remove-ai-watermarks

mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-07-07 08:57:50 +02:00

Files

T

Victor Kuznetsov 0e5a4cbc54 feat(visible): capture-less AI生成 pill (#54 ), inpaint fallback, MI-GAN backend (#56 )

- Add the Jimeng-basic top-left "AI生成" pill as a CAPTURE-LESS mark
  (pill_engine.py): synthetic-silhouette edge-NCC detect + inpaint-only removal.
  Gated in remove_auto_marks: kept only when Jimeng is confirmed (TC260 metadata
  OR the bottom-right "★ 即梦AI" wordmark fired -- the wordmark keeps recall on
  metadata-STRIPPED uploads) AND Doubao did not fire.
- Add an inpaint-fallback removal path + MI-GAN ONNX backend (migan extra, MIT,
  ~28 MB / ~1 GB peak -- droplet-friendly) alongside big-LaMa. New
  --method auto|reverse-alpha|inpaint (shared across visible/all/batch) and
  erase --backend migan; footprint_mask on each engine.
- auto is deterministic: reverse-alpha for capture marks (recovers exact pixels,
  lighter -- measured cleaner than MI-GAN on structured backgrounds) and inpaint
  only for the capture-less pill.
- --mark auto now removes EVERY detected mark in one pass (remove_auto_marks),
  so a Jimeng-basic image's top-left pill AND bottom-right wordmark both clear.
- Bump 0.12.1 -> 0.13.0.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-06 20:38:23 +03:00

_plain_console.py

fix(scripts): drop rich import from analysis scripts (red CI after rich removal)

2026-05-31 15:41:50 -07:00

controlnet_sweep.py

feat: controlnet pipeline for text/face-structure preservation

2026-06-03 16:59:28 -07:00

corpus_gap_scan.py

fix(scripts): drop rich import from analysis scripts (red CI after rich removal)

2026-05-31 15:41:50 -07:00

fidelity_metrics.py

fix(qwen): native-geometry img2img + pipeline-aware strength; record dropped auto/mixed/Z-Image leads