CalvinBackup/remove-ai-watermarks
1
0
Fork 0
mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-07-06 08:27:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs(qwen): drop false 'pending seed-repeat cert' from pipeline docstring

Browse Source 
The qwen oracle floors are certified, not pending. Near-threshold scrub is
seed-non-deterministic, but the prod path pins one fixed seed, so a certified
floor reproduces run-to-run -- pinning the seed is the release gate, not a seed
sweep. Reword the docstring so it stops implying an open seed-repeat gate.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Victor Kuznetsov
2026-06-22 10:30:42 -07:00
parent 78e2ae65ad
commit 9695a7cbd2
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/remove_ai_watermarks/noai/watermark_remover.py
+4 -2
View File
@@ -5,8 +5,10 @@ Three pipelines (selected by the explicit ``pipeline`` ctor arg):
0. ``qwen`` -- Qwen-Image (20B MMDiT, Apache-2.0) img2img. The scrub still comes from
the img2img ``strength``; Qwen preserves text (incl. CJK) and structure markedly
better than SDXL at the scrub floor, so it over-regenerates real photos far less.
CUDA/cloud-class (does not fit MPS). See ``watermark_profiles`` for the prototype
oracle floors (pending seed-repeat cert).
CUDA/cloud-class (does not fit MPS). See ``watermark_profiles`` for the certified
oracle floors. (Near-threshold scrub is seed-non-deterministic, but the prod path
pins ONE fixed seed, so a certified floor reproduces run-to-run -- pinning the seed
is the release gate, not sweeping seeds.)
Two SDXL pipelines:
1. ``controlnet`` (DEFAULT) -- SDXL img2img with a canny ControlNet. The watermark