CalvinBackup/remove-ai-watermarks
1
0
Fork 0
mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-07-12 11:06:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: certify qwen scrub floors (OpenAI 0.10 seed-robust, Gemini 0.25)

Browse Source 
Oracle seed-repeat + floor refinement (2026-06-20, data/qwen_in):
- OpenAI floor 0.10 is SEED-ROBUST: 0.05 and 0.075 still detected; 0.10 clean on
  seeds 0-4 (5/5) -> a random seed is safe.
- Gemini floor lowered 0.30 -> 0.25 (0.20 still detected, 0.25 clean on both
  images). Single-seed (seed 0): the Gemini oracle rate-limits volume seed-repeat,
  so pin a seed in prod rather than relying on seed-robustness there.

Re-measured fidelity at the certified floors (controlnet 0.15 vs Qwen 0.25 for
Gemini): faces still favor controlnet (ArcFace 0.546 vs 0.382, lapvar 0.62 vs
0.40); the short-CJK text case is now a TIE (gemini_1 0.037 vs 0.037 -- the earlier
Qwen 0.000 was at 0.30, not the floor). Qwen's text win holds on substantial
Latin/mixed text (OpenAI 0.385 vs 0.241 / 0.341 vs 0.290). Update watermark_profiles
comment, CLAUDE.md, module-internals, known-limitations.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Victor Kuznetsov
2026-06-20 15:16:51 -07:00
parent 373b910a60
commit 7dddfef14e
4 changed files with 13 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/remove_ai_watermarks/noai/watermark_profiles.py
+7 -5
View File
@@ -14,11 +14,13 @@ DEFAULT_MODEL_ID = "stabilityai/stable-diffusion-xl-base-1.0"
# Qwen-Image (20B MMDiT, Apache-2.0 code AND weights) base for the ``qwen`` pipeline:
# an img2img alternative to SDXL with native text rendering (incl. CJK). Loaded only
# when ``--pipeline qwen`` is selected; CUDA/cloud-class (does not fit MPS). Prototype
# oracle floors (single-seed, 2026-06-19, pending seed-repeat cert): OpenAI clears at
# strength ~0.10, Google/Gemini at ~0.30 (0.20 still detected) -- the latter is HIGHER
# than the certified controlnet Google floor (0.15), so pass an explicit ``--strength``
# for Gemini content on this pipeline until a Qwen-specific ladder is certified.
# when ``--pipeline qwen`` is selected; CUDA/cloud-class (does not fit MPS). CERTIFIED
# oracle floors (2026-06-20): OpenAI **0.10** (seed-robust -- clean on seeds 0-4) and
# Google/Gemini **0.25** (seed 0 verified on 2 images; pin a seed in prod, the Gemini
# oracle rate-limits volume seed-repeat). The Gemini floor (0.25) is HIGHER than the
# certified controlnet Gemini floor (0.15), and ``resolve_strength`` is shared/
# pipeline-independent, so pass an explicit ``--strength 0.25`` for Gemini content on
# this pipeline until a Qwen-specific ladder is wired into ``resolve_strength``.
# (Dispatch uses the bare "qwen" literal, matching the sdxl/controlnet sites, so there
# is no QWEN_PROFILE constant -- only the model id is referenced from code.)
QWEN_MODEL_ID = "Qwen/Qwen-Image"