Add the sdxl-zimage profile: the same recipe on an SDXL global stage

SdxlZImagePipeline subclasses QwenZImagePipeline and overrides only _run_global
and preload, so the face stage is inherited rather than copied and cannot drift
between the two profiles. A test asserts the shared methods are the same objects.

Four things are architecture-bound and swap with the model: the ControlNet, the
four-step distillation LoRA (SDXL-Lightning at its documented 1.0, not the
reference graph's 0.8, which belongs to a different LoRA), the sampler (Euler
trailing, no AuraFlow shift), and the latent grid at 8 px against Qwen's 16.

Strength is architecture-bound too, which is the easy mistake and cost two wrong
conclusions before it was caught. An SDXL global pass leaves SynthID at the
strength Qwen needs: through the Gemini app on a native 2816x1536 original, 0.154
is FOUND while 0.20, 0.25 and 0.30 are clean. The profile therefore takes a flat
vendor policy - OpenAI 0.15, Gemini 0.25, unknown following Gemini - rather than
resolution_adaptive_denoise, because flat values are what was measured and no
size dependence has been established for this stage.

requested_steps exists because the runtimes truncate differently: DiffSynth sets
sigma_start = denoising_strength and runs every requested step, while Diffusers
img2img truncates the step count, so four steps at 0.15 executes zero and returns
a bare VAE round-trip.

Also records both measured provider boundaries for the shipped qwen-zimage curve
- OpenAI detected at 0.06 and clean from 0.08, Gemini detected at 0.08 and clean
from 0.10 - together with the two low-resolution Gemini verdicts that explain why
the curve's sub-1 MP rungs are not under-driven despite looking short against a
boundary measured at 4.33 MP. The curve is left unchanged; nothing measured fails.

The profile is not deployed and not production-ready: every verdict so far comes
from one fixture and one seed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

src/remove_ai_watermarks/invisible_engine.py

@@ -107,7 +107,9 @@ class InvisibleEngine:
                 flat-graphic content), or "qwen" (Qwen-Image 20B img2img, best text/
                 structure preservation but CUDA/cloud-class), or "qwen-zimage"
                 (Qwen-Image-2512 Lightning + Canny, then SAM-masked Z-Image face
-                repair; CUDA-only). "default" aliases "sdxl".
+                repair; CUDA-only), or "sdxl-zimage" (the same recipe and the same face
+                stage on an SDXL global pass, vendor-adaptive strength because an SDXL
+                global stage needs more of it; CUDA-only). "default" aliases "sdxl".
             hf_token: HuggingFace API token.
             progress_callback: Optional callback for progress messages.
             controlnet_conditioning_scale: ControlNet structure-preservation
@@ -238,7 +240,7 @@ class InvisibleEngine:
 
         if num_inference_steps is None:
             profile = getattr(self._remover, "model_profile", None)
-            num_inference_steps = 4 if profile == "qwen-zimage" else 100
+            num_inference_steps = 4 if profile in {"qwen-zimage", "sdxl-zimage"} else 100
         profile = getattr(self._remover, "model_profile", "controlnet")
         seed = resolve_seed(seed, profile)
 
@@ -266,7 +268,7 @@ class InvisibleEngine:
         # Keep an explicit max cap available for callers, but do not apply the SDXL
         # 1024px minimum-resolution floor to this profile.
         effective_min_resolution = (
-            0 if getattr(self._remover, "model_profile", None) == "qwen-zimage" else min_resolution
+            0 if getattr(self._remover, "model_profile", None) in {"qwen-zimage", "sdxl-zimage"} else min_resolution
         )
         target = _target_size(
             image.width,
@@ -392,7 +394,7 @@ class InvisibleEngine:
         """Remove invisible watermarks from all images in a directory."""
         if steps is None:
             profile = getattr(self._remover, "model_profile", None)
-            steps = 4 if profile == "qwen-zimage" else 50
+            steps = 4 if profile in {"qwen-zimage", "sdxl-zimage"} else 50
         return self._remover.remove_watermark_batch(
             input_dir=input_dir,
             output_dir=output_dir,