mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-05-22 12:36:52 +02:00

Files

T

test-user 87d02126e3 feat(metadata): parse C2PA JUMBF manifest fields, add Images 2.0 sample, bump to 0.3.4

- metadata --check now shows claim_generator, c2pa_spec, digital_source_type,
  c2pa_actions, signer instead of empty table for C2PA-only files
- reuses existing extract_c2pa_chunk() from noai/c2pa.py — no more duplicate
  PNG chunk parsing or full-file reads
- adds data/samples/openai-images-2/amur-leopard.png: real gpt-image-2 output
  with C2PA manifest signed by OpenAI OpCo LLC / Trufo CA (spec 2.2.0)
- removes stale data/samples/nano-banana-1/2.png (no longer referenced)
- updates README: new Images 2.0 row in supported models table
- documents known text-degradation limitation in CLAUDE.md

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-22 17:21:51 -07:00

1.3 KiB

Raw Permalink Blame History

Remove-AI-Watermarks

You are a principal Python engineer maintaining a CLI tool and library for removing visible and invisible AI watermarks from images.

How to run

uv run remove-ai-watermarks all <image.png> -o <output.png>
uv run remove-ai-watermarks metadata <image.png> --check — inspect AI metadata (C2PA, EXIF, PNG chunks)
uv run remove-ai-watermarks metadata <image.png> --remove -o <out.png> — strip all AI metadata

Configuration

GPU/ML modules (invisible_engine, ctrlregen, watermark_remover) are optional — guard imports with is_available() checks
Tests for ML modules are limited to availability checks (require multi-GB downloads)

Key modules

noai/c2pa.py — PNG chunk parser; use extract_c2pa_chunk(path) to get raw caBX payload, has_c2pa_metadata(path) to detect. Do not reimplement chunk parsing.
noai/constants.py — PNG_SIGNATURE, C2PA_CHUNK_TYPE, C2PA_SIGNATURES constants
face_protector.py — YOLO detect + soft-blend pattern; mirror this for any "protect region during diffusion" features

Known limitations

invisible pipeline downscales to 768 px before diffusion → degrades fine text in infographics. Tracked; fix is tile-based or skip-downscale approach.
Pyright first run is slow (2-3 min) due to ML deps (torch/diffusers/transformers stubs)