CalvinBackup/remove-ai-watermarks
1
0
Fork 0
mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-06-04 18:18:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs(text-protection): update stale strength note (~0.05 -> ~0.30 SynthID threshold)

Browse Source 
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Victor Kuznetsov
2026-05-31 17:53:48 -07:00
parent 2e23cf9c4b
commit 4b4049a6f1
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/text-protection-research.md
+4 -2
View File
@@ -14,8 +14,10 @@ filter applied to every candidate below.
## Problem recap
The `invisible` pipeline is SDXL base 1.0 img2img at low strength (~0.05) to defeat
SynthID with minimal visible change. Text is protected via Differential Diffusion with a
The `invisible` pipeline is SDXL base 1.0 img2img to defeat SynthID. The default
strength has risen over time as Google hardens SynthID (0.05 -> 0.10 -> **~0.30**, the
current threshold for fresh Gemini output); higher strength deforms text more, which is
exactly why text protection matters. Text is protected via Differential Diffusion with a
per-pixel change map (`preserve` ~0.9) driven by the PP-OCRv3 DB detector
(`text_protector.py`). Large text survives; **small text (sub ~8 px strokes) softens or
garbles** (issue #14, confirmed on real content).