mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-06-10 04:43:54 +02:00
Victor Kuznetsov
439eeadc07
The GFPGAN `restore` extra and its `face_restore.py` module are gone. They were oracle-confirmed to re-introduce SynthID by blending watermarked original face pixels at fidelity weight 0.5 (clean A/B: gemini_3 controlnet 0.20 detected WITH GFPGAN, clean WITHOUT). Keeping them as the default restore method was a footgun for the removal pipeline. PhotoMaker-V2 (added in the previous commit) is the single shipped restore path now -- identity-as-embedding, SynthID-safe by construction. Removed: - src/remove_ai_watermarks/face_restore.py + tests/test_face_restore.py - pyproject.toml `restore` extra (gfpgan/facexlib/basicsr + scipy/numba pins) - pyproject.toml `[tool.uv.extra-build-dependencies] basicsr = [...]` build pin - CLI: `--restore-faces-method` and `--restore-faces-weight` (no method choice to make, no GFPGAN weight knob to expose) - InvisibleEngine._restore_faces method (only _restore_faces_photomaker remains) - All restore-faces-method / restore-faces-weight threading through cmd_* signatures and _process_batch_image Kept: - `--restore-faces / --no-restore-faces`: now binds to PhotoMaker-V2. - All adopted oracle findings about GFPGAN re-introducing SynthID (kept in the research docs as historical context that explains why the path was removed). Docs updated: CLAUDE.md (restore extras bullet collapsed to photomaker, removed face_restore Key-modules bullet, several inline GFPGAN refs scrubbed), README.md (face-identity callout + install section now point to the photomaker extra), docs/synthid.md 5.5 (net recipe), docs/controlnet-removal-pipeline-research.md (recommendations). ruff + strict pyright (src/) clean; 578 tests pass (the 9 GFPGAN tests are gone, the 9 PhotoMaker tests stay green). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
211 lines
9.1 KiB
TOML
211 lines
9.1 KiB
TOML
[project]
|
|
name = "remove-ai-watermarks"
|
|
version = "0.8.9"
|
|
description = "Remove visible and invisible AI watermarks from images (Gemini / Nano Banana, ChatGPT, Stable Diffusion)"
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
license = {text = "MIT"}
|
|
classifiers = [
|
|
"License :: OSI Approved :: MIT License",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Topic :: Multimedia :: Graphics",
|
|
"Topic :: Scientific/Engineering :: Image Processing",
|
|
]
|
|
dependencies = [
|
|
"pillow>=10.0.0",
|
|
"piexif>=1.1.3",
|
|
"numpy>=1.24.0",
|
|
"opencv-python-headless>=4.8.0",
|
|
"click>=8.0.0",
|
|
"python-dotenv>=1.0.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
gpu = [
|
|
"torch>=2.0.0",
|
|
# The default PyPI torch wheel is a CPU/CUDA build. To drive an Intel GPU
|
|
# (Arc / Data Center) via ``--device xpu`` you need an XPU-enabled torch
|
|
# from PyTorch's XPU wheel index (Linux/Windows only -- there is no macOS
|
|
# XPU build). Install that build first, then this extra (torch is then
|
|
# already satisfied and won't be re-pulled):
|
|
# pip install torch --index-url https://download.pytorch.org/whl/xpu
|
|
# pip install 'remove-ai-watermarks[gpu]'
|
|
# uv users can target the ``pytorch-xpu`` index declared under [tool.uv]:
|
|
# uv pip install torch --index-url https://download.pytorch.org/whl/xpu
|
|
"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",
|
|
]
|
|
# Open invisible-watermark (imwatermark) decoder for detecting the DWT-DCT
|
|
# watermarks embedded by Stable Diffusion / SDXL / FLUX. Optional because it
|
|
# pulls non-headless opencv AND torch (invisible-watermark declares torch a hard
|
|
# dependency, and WatermarkDecoder eagerly imports rivaGan -> torch at import
|
|
# time, so the dwtDct-only detect path still needs torch present even though it
|
|
# never runs on GPU). So `detect` alone pulls torch -- no need to add `gpu` for
|
|
# detection. identify() guards the import and skips the signal when absent.
|
|
detect = [
|
|
"invisible-watermark>=0.2.0",
|
|
]
|
|
# 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>=0.8.0",
|
|
]
|
|
# 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 = [
|
|
"onnxruntime>=1.16.0",
|
|
"huggingface-hub>=0.20.0",
|
|
]
|
|
# Optional PhotoMaker-V2 face-identity restoration (commercial-safe end-to-end:
|
|
# PhotoMaker-V2 weights Apache-2.0 + OpenCLIP-ViT-H/14 MIT, NO InsightFace). Carries
|
|
# identity in a SEMANTIC EMBEDDING and generates fresh face pixels conditioned on it
|
|
# -- so the pixel watermark is not transported. Empirically validated 2026-06-04: the
|
|
# OpenCLIP embedding changes by cosine 0.002 under SynthID-magnitude pixel noise (an
|
|
# order of magnitude less than JPEG90 drift, which SynthID survives). Replaces the
|
|
# removed `restore` (GFPGAN) extra, which ran on the watermarked ORIGINAL and was
|
|
# oracle-confirmed to re-introduce SynthID. See
|
|
# docs/synthid-robust-identity-research.md and
|
|
# src/remove_ai_watermarks/photomaker_restore.py. Weights (~3 GB SDXL + ~1 GB
|
|
# PhotoMaker-V2 adapter) download on first use; never bundled. Kept OUT of `all`
|
|
# (heavy + model download), same as `esrgan`.
|
|
photomaker = [
|
|
"photomaker @ git+https://github.com/TencentARC/PhotoMaker.git",
|
|
"huggingface-hub>=0.20.0",
|
|
]
|
|
# Optional pre-diffusion super-resolution for small inputs (Real-ESRGAN). Loaded via
|
|
# spandrel (MIT) -- a pure model-loader with NO basicsr dependency (it pulls only
|
|
# torch / torchvision / safetensors / numpy / einops).
|
|
# The Real-ESRGAN weights (BSD-3-Clause) download on first use and are cached; they
|
|
# are never bundled. CPU works but is slow on large inputs -- it is meant for the
|
|
# pre-diffusion upscale of SMALL inputs (and the GPU worker). Guarded by
|
|
# upscaler.is_available(); the default upscaler stays Lanczos (cv2, no deps). The
|
|
# weights are fetched with torch.hub (bundled with spandrel's torch), so no extra
|
|
# download dependency is needed.
|
|
esrgan = [
|
|
"spandrel>=0.3.0",
|
|
]
|
|
dev = [
|
|
"pytest>=8.0.0",
|
|
"pytest-cov>=4.1.0",
|
|
"ruff>=0.4.0",
|
|
"pyright>=1.1.0",
|
|
"invisible-watermark>=0.2.0",
|
|
]
|
|
all = ["remove-ai-watermarks[gpu,detect,trustmark,lama,dev]"]
|
|
|
|
# diffusers 0.38.0 (security fix for GHSA-98h9-4798-4q5v) declares a dependency
|
|
# on safetensors>=0.8.0rc0 — a pre-release. Allow pre-releases globally so the
|
|
# resolver can satisfy that. Drop once diffusers publishes a release with a
|
|
# stable safetensors pin (or once safetensors 0.8.0 stable is out).
|
|
[tool.uv]
|
|
prerelease = "allow"
|
|
|
|
# PyTorch Intel-GPU (XPU) wheel index. ``explicit = true`` keeps it inert for
|
|
# the default CPU/CUDA install: uv consults it only when a torch install
|
|
# explicitly targets it (see the ``gpu`` extra comment), so it does not alter
|
|
# the locked CPU/CUDA resolution. Linux/Windows only -- no macOS XPU build.
|
|
[[tool.uv.index]]
|
|
name = "pytorch-xpu"
|
|
url = "https://download.pytorch.org/whl/xpu"
|
|
explicit = true
|
|
|
|
[project.scripts]
|
|
remove-ai-watermarks = "remove_ai_watermarks.cli:main"
|
|
|
|
[project.urls]
|
|
Repository = "https://github.com/wiltodelta/remove-ai-watermarks"
|
|
|
|
[build-system]
|
|
# Pin hatchling < 1.31. hatchling 1.30.0 made Metadata-Version 2.5 (PEP 794) the
|
|
# default, which the twine bundled in pypa/gh-action-pypi-publish@release/v1 rejects
|
|
# ("'2.5' is not a valid Metadata-Version"), failing the v0.8.3 PyPI upload
|
|
# (2026-06-01) when unpinned requires = ["hatchling"] pulled 1.30.0. hatchling 1.30.1
|
|
# reverted the default to 2.4 ("kept at 2.4 until more tools support 2.5"), and
|
|
# 1.27-1.29 were always 2.4 -- so < 1.31 keeps `uv build` on a 2.4-emitting hatchling
|
|
# (it resolves to the latest allowed, 1.30.1). The publish workflow now uses
|
|
# `uv publish`, whose uploader accepts 2.5, so this pin is belt-and-suspenders, not
|
|
# load-bearing: keeping it makes the first uv-publish release ship 2.4 metadata
|
|
# (isolating the uploader swap from the metadata-version bump). Drop to
|
|
# `requires = ["hatchling"]` once that release confirms the path.
|
|
requires = ["hatchling<1.31"]
|
|
build-backend = "hatchling.build"
|
|
|
|
# Allow the `photomaker` extra to reference its upstream git URL directly (the
|
|
# TencentARC/PhotoMaker package is not on PyPI). Apache-2.0; weights download on
|
|
# first use, so this only adds the Python wrapper.
|
|
[tool.hatch.metadata]
|
|
allow-direct-references = true
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["src/remove_ai_watermarks"]
|
|
|
|
[tool.hatch.build.targets.sdist]
|
|
# Keep the source distribution small: ship the package + metadata, not the
|
|
# committed test corpora / calibration captures under data/ (tens of MB --
|
|
# synthid_corpus images + the visible-mark captures), which pushed the 0.8.0
|
|
# sdist past PyPI's per-project file-size limit (the wheel ships only src/).
|
|
exclude = ["/data"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
pythonpath = ["src"]
|
|
addopts = "-v --tb=short"
|
|
|
|
[tool.ruff]
|
|
target-version = "py310"
|
|
line-length = 120
|
|
exclude = ["_refs"]
|
|
|
|
[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]
|
|
"tests/*.py" = ["ANN", "S101", "S105", "S106", "S108"]
|
|
"src/remove_ai_watermarks/noai/watermark_remover.py" = ["S603", "S606", "S607", "T201"] # subprocess calls for auto-install/CUDA fix
|
|
"src/remove_ai_watermarks/noai/c2pa.py" = ["S110"] # try-except-pass for corrupt file handling
|
|
|
|
[tool.ruff.format]
|
|
quote-style = "double"
|
|
indent-style = "space"
|
|
|
|
[tool.pyright]
|
|
pythonVersion = "3.10"
|
|
typeCheckingMode = "strict"
|
|
exclude = ["_refs"]
|
|
|
|
[[tool.pyright.executionEnvironments]]
|
|
root = "tests"
|
|
extraPaths = ["."]
|
|
reportAttributeAccessIssue = false
|
|
reportOptionalSubscript = false
|
|
reportOptionalMemberAccess = false
|
|
reportArgumentType = false
|
|
reportUnknownMemberType = false
|
|
reportUnknownArgumentType = false
|
|
reportUnknownVariableType = false
|
|
reportMissingTypeArgument = false
|