CalvinBackup/remove-ai-watermarks
1
0
Fork 0
mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-07-04 23:47:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs(landscape): confirm BFL hosted = C2PA-only on FLUX.1 [dev] too

Browse Source 
Lossless-PNG check across both BFL Playground model lines (FLUX.2 [pro] and
FLUX.1 [dev]) confirms the open DWT-DCT pixel watermark is absent on hosted
output regardless of model or container; only the signed C2PA manifest is present.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Victor Kuznetsov
2026-06-19 09:42:03 -07:00
parent 9e307d020e
commit 9614615001
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/watermarking-landscape.md
+1 -1
View File
@@ -5,7 +5,7 @@
> no content was changed or summarized.
Who embeds what, and whether it is locally detectable (so we know which gaps are fillable). See `identify.py` for what we read.
- **Locally detectable (open decoder, no key/API):** Stable Diffusion / SDXL / FLUX via `imwatermark` DWT-DCT (now covered by `invisible_watermark.py`). FLUX uses the same library (`black-forest-labs/flux2` `src/flux2/watermark.py`, 48-bit `0b001010101111111010000111100111001111010100101110`); SDXL is the diffusers `WATERMARK_MESSAGE` (`0b101100111110110010010000011110111011000110011110`). Caveat: fragile to re-encoding. **The FLUX open DWT-DCT is OPTIONAL dev-inference-code only and is NOT applied by Black Forest Labs' hosted surface** — verified 2026-06-19 on 2 real FLUX.2 BFL Playground outputs (PNG + JPG): both carry the signed C2PA manifest (issuer "Black Forest Labs") but the DWT-DCT decode returns the degenerate all-ones (28/27 of 48 bits match the FLUX reference, i.e. chance level, threshold 44), so the open pixel watermark is absent. Practical consequence: a hosted FLUX.2 image is identified by C2PA only; once C2PA is stripped there is NO open-pixel fallback for it (the 48-bit pattern in `_BITS_48` is correct and would fire only on a locally-generated FLUX.2 with the watermark flag explicitly enabled).
- **Locally detectable (open decoder, no key/API):** Stable Diffusion / SDXL / FLUX via `imwatermark` DWT-DCT (now covered by `invisible_watermark.py`). FLUX uses the same library (`black-forest-labs/flux2` `src/flux2/watermark.py`, 48-bit `0b001010101111111010000111100111001111010100101110`); SDXL is the diffusers `WATERMARK_MESSAGE` (`0b101100111110110010010000011110111011000110011110`). Caveat: fragile to re-encoding. **The FLUX open DWT-DCT is OPTIONAL dev-inference-code only and is NOT applied by Black Forest Labs' hosted surface** — verified 2026-06-19 on real BFL Playground outputs from BOTH FLUX.2 [pro] and FLUX.1 [dev] (lossless PNG + JPG each): all carry the signed C2PA manifest (issuer "Black Forest Labs") but the DWT-DCT decode lands at chance level (FLUX.2 [pro] PNG decodes to the degenerate all-ones; FLUX.1 [dev] lossless PNG to 17/48 ones; matches to the FLUX reference 19-28/48, threshold 44), so the open pixel watermark is absent on hosted output regardless of model line or container. Practical consequence: a hosted FLUX.2 image is identified by C2PA only; once C2PA is stripped there is NO open-pixel fallback for it (the 48-bit pattern in `_BITS_48` is correct and would fire only on a locally-generated FLUX.2 with the watermark flag explicitly enabled).
- **C2PA / IPTC (covered by the issuer/marker scan):** OpenAI, Google, Adobe Firefly, Microsoft (Designer + **Bing Image Creator** — collected 2026-05-24; Bing now runs Microsoft's own **MAI-Image** model, signs C2PA as "Microsoft", NOT OpenAI/DALL-E), **Stability AI** (collected from Brand Studio / DreamStudio successor; signs C2PA as "Stability AI Ltd", no SynthID, no imwatermark on its current Stable Image model — issuer added to `C2PA_ISSUERS`), and **Canva** (Magic Media signs C2PA as "Canva" + `trainedAlgorithmicMedia` with a generic `c2pa-rs` claim generator, no SynthID — issuer `b"Canva"` → "Canva (Magic Media)"; found on real production traffic 2026-06-19, which **disproved the earlier assumption** that Canva downloads are re-encoded exports that always strip C2PA). Still unsampled: Getty, Shutterstock. Midjourney embeds NO C2PA and no invisible watermark (our `mj-*` sample carried only the IPTC tag).
**Samsung Galaxy AI** (Generative Edit / Sketch to Image / Portrait Studio on Galaxy S23 FE / S24 / S25, One UI 7+) signs C2PA as "Samsung Galaxy" with the standard `trainedAlgorithmicMedia` source type AND a proprietary `genAIType` marker; verified on real signed files 2026-05-29 (the standard scan catches the source type; `genAIType` additionally catches a Galaxy S24 file that omits it). It ALSO burns a **visible** localized wordmark into the pixels — a sparkle + "generated with AI" string in the bottom-LEFT corner (issue #37; the Italian "✦ Contenuti generati dall'AI" variant is calibrated) — removed by `samsung_engine.py` / `visible --mark samsung` (reverse-alpha, see the engine bullet); detection feeds `identify` as the medium `visible_samsung` signal. The string is locale-specific, so each locale needs its own captured alpha template.