feat(invisible): protect text automatically by default (#21)

Mirror protect_faces: protect_text defaults to True in invisible_engine and
watermark_remover, so the SDXL pipeline detects text per image and switches to
Differential Diffusion only when glyphs are found. Text-free inputs fall back to
plain img2img with no differential-pipeline load, so the autonomy is free. The
CLI now exposes a single off-switch --no-protect-text instead of the positive
flag, keeping the interface minimal.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/remove_ai_watermarks/cli.py

@@ -461,10 +461,10 @@ def cmd_erase(
     help="Cap long side (px) before diffusion; 0 = native (best quality, like raiw.cc). Raise only on GPU/MPS OOM.",
 )
 @click.option(
-    "--protect-text",
+    "--no-protect-text",
     is_flag=True,
     default=False,
-    help="Preserve detected text (incl. CJK) via Differential Diffusion. SDXL default pipeline only.",
+    help="Disable automatic text protection (text/CJK is preserved by default on the SDXL pipeline).",
 )
 @click.pass_context
 def cmd_invisible(
@@ -479,7 +479,7 @@ def cmd_invisible(
     hf_token: str | None,
     humanize: float,
     max_resolution: int,
-    protect_text: bool,
+    no_protect_text: bool,
 ) -> None:
     """Remove invisible AI watermarks (SynthID, StableSignature, TreeRing).
 
@@ -526,7 +526,7 @@ def cmd_invisible(
         guidance_scale=None,
         seed=seed,
         humanize=humanize,
-        protect_text=protect_text,
+        protect_text=not no_protect_text,
         max_resolution=max_resolution,
     )
     elapsed = time.monotonic() - t0
@@ -680,10 +680,10 @@ def cmd_identify(ctx: click.Context, source: Path, no_visible: bool, as_json: bo
     help="Cap long side (px) before diffusion; 0 = native (best quality, like raiw.cc). Raise only on GPU/MPS OOM.",
 )
 @click.option(
-    "--protect-text",
+    "--no-protect-text",
     is_flag=True,
     default=False,
-    help="Preserve detected text (incl. CJK) via Differential Diffusion. SDXL default pipeline only.",
+    help="Disable automatic text protection (text/CJK is preserved by default on the SDXL pipeline).",
 )
 @click.pass_context
 def cmd_all(
@@ -701,7 +701,7 @@ def cmd_all(
     hf_token: str | None,
     humanize: float,
     max_resolution: int,
-    protect_text: bool,
+    no_protect_text: bool,
 ) -> None:
     """Remove ALL watermarks: visible + invisible + metadata.
 
@@ -793,7 +793,7 @@ def cmd_all(
                 num_inference_steps=steps,
                 seed=seed,
                 humanize=humanize,
-                protect_text=protect_text,
+                protect_text=not no_protect_text,
                 max_resolution=max_resolution,
             )
             console.print("    [green]✓[/] Invisible watermark removed")

src/remove_ai_watermarks/invisible_engine.py

@@ -125,7 +125,7 @@ class InvisibleEngine:
         seed: int | None = None,
         humanize: float = 0.0,
         protect_faces: bool = True,
-        protect_text: bool = False,
+        protect_text: bool = True,
         max_resolution: int = 0,
     ) -> Path:
         """Remove invisible watermark from an image.
@@ -139,8 +139,9 @@ class InvisibleEngine:
             seed: Random seed for reproducibility.
             humanize: Intensity of Analog Humanizer film grain (0 = off).
             protect_faces: Boolean to extract and restore faces intact.
-            protect_text: Preserve detected text regions via Differential
-                Diffusion so glyphs (incl. CJK) survive the removal pass.
+            protect_text: Detect text regions and preserve them via Differential
+                Diffusion when any are found, so glyphs (incl. CJK) survive the
+                removal pass. On by default; the detector decides per image.
             max_resolution: Cap the long side (px) before diffusion. 0 (default)
                 = native resolution, no pre-downscale -- matches the hosted
                 raiw.cc backend. Set a positive value only to bound GPU/MPS

src/remove_ai_watermarks/noai/watermark_remover.py

@@ -387,7 +387,7 @@ class WatermarkRemover:
         num_inference_steps: int = 50,
         guidance_scale: float | None = None,
         seed: int | None = None,
-        protect_text: bool = False,
+        protect_text: bool = True,
     ) -> Path:
         """Remove watermark from an image using regeneration attack.
 
@@ -398,8 +398,10 @@ class WatermarkRemover:
             num_inference_steps: Number of denoising steps.
             guidance_scale: Classifier-free guidance scale.
             seed: Random seed for reproducibility.
-            protect_text: Preserve detected text regions via Differential
-                Diffusion (SDXL default profile only). Off by default.
+            protect_text: Detect text regions and preserve them via Differential
+                Diffusion when any are found (SDXL default profile only). On by
+                default; the detector decides per image, and text-free inputs run
+                the standard pass at no extra cost.
 
         Returns:
             Path to the cleaned image.
@@ -458,8 +460,8 @@ class WatermarkRemover:
             )
         else:
             if protect_text:
-                logger.warning(
-                    "protect_text requested but unavailable "
+                logger.debug(
+                    "Text protection unavailable "
                     "(needs the SDXL default model and the cv2 text detector); "
                     "running standard img2img."
                 )
@@ -611,6 +613,10 @@ class WatermarkRemover:
             logger.warning("Text detection failed (%s); running standard img2img.", exc)
             return self._run_img2img(init_image, strength, num_inference_steps, guidance_scale, generator)
 
+        if not boxes:
+            self._set_progress("No text detected; running standard img2img.")
+            return self._run_img2img(init_image, strength, num_inference_steps, guidance_scale, generator)
+
         width, height = init_image.size
         change_map = text_protector.build_change_map(boxes, height, width)
         self._set_progress(f"Protecting {len(boxes)} text region(s) via Differential Diffusion...")