remove-ai-watermarks

CalvinBackup/remove-ai-watermarks

Fork 0

mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-08-07 06:28:36 +02:00

Files

T

History

Victor KuznetsovandClaude Opus 4.8 183793fbf2 fix(invisible): disable diffusers SDXL watermarker on removal output

The SDXL removal pipelines (sdxl + controlnet) were built without
add_watermarker=False, so diffusers embedded its default open "Stable
Diffusion XL" DWT-DCT invisible watermark on every output whenever
invisible-watermark is installed (the detect extra). A watermark REMOVER was
therefore replacing one detectable AI watermark (SynthID) with another: the
cleaned output re-read as AI (identify -> "Open invisible watermark: Stable
Diffusion XL"), observed on the SynthID validation sample.

Both SDXL loaders now call a shared _disable_sdxl_watermarker helper (mirrors
_maybe_add_fp16_vae; the ControlNetModel sub-model and the Qwen loader never
call it, since only the pipeline accepts the kwarg). Verified end to end: the
affected outputs re-run clean (is_ai=None, no open watermark).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-14 17:16:49 +03:00

controlnet-removal-pipeline-research.md

docs(restore): document that restore methods REGENERATE, not preserve

2026-06-08 21:08:11 -07:00

known-limitations.md

fix: metadata-strip parity, input robustness, and detection/clash coverage

2026-07-13 10:49:24 +03:00

module-internals.md

fix(invisible): disable diffusers SDXL watermarker on removal output

2026-07-14 17:16:49 +03:00

qwen-improvement-research.md

fix(qwen): native-geometry img2img + pipeline-aware strength; record dropped auto/mixed/Z-Image leads