUDA on Linux/Windows;
    # on macOS there is no CUDA build and this extra installs only for the
    # non-diffusion imports it shares.
    "torch>=2.0.0",
    "diffusers>=0.38.0",
    # diffusers 0.38's auto-pipeline registry imports ``Qwen3VLForConditional
    # Generation`` (its ``nucleusmoe_image`` pipeline), which only exists in
    # transformers 5.x -- so ``from diffusers import AutoPipelineForImage2Image``
    # fails on transformers 4.x. The real SDXL-loading break was NOT transformers
    # 5.x but the tokenizers *release candidate* (0.23.0rc0) that the global
    # ``prerelease = "allow"`` drags in: its CLIP tokenizer raises
    # ``RobertaProcessing.__new__() got an unexpected keyword argument 'cls'``.
    # Cap tokenizers to the stable 0.22 line (transformers 5.x accepts
    # >=0.22,<=0.23.0) so the rc is excluded while SDXL still loads.
    "transformers>=5,<6",
    "tokenizers>=0.22,<0.23",
    "accelerate>=0.25.0",
    "safetensors",
]
# Full two-stage high-fidelity profile: Qwen-Image-2512 Lightning + DiffSynth
# Canny ControlNet for the frame, then SAM-masked Z-Image Turbo face repair.
# CUDA-only and intentionally separate from the normal diffusion extra because the
# additional model stack and DiffSynth runtime are large.
qwen-zimage = [
    "remove-ai-watermarks[diffusion]",
    "diffsynth>=2.0.17,<3",
    "torchvision>=0.20.0",
]
# Opt-in verified-text reconstruction over qwen-zimage. LaMa removes the changed
# candidate glyphs before exact Qwen-VAE cores are composited back.
text-restoration = [
    "remove-ai-watermarks[qwen-zimage,lama]",
]
# Draft-only OCR proposals for verified-text manifests. CPU, no torch:
# PaddleOCR detection plus three script-chosen recognition engines. The models
# download on first use and are cached by huggingface_hub; never bundled.
text-draft = [
    "paddleocr>=3.3.3",
    "paddlepaddle>=3.0.0",
    "huggingface-hub>=0.20.0",
]
# Adobe TrustMark decoder -- the open, keyless watermark behind Adobe Durable
# Content Credentials (soft-binding alg ``com.adobe.trustmark.P``). Optional
# because it pulls torch and downloads model weights on first use. identify()
# guards the import and skips the TrustMark signal when absent.
trustmark = [
    # TrustMark requires NumPy <2, whose last release has no CPython 3.13+
    # wheels. Keep this feature installable only on its real runtime range.
    "trustmark>=0.8.0; python_version < '3.13'",
]
# Metadata-free photo classifier (Model 1 then gated Model 2). CPU torch is
# enough. identify never imports this extra. Weights download on first use.
classify = [
    "remove-ai-watermarks[pixels]",
    "torch>=2.0.0",
    "transformers>=5,<6",
    "tokenizers>=0.22,<0.23",
    "huggingface-hub>=0.20.0",
]
# Official remote OpenAI SynthID verification. The command strips AI provenance
# metadata and proves pixel identity before upload; it is never called implicitly.
verify = [
    "openai>=2.52.0",
]
# Universal region eraser backend -- big-LaMa via onnxruntime (Carve/LaMa-ONNX,
# Apache-2.0). CPU, no torch. Model (~200 MB) is downloaded on first use and
# cached by huggingface_hub; it is never bundled in this repo. The default cv2
# eraser backend needs none of this.
lama = [
    "remove-ai-watermarks[visible]",
    "onnxruntime>=1.24.0",
    "huggingface-hub>=0.20.0",
]
# Lightweight inpaint backend -- MI-GAN via onnxruntime (andraniksargsyan/migan,
# MIT). CPU, no torch. Model (~28 MB) downloaded on first use and cached by
# huggingface_hub; never bundled. ~700-950 MB peak RAM / ~0.19 s/call -- the
# memory-tight learned tier (vs big-LaMa's ~4.7 GB). Select it explicitly when
# LaMa, the quality-first `auto` choice, is too large. Same runtime as `lama`.
migan = [
    "remove-ai-watermarks[visible]",
    "onnxruntime>=1.24.0",
    "huggingface-hub>=0.20.0",
]
dev = [
    "remove-ai-watermarks[video]",
    "remove-ai-watermarks[detect]",
    "pytest>=8.0.0",
    "pytest-cov>=4.1.0",
    "pytest-xdist>=3.5.0",
    "packaging>=24.0",
    "ruff>=0.4.0",
    "pyright>=1.1.0",
    "invisible-watermark>=0.2.0",
]
# ``qwen-zimage`` already pulls ``diffusion``; naming both would suggest diffusion is
# independently sufficient for a removal, which it is not.
all = ["remove-ai-watermarks[video,heif,detect,trustmark,text-restoration,migan,classify,verify]"]

[project.scripts]
remove-ai-watermarks = "remove_ai_watermarks.cli:main"

[project.urls]
Repository = "https://github.com/wiltodelta/remove-ai-watermarks"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["src/remove_ai_watermarks"]

[tool.hatch.build.targets.sdist]
# Keep the source distribution small and public-safe: ship tracked source and
# metadata, not corpora or local research/session artifacts. The wheel ships
# only src/.
include = [
    "/src",
    "/LICENSE",
    "/README.md",
    "/pyproject.toml",
]
exclude = [
    "/data",
    "/tmp",
    "/.sc",
]

[tool.pytest.ini_options]
testpaths = ["tests"]
pythonpath = ["src", "scripts"]
addopts = "-v --tb=short"

[tool.ruff]
target-version = "py311"
line-length = 120
exclude = ["_refs", ".local-eval"]
extend-exclude = ["*.md"]

[tool.ruff.lint]
select = ["E", "F", "B", "I", "S", "UP", "SIM", "RET", "COM", "C4", "G", "PT", "PIE", "T20", "DTZ", "ICN", "TCH", "RUF", "ANN"]
ignore = [
    "COM812",  # missing trailing comma (conflicts with ruff formatter)
    "ANN401",  # typing.Any — sometimes unavoidable with third-party libs
]

[tool.ruff.lint.per-file-ignores]
"scripts/**/*.py" = ["G004", "S108", "S310", "T20"]
"tests/*.py" = ["ANN", "S101", "S105", "S106", "S108"]
"src/remove_ai_watermarks/_internal/watermark_remover.py" = ["S603", "S606", "S607"]  # nvidia-smi capability probe
"src/remove_ai_watermarks/_internal/c2pa.py" = ["S110"]  # try-except-pass for corrupt file handling

[tool.ruff.format]
quote-style = "double"
indent-style = "space"

[tool.pyright]
pythonVersion = "3.11"
typeCheckingMode = "strict"
exclude = ["_refs", ".local-eval"]

[[tool.pyright.executionEnvironments]]
root = "tests"
extraPaths = ["."]
reportAttributeAccessIssue = false
reportOptionalSubscript = false
reportOptionalMemberAccess = false
reportArgumentType = false
reportUnknownMemberType = false
reportUnknownArgumentType = false
reportUnknownVariableType = false
reportMissingTypeArgument = false