remove-ai-watermarks

_internal

Fix SDXL offload placement on the current CUDA device

2026-10-08 16:17:11 -07:00

assets

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

licenses

Release 0.22.0 with composable feature extras

2026-07-31 10:39:13 -07:00

__init__.py

Release 0.45.1

2026-10-08 16:42:57 -07:00

_text_mark_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

_text_mark_variants.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

api.py

Unify TC260 producers and strengthen provenance regression coverage

2026-10-01 11:30:32 -07:00

baidu_engine.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

classify.py

Pin published ONNX classifier snapshot

2026-09-10 20:07:33 -07:00

cli.py

Stream the sdxl-zimage global stack on cards below 12 GiB

2026-10-08 23:27:55 +02:00

dola_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

doubao_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

dwt_dct.py

Align watermark content with detector coverage

2026-08-27 20:05:03 -07:00

forensic_metadata.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

gemini_engine.py

Document Gemini sparkle decorative-glyph false positive, add observability

2026-09-21 21:41:59 -07:00

generic_ai_label_engine.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

humanizer.py

Fix sharpening quantization and cross-platform regression tests

2026-09-08 19:25:44 -07:00

identify.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

image_io.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

invisible_engine.py

Stream the sdxl-zimage global stack on cards below 12 GiB

2026-10-08 23:27:55 +02:00

invisible_watermark.py

Align watermark content with detector coverage

2026-08-27 20:05:03 -07:00

jimeng_engine.py

Collapse the duplicated detection path and lift the image pipeline into the library

2026-08-03 22:49:45 -07:00

kling_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

liblib_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

metadata_record.py

Add paid-service captures, aggregator attribution, and provenance vetoes

2026-09-26 14:32:53 -07:00

metadata.py

Unify TC260 producers and strengthen provenance regression coverage

2026-10-01 11:30:32 -07:00

microsoft_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

microsoft_invismark.py

Add local Microsoft InvisMark payload disruption

2026-09-14 12:07:00 -07:00

openai_provenance.py

Add unified provider oracle tooling

2026-09-08 13:26:43 -07:00

openart_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

optional_deps.py

Fix agent skill dependency checks and metadata guidance

2026-09-05 11:32:22 -07:00

pill_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

pixel_evidence.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

qwen_engine.py

Release 0.40.1 with Qwen symbol false-positive fix

2026-09-11 10:55:28 -07:00

region_eraser.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

runninghub_engine.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

samsung_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

source_classify_v2.py

Export calibrated image source providers

2026-09-25 14:38:04 -07:00

source_classify.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

text_draft.py

Fix output preservation, research validation, and documentation drift

2026-09-08 19:07:10 -07:00

trustmark_detector.py

Add stratified watermark benchmark and resource profiling

2026-09-06 20:18:48 -07:00

video_encoding.py

Upgrade to OpenCV 5 with frozen Hershey templates and tighten video marks

2026-09-23 19:19:00 -07:00

video_invisible.py

Make the video SynthID operating point measurable and hard to move silently

2026-08-05 11:17:38 -07:00

video_synthid.py

Separate runtime actions from development provenance checks

2026-09-06 20:18:47 -07:00

video_temporal.py

feat: complete product video watermark pipeline

2026-07-31 10:42:39 -07:00

video_visible.py

Unify TC260 producers and strengthen provenance regression coverage

2026-10-01 11:30:32 -07:00

video.py

Unify TC260 producers and strengthen provenance regression coverage

2026-10-01 11:30:32 -07:00

wan_engine.py

Close the remaining raw-byte identity scans and unify two rules

2026-09-26 22:19:30 -07:00

watermark_registry.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

workbuddy_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00

yuanbao_engine.py

Add AI disclosure layouts, tighten detection and provenance warnings

2026-10-04 11:03:37 -07:00