mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-08-10 08:00:32 +02:00
Victor KuznetsovandClaude Opus 5
78d9e81d0f
The visible-mark path had grown three copies of one ladder sweep, four
near-identical `detect` arms, and four hand-rolled `footprint_mask` overrides;
mark knowledge sat in five hand-maintained tables across three modules; and the
flagship `all`/`batch` pipeline existed only in cli.py, written twice with
divergent behavior.
Detection is now one measurement. `_ladder_best` replaces the three sweeps,
`_scan`/`_verdict` replace the four arms, and the winning box travels to the
mask on `TextMarkDetection.match_box` instead of being swept a second time.
`detect_both` returns the strict and relaxed verdicts from one scan, which
halves the arbiter's perception cost (260 -> 130 matchTemplate calls on a 2048²
image, verdicts identical field for field). A per-mark demotion goes in the new
`_post_gate` hook, never in a `detect` override -- an override is invisible to
the single-pass path, which is how the RunningHub and Yuanbao anchor gates
briefly stopped applying.
Everything about a mark is now one registry row: product, label regime, the
platform sentence `identify` reports, the metadata signals that confirm it, and
its TC260 producer codes. `identify._VISIBLE_MARK_PLATFORM`, the signal mapping
in `api.visible_provenance`, `_PRODUCT_OF` and the pill veto are derived from
those rows.
`api.remove_all` / `api.remove_batch` are the library form of the `all` and
`batch` commands; the CLI is a wrapper that owns console text and exit codes.
Progress is a `(stage, detail)` pair of stable tokens, so the CLI keys its
wording off structure rather than parsing the library's prose back.
Two intentional behavior changes, both verified against a recorded 811-image
sample of detector verdicts, removal-mask hashes, arbiter decisions and
`identify` reports:
* A TC260 label now relaxes the vendor its `ContentProducer` names rather than
ByteDance's pair on every China-AIGC image. 333 of 811 samples move; on 185
of them the previously relaxed pair was simply the wrong vendor, and the
mark actually present never reached the relaxed gate its own
`provenance_ncc_factor` was calibrated for.
* A confident LibLibAI detection suppresses the Jimeng pill, like every other
TC260 product's mark. It was registered alongside RunningHub and Baidu, both
of which were added to the hand-written veto list, and it was not. 1 sample
moves, and it is exactly the co-firing case.
Nothing else in that record changes: detector verdicts, mask hashes and
`identify` verdicts are byte-identical, and all 200 calibration constants are
untouched.
Also: `aigc_label` and friends plus `extract_c2pa_info` are memoized on
(path, mtime_ns, size) -- size because this package rewrites in place; the
native TC260 container readers route on magic bytes instead of the file
extension, so a mislabeled AVI or FLV is no longer invisible; `identify` shares
one pixel decode between the DWT-DCT and visible stages (TrustMark keeps its own
Pillow decode, which is not substitutable); and the six `stabilize_*` video
wrappers collapse into one policy table.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
107 lines
3.5 KiB
Python
107 lines
3.5 KiB
Python
"""Remove-AI-Watermarks: Unified tool for removing visible and invisible AI watermarks.
|
|
|
|
High-level API (lazy, so ``import remove_ai_watermarks`` stays cheap)::
|
|
|
|
import remove_ai_watermarks as raiw
|
|
raiw.remove_visible("in.png", "out.png") # clean a file (provenance auto)
|
|
result, removed = raiw.remove_visible(bgr_array) # array -> array
|
|
raiw.visible_provenance("in.png") # -> frozenset of confirmed vendors
|
|
raiw.identify_video("in.mp4") # -> VideoProvenanceReport
|
|
raiw.inspect_video_metadata("in.mp4") # -> VideoMetadataReport
|
|
raiw.remove_video_all("in.mp4", "out.mp4") # visible + verified metadata
|
|
raiw.remove_video_batch("videos", "videos_clean") # complete per-file results
|
|
raiw.remove_video_metadata("in.mp4", "out.mp4") # verified metadata strip
|
|
raiw.remove_video_invisible("in.mp4", "out.mp4") # oracle-certified SynthID removal
|
|
raiw.remove_video_visible("in.mp4", "out.mp4") # stable visible video-mark removal
|
|
|
|
For a provenance verdict use the ``identify`` submodule::
|
|
|
|
from remove_ai_watermarks.identify import identify
|
|
report = identify("in.png")
|
|
"""
|
|
|
|
import os as _os
|
|
import warnings as _warnings
|
|
from typing import TYPE_CHECKING
|
|
|
|
# transformers prints a noisy deprecation for the Siglip2ImageProcessorFast
|
|
# alias when it is imported (by the optional GPU/ML path). Silence it before
|
|
# any submodule pulls transformers in, so the CLI startup stays quiet. Uses
|
|
# setdefault so a user-set TRANSFORMERS_VERBOSITY still wins.
|
|
_os.environ.setdefault("TRANSFORMERS_VERBOSITY", "error")
|
|
_warnings.filterwarnings("ignore", message=r".*ImageProcessorFast.*")
|
|
|
|
|
|
__version__ = "0.25.0"
|
|
|
|
__all__ = [
|
|
"BatchSummary",
|
|
"InvisibleOptions",
|
|
"MetadataStripIncomplete",
|
|
"RemoveAllResult",
|
|
"__version__",
|
|
"identify_video",
|
|
"inspect_video_metadata",
|
|
"remove_all",
|
|
"remove_batch",
|
|
"remove_video_all",
|
|
"remove_video_batch",
|
|
"remove_video_invisible",
|
|
"remove_video_metadata",
|
|
"remove_video_visible",
|
|
"remove_visible",
|
|
"visible_provenance",
|
|
]
|
|
|
|
if TYPE_CHECKING:
|
|
from remove_ai_watermarks.api import (
|
|
BatchSummary,
|
|
InvisibleOptions,
|
|
MetadataStripIncomplete,
|
|
RemoveAllResult,
|
|
remove_all,
|
|
remove_batch,
|
|
remove_visible,
|
|
visible_provenance,
|
|
)
|
|
from remove_ai_watermarks.video import (
|
|
identify_video,
|
|
inspect_video_metadata,
|
|
remove_video_all,
|
|
remove_video_batch,
|
|
remove_video_invisible,
|
|
remove_video_metadata,
|
|
remove_video_visible,
|
|
)
|
|
|
|
|
|
def __getattr__(name: str) -> object:
|
|
"""Lazily resolve the high-level API (PEP 562), so the heavy imports (cv2, the
|
|
metadata/identify stack) load only when a caller actually reaches for them."""
|
|
if name in (
|
|
"BatchSummary",
|
|
"InvisibleOptions",
|
|
"MetadataStripIncomplete",
|
|
"RemoveAllResult",
|
|
"remove_all",
|
|
"remove_batch",
|
|
"remove_visible",
|
|
"visible_provenance",
|
|
):
|
|
from remove_ai_watermarks import api
|
|
|
|
return getattr(api, name)
|
|
if name in (
|
|
"identify_video",
|
|
"inspect_video_metadata",
|
|
"remove_video_all",
|
|
"remove_video_batch",
|
|
"remove_video_invisible",
|
|
"remove_video_metadata",
|
|
"remove_video_visible",
|
|
):
|
|
from remove_ai_watermarks import video
|
|
|
|
return getattr(video, name)
|
|
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|