Register RunningHub, Baidu, and LibLibAI visible marks; park Qingyan and MiniMax (measured)

New engines, each calibrated on its TC260 USCC cohort and validated by a
full-corpus sweep (42009 files):
- runninghub: top-left corner (new corner="tl"), faint mid-gray text via
  the new raw-grayscale "gray" detection front-end, anchor-position gate
- baidu: text-run-only template (pill is a bright-blob magnet), load-bearing
  Doubao+Qwen rival margins, corner-extended footprint for the white tag
- liblib: bottom-center (new corner="bc"), Arial silhouette (font is the
  discriminative lever against latin UI text), logo-extended footprint

Qingyan parked (no clean-arm separation at any render/box), MiniMax/Hailuo
parked (1 visible frame, the xinghui rule); silhouettes kept as starting
points.

src/remove_ai_watermarks/_text_mark_engine.py

@@ -97,7 +97,9 @@ class TextMarkConfig:
 
     name: str  # short label for log lines (e.g. "Doubao")
     asset_name: str  # bundled alpha PNG under assets/ (e.g. "doubao_alpha.png")
-    corner: Literal["br", "bl"]  # bottom-right (Doubao/Jimeng) or bottom-left (Samsung)
+    corner: Literal[
+        "br", "bl", "tl", "bc"
+    ]  # bottom-right (Doubao/Jimeng), bottom-left (Samsung), top-left (RunningHub), bottom-center (LibLibAI)
     margin_floor: int  # min margin in px for locate (4 for br marks, 2 for Samsung)
     # locate geometry (fraction of scale_base -- see scale_base())
     width_frac: float
@@ -125,7 +127,12 @@ class TextMarkConfig:
     # correlates a binary silhouette against it; "tophat" correlates the CONTINUOUS
     # top-hat response against a soft template and never binarizes. See
     # TextMarkEngine.tophat_response for the measurement that motivated the split.
-    detect_frontend: Literal["binary", "tophat"] = "binary"
+    # "gray" correlates the silhouette against the raw GRAYSCALE of the locate box:
+    # for a faint mid-gray mark (RunningHub) the top-hat's background-subtraction and
+    # max-normalization suppress the response to clean-arm levels (positives 0.16-0.23
+    # vs clean p99 0.31), while raw gray NCC separates (positives 0.38-0.54 vs clean
+    # p99 0.264 / max 0.304, measured 2026-07-22). Contrast-DEPENDENT, unlike tophat.
+    detect_frontend: Literal["binary", "tophat", "gray"] = "binary"
     # Gaussian sigma applied to the template in the "tophat" front-end (0 = none).
     template_blur: float = 0.0
     # Which image dimension the mark's size and margins scale with. VENDOR-SPECIFIC,
@@ -391,6 +398,42 @@ class TextMarkEngine:
         """The detection score alone -- the box the removal mask needs is discarded here."""
         return self._tophat_best(image, loc)[0]
 
+    def _gray_best(self, image: NDArray[Any], loc: TextMarkLocation) -> tuple[float, tuple[int, int, int, int] | None]:
+        """Best TM_CCOEFF_NORMED of the silhouette against the raw GRAYSCALE ROI, and
+        the ROI-local box (x0, y0, x1, y1) of that best match.
+
+        Mirrors :meth:`_tophat_best` (same ladder sweep, same one-method contract so
+        detection and the removal mask can never drift), but skips the top-hat
+        entirely: the RunningHub mark is a faint mid-gray text the top-hat's
+        background subtraction suppresses to clean-arm levels, while raw gray NCC
+        separates (see ``TextMarkConfig.detect_frontend``). Contrast-DEPENDENT by
+        construction, so the gate must be picked against the clean arm, which is
+        what ``scripts/vendor_mark_calibrate.py`` does.
+        """
+        c = self.config
+        x, y, bw, bh = loc.bbox
+        if bh < 16 or bw < 16:
+            return (0.0, None)
+        roi = cv2.cvtColor(image_io.to_bgr(image[y : y + bh, x : x + bw]), cv2.COLOR_BGR2GRAY)
+        sil = self._glyph_silhouette()
+        if sil is None:
+            return (0.0, None)
+        base = self.scale_base(image)
+        best_score = 0.0
+        best_box: tuple[int, int, int, int] | None = None
+        for scale in c.ladder:
+            gw = max(c.min_gw, int(c.alpha_width_frac * base * scale))
+            gh = max(4, int(c.alpha_height_frac * base * scale))
+            if gw >= roi.shape[1] or gh >= roi.shape[0]:
+                continue
+            tmpl = cv2.resize(sil, (gw, gh), interpolation=cv2.INTER_AREA)
+            result = cv2.matchTemplate(roi, tmpl, cv2.TM_CCOEFF_NORMED)
+            _, score, _, top_left = cv2.minMaxLoc(result)
+            if score > best_score:
+                tx, ty = int(top_left[0]), int(top_left[1])
+                best_score, best_box = float(score), (tx, ty, tx + gw - 1, ty + gh - 1)
+        return (best_score, best_box)
+
     def scale_base(self, image: NDArray[Any]) -> int:
         """The image dimension this mark's geometry scales with.
 
@@ -433,8 +476,14 @@ class TextMarkEngine:
         wm_h = max(16, int(base * c.height_frac))
         margin_x = max(c.margin_floor, int(base * c.margin_x_frac))
         margin_b = max(c.margin_floor, int(base * c.margin_bottom_frac))
-        x = max(0, w - margin_x - wm_w) if c.corner == "br" else min(margin_x, max(0, w - wm_w))
-        y = max(0, h - margin_b - wm_h)
+        if c.corner == "br":
+            x = max(0, w - margin_x - wm_w)
+        elif c.corner == "bc":  # bottom-center: horizontally centered, margin_x unused
+            x = max(0, (w - wm_w) // 2)
+        else:
+            x = min(margin_x, max(0, w - wm_w))
+        # "tl" anchors at the top instead: margin_bottom_frac is then the TOP margin.
+        y = min(margin_b, max(0, h - wm_h)) if c.corner == "tl" else max(0, h - margin_b - wm_h)
         wm_w = min(wm_w, w - x)
         wm_h = min(wm_h, h - y)
         return TextMarkLocation(x=x, y=y, w=wm_w, h=wm_h, is_fallback=True)
@@ -526,6 +575,15 @@ class TextMarkEngine:
             det.detected = score >= threshold and self._rival_margin_ok(score, box, self.scale_base(image))
             logger.debug("%s detect (tophat): ncc=%.2f thr=%.2f detected=%s", c.name, score, threshold, det.detected)
             return det
+        if c.detect_frontend == "gray":
+            # Same no-coverage-gate reasoning as tophat: the gray front-end never
+            # binarizes, so a blob-area heuristic does not apply to it either.
+            score = self._gray_best(image, loc)[0]
+            threshold = c.detect_ncc_threshold * (c.provenance_ncc_factor if provenance else 1.0)
+            det.confidence = score
+            det.detected = score >= threshold and self._rival_margin_ok(score, box, self.scale_base(image))
+            logger.debug("%s detect (gray): ncc=%.2f thr=%.2f detected=%s", c.name, score, threshold, det.detected)
+            return det
         if coverage >= c.detect_min_coverage:
             score = self._template_match_score(box, self.scale_base(image))
             threshold = c.detect_ncc_threshold * (c.provenance_ncc_factor if provenance else 1.0)
@@ -578,7 +636,14 @@ class TextMarkEngine:
         glyph = self.extract_mask(image, loc)  # box-sized, 255 = glyph
         ys, xs = np.where(glyph > 0)
         box: tuple[int, int, int, int] | None = None
-        if xs.size >= self._MIN_GLYPH_PIXELS:
+        if self.config.detect_frontend == "gray" and self.detect(image).detected:
+            # The gray front-end exists for marks the top-hat under-segments, so the
+            # binary blob is NOT authoritative here: trusting it first bounded the
+            # fill by a PARTIAL blob (the faint head glyphs dropped out) and left the
+            # leftmost "Runni" of "RunningHub AI生成" unremoved (2026-07-22). Use the
+            # detector's own best-match box, same as the tophat faint path below.
+            _, box = self._gray_best(image, loc)
+        elif xs.size >= self._MIN_GLYPH_PIXELS:
             box = (int(xs.min()), int(ys.min()), int(xs.max()), int(ys.max()))
         elif self.config.detect_frontend == "tophat" and self.detect(image).detected:
             # A mark found only by the CONTINUOUS front-end has no binary glyph blob to

src/remove_ai_watermarks/baidu_engine.py

@@ -0,0 +1,203 @@
+"""Baidu visible watermark detector/localizer.
+
+Baidu stamps its generations with a white bold "百度" text run plus a separate
+white rounded tag carrying dark "AI生成", bottom-right -- the China TC260
+explicit AIGC label. Detection keys on the **百度 text run only**: a
+two-component template (text + pill tag) was measured and REJECTED -- the solid
+white pill is a bright-blob magnet and both front-ends scored the clean arm at
+cohort levels (tophat clean p95 0.445 / gray clean p95 0.487 vs cohort ~0.5,
+2026-07-22). The text-only silhouette separates cleanly (below). The white tag
+is still removed with the mark: the fill blob covers both bright components in
+the corner box.
+
+Removal is the shared **localize -> fill** (:meth:`footprint_mask` ->
+``region_eraser``). This module supplies only Baidu's tuned
+:class:`TextMarkConfig` (``assets/baidu_alpha.png`` -- a font-rendered
+synthetic silhouette from ``scripts/render_vendor_silhouettes.py``, never cut
+from an upload).
+
+Measured on the vendor cohort (16 TC260 carriers whose producer USCC
+91110000802100433B names Baidu, harvested 2026-07-22 by
+``scripts/vendor_cohort_harvest.py``), NOT inherited from Doubao:
+
+  * The 百度 text run is 0.090 of the SHORT side wide (measured on 720/768/
+    1024-px frames), with its right edge ~0.099 of short off the right edge
+    (the pill tag sits between the text and the corner), bottom margin
+    ~0.006; the locate box below covers the whole mark (text + tag).
+  * Gate 0.43 (tophat front-end): on 278 hand-labelled clean frames
+    (cohort-contamination-guarded) the max is 0.352 / p99 0.314, and the
+    visibly-marked cohort frames score 0.386-0.65. Picked over the clean-arm
+    0.37 after a full-corpus check on the 741-frame blind-labelled eval set
+    surfaced 13 cross-fires at 0.38-0.43 (12 Qwen marks + one 抖音 mark) --
+    see DETECT_NCC_THRESHOLD below. At 0.43 the cohort keeps 7 detections
+    (0.61-0.65) and the whole 741 set fires only on the true Baidu frame.
+  * STRICT ONLY (``provenance_ncc_factor`` 1.0): the cohort is small (16) and
+    the sub-gate band is unmeasured, so no provenance relaxation exists.
+"""
+# The module-level _alpha_template / _glyph_silhouette / _template_match_score below
+# are thin test-facing shims (imported by tests/), so pyright's src-only pass sees them
+# as unused; the use is cross-module.
+# pyright: reportUnusedFunction=false
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from remove_ai_watermarks import _text_mark_engine
+from remove_ai_watermarks._text_mark_engine import TextMarkConfig, TextMarkDetection, TextMarkEngine
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from numpy.typing import NDArray
+
+# Locate geometry as a fraction of the image SHORT side (measured basis). The
+# box covers the text run AND the pill tag to its right (tag right edge ~0.002
+# off the frame edge, text run left edge ~0.19 off).
+WM_WIDTH_FRAC = 0.25
+WM_HEIGHT_FRAC = 0.07
+MARGIN_RIGHT_FRAC = 0.002
+MARGIN_BOTTOM_FRAC = 0.002
+
+# Glyph appearance: white bold text on a usually-darker background (white
+# top-hat), same overlay class as Doubao -- inherited, harmless because the
+# tophat front-end turns these gates into weights.
+MAX_SATURATION = 55
+LOGO_MIN_LUMA = 150
+TOPHAT_DELTA = 12
+
+DETECT_MIN_COVERAGE = 0.04  # unused by the tophat front-end (kept for config parity)
+# Calibrated 2026-07-22 on the vendor cohort vs 278 hand-labelled clean frames
+# (clean p99 0.314 / max 0.352), THEN raised 0.37 -> 0.43 after a full-corpus
+# check: on the 741-frame blind-labelled eval set the 0.37 gate fired 14 times
+# outside the cohort, and only ONE was the vendor -- 12 were 千问AI生成 (Qwen)
+# marks (the 百/千 first glyphs are near-identical after binarization) and one
+# was a 抖音 AI创作 mark at 0.425. The Qwen fires are handled by the rival
+# margin (Qwen scores 0.58-0.76 there, beating Baidu by 0.17-0.35), but the
+# 抖音 one named no registered rival, so the gate moved above it. Cost: the
+# cohort's low trio at 0.386 (3 genuine marks) -- precision over recall on a
+# small cohort. Raised again 0.43 -> 0.48 after the full-corpus sweep
+# (2026-07-22): outside-cohort true Baidu carriers score 0.50-0.66 while the
+# false fires (大众点评 UI, a math blackboard, an 80s banner, a checkerboard)
+# top out at 0.47. Remaining cohort detections: 7 at 0.61-0.65, plus the 6
+# metadata-stripped true carriers the cohort cannot see.
+DETECT_NCC_THRESHOLD = 0.48
+
+# Detection-silhouette geometry (fraction of the short side): the 百度 text run
+# only, measured 0.090 wide with aspect 0.51.
+_ALPHA_WIDTH_FRAC = 0.090
+_ALPHA_HEIGHT_FRAC = 0.046
+
+# Tight ladder: the NCC comb is sharp in size (see runninghub_engine), so the
+# nominal sits exactly on the measured 0.090 with +-5% rungs.
+_LADDER = (0.95, 1.0, 1.05)
+
+_CONFIG = TextMarkConfig(
+    name="Baidu",
+    asset_name="baidu_alpha.png",
+    corner="br",
+    margin_floor=4,
+    width_frac=WM_WIDTH_FRAC,
+    height_frac=WM_HEIGHT_FRAC,
+    margin_x_frac=MARGIN_RIGHT_FRAC,
+    margin_bottom_frac=MARGIN_BOTTOM_FRAC,
+    max_saturation=MAX_SATURATION,
+    logo_min_luma=LOGO_MIN_LUMA,
+    tophat_delta=TOPHAT_DELTA,
+    morph_open_size=5,
+    detect_min_coverage=DETECT_MIN_COVERAGE,
+    detect_ncc_threshold=DETECT_NCC_THRESHOLD,
+    detect_frontend="tophat",
+    scale_basis="short",
+    ladder=_LADDER,
+    alpha_width_frac=_ALPHA_WIDTH_FRAC,
+    alpha_height_frac=_ALPHA_HEIGHT_FRAC,
+    min_gw=8,
+    # Load-bearing rival margins (crossfire measured 2026-07-22): the 百度 and
+    # 豆包 silhouettes share their second glyph and a similar first, and 百度 vs
+    # 千问 are near-identical after binarization -- at the 0.37 gate this
+    # template fires on 45.8% of 400 Doubao-marked frames AND on Qwen-marked
+    # frames at 0.38-0.43. Doubao's template beats it by ~0.56 on Doubao marks,
+    # Qwen's by 0.17-0.35 on Qwen marks, so the 0.10 margin suppresses all of
+    # that crossfire at zero genuine-Baidu cost (cohort fire+m == fire).
+    rivals=("doubao_alpha.png", "qwen_alpha.png"),
+    # STRICT ONLY: small cohort, the relaxed band is unmeasured.
+    provenance_ncc_factor=1.0,
+)
+
+BaiduDetection = TextMarkDetection
+
+
+def _alpha_template() -> NDArray[Any] | None:
+    """The bundled Baidu alpha template (float [0,1]), or None."""
+    return _text_mark_engine.load_alpha_template(_CONFIG.asset_name)
+
+
+def _glyph_silhouette() -> NDArray[Any] | None:
+    """Binary "百度" silhouette (255 = glyph) from the alpha map, or None."""
+    return _text_mark_engine.glyph_silhouette(_CONFIG.asset_name)
+
+
+def _template_match_score(box_mask: NDArray[Any], scale_base: int) -> float:
+    """TM_CCOEFF_NORMED of the Baidu glyph silhouette against ``box_mask``."""
+    return _text_mark_engine.template_match_score(box_mask, scale_base, _CONFIG)
+
+
+class BaiduEngine(TextMarkEngine):
+    """Detect/localize the visible Baidu "百度 AI生成" mark (bottom-right; localize -> fill)."""
+
+    def __init__(self) -> None:
+        super().__init__(_CONFIG)
+
+    def footprint_mask(
+        self, image: NDArray[Any] | None, *, force: bool = False, dilate: int | None = None
+    ) -> NDArray[Any] | None:
+        """Full-frame mask of the WHOLE mark (text run + the pill tag to its right).
+
+        The base class's blob-bbox footprint UNDERCOVERS this mark: the white tag's
+        flat interior gives no top-hat response (a top-hat answers edges, not flats),
+        so the blob ends at the text run and the fill leaves the tag's right half as
+        a ghost (measured 2026-07-22 on the 768x1024 cohort frame: blob bbox x
+        632..746 vs the tag ending ~758). The layout is measured and fixed -- the
+        text run is at the left of the locate box, the tag runs to the corner -- so
+        the footprint is the detector's match box extended RIGHT to the corner.
+        """
+        if image is None or image.size == 0:
+            return None
+
+        from remove_ai_watermarks import image_io, region_eraser
+
+        image = image_io.to_bgr(image)
+        h, w = image.shape[:2]
+        if h < 32 or w < 64:
+            return None
+        loc = self.locate(image)
+        bx, by, bw, bh = loc.bbox
+        if force:
+            rx1, ry1, rx2, ry2 = bx, by, min(w, bx + bw), min(h, by + bh)
+        else:
+            if not self.detect(image).detected:
+                return None
+            _, box = self._tophat_best(image, loc)
+            if box is None:
+                return None
+            gx0, gy0, _gx1, gy1 = box
+            pad = max(4, int(0.15 * bh))
+            rx1 = max(0, bx + gx0 - pad)
+            ry1 = max(0, by + gy0 - pad)
+            rx2 = min(w, bx + bw)  # the tag runs to the corner end of the box
+            ry2 = min(h, by + gy1 + 1 + pad)
+        if rx1 >= rx2 or ry1 >= ry2:
+            return None
+        d = dilate if dilate is not None else max(3, int(0.02 * bw))
+        return region_eraser.boxes_to_mask((h, w), [(rx1, ry1, rx2 - rx1, ry2 - ry1)], dilate=d)
+
+
+def load_image_bgr(path: str | Path) -> NDArray[Any]:
+    """Read an image as BGR ndarray (helper for scripts/tests)."""
+    from remove_ai_watermarks import image_io
+
+    img = image_io.imread(path)
+    if img is None:
+        raise FileNotFoundError(f"Failed to read image: {path}")
+    return img

src/remove_ai_watermarks/identify.py

@@ -449,6 +449,9 @@ _VISIBLE_MARK_PLATFORM = {
     "qwen": "Alibaba Tongyi Qianwen (visible 千问AI生成 mark detected)",
     "kling": "Kuaishou Kling (visible 可灵AI 3.0 mark detected)",
     "samsung": "Samsung Galaxy AI (visible 'Contenuti generati dall'AI' mark detected)",
+    "runninghub": "RunningHub (visible RunningHub AI生成 mark detected)",
+    "baidu": "Baidu (visible 百度 AI生成 mark detected)",
+    "liblib": "LibLibAI (visible LibLibAI mark detected)",
 }
 
 

src/remove_ai_watermarks/liblib_engine.py

@@ -0,0 +1,189 @@
+"""LibLibAI visible watermark detector/localizer.
+
+LibLibAI (哩布哩布AI, USCC 91110105MACJ6K1C8A) stamps its generations with a
+white triangle logo + "LibLibAI" latin wordmark at **bottom-center** (not a
+corner -- the locate box is horizontally centered). Detection matches the
+bundled font-rendered "LibLibAI" silhouette (the triangle logo is NOT rendered
+-- logos vary, the wordmark discriminates); removal is the shared **localize ->
+fill** (the glyph blob covers logo + wordmark, both bright).
+
+This module supplies only LibLibAI's tuned :class:`TextMarkConfig`
+(``assets/liblib_alpha.png`` from ``scripts/render_vendor_silhouettes.py``,
+never cut from an upload).
+
+Measured on the vendor cohort (15 TC260 carriers, harvested 2026-07-22 by
+``scripts/vendor_cohort_harvest.py``), NOT inherited from Doubao:
+
+  * The wordmark is ~0.10 of the frame WIDTH wide, centered horizontally, its
+    baseline ~0.94-0.95 of the height; consistent across 768..2240-px frames.
+  * The silhouette font is Arial, NOT the STHeiti the CJK marks use: the real
+    wordmark is a grotesque, and measured across 7 candidate fonts Arial lifts
+    the cohort positives from 0.31-0.47 to 0.42-0.73 while the full-corpus
+    false arm (latin UI text) drops to max 0.398. A 200x200 icon false-fired
+    at 0.444, so a per-mark size floor (``_MIN_SHORT_SIDE``) backs the gate.
+  * Gate 0.42 (tophat front-end): false arm max 0.398, cohort 0.43-0.59.
+  * STRICT ONLY (``provenance_ncc_factor`` 1.0): small cohort, the relaxed band
+    is unmeasured.
+"""
+# The module-level _alpha_template / _glyph_silhouette / _template_match_score below
+# are thin test-facing shims (imported by tests/), so pyright's src-only pass sees them
+# as unused; the use is cross-module.
+# pyright: reportUnusedFunction=false
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from remove_ai_watermarks import _text_mark_engine
+from remove_ai_watermarks._text_mark_engine import TextMarkConfig, TextMarkDetection, TextMarkEngine
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from numpy.typing import NDArray
+
+# Locate geometry as a fraction of the image WIDTH (measured basis). The box is
+# horizontally centered (corner="bc") and covers the logo + wordmark with NCC
+# slack around the measured 0.10 width.
+WM_WIDTH_FRAC = 0.20
+WM_HEIGHT_FRAC = 0.09
+MARGIN_BOTTOM_FRAC = 0.02
+
+# Glyph appearance: white wordmark on a usually-darker background (white
+# top-hat), same overlay class as Doubao -- inherited, harmless because the
+# tophat front-end turns these gates into weights.
+MAX_SATURATION = 55
+LOGO_MIN_LUMA = 150
+TOPHAT_DELTA = 12
+
+DETECT_MIN_COVERAGE = 0.04  # unused by the tophat front-end (kept for config parity)
+# Calibrated 2026-07-22 on the vendor cohort vs 286 hand-labelled clean frames
+# (clean p99 0.315 / max 0.367) and re-measured after the font fix: the wordmark
+# is set in an Arial-class grotesque, and the Arial silhouette lifts the cohort
+# positives to 0.43-0.59 while the full-corpus false arm (latin UI text bands,
+# website screenshots) drops to max 0.398 -- generic latin text matches the
+# wrong font less, which is exactly where the discrimination comes from. Gate
+# 0.42 keeps all 8 marked cohort frames with a 0.022 margin over the false arm.
+DETECT_NCC_THRESHOLD = 0.42
+
+# Detection-silhouette geometry (fraction of the frame width): the wordmark,
+# measured 0.10 wide with aspect 0.26.
+_ALPHA_WIDTH_FRAC = 0.10
+_ALPHA_HEIGHT_FRAC = 0.026
+
+# Tight ladder: the NCC comb is sharp in size (see runninghub_engine).
+_LADDER = (0.9, 1.0, 1.1)
+
+_CONFIG = TextMarkConfig(
+    name="LibLibAI",
+    asset_name="liblib_alpha.png",
+    corner="bc",
+    margin_floor=4,
+    width_frac=WM_WIDTH_FRAC,
+    height_frac=WM_HEIGHT_FRAC,
+    margin_x_frac=0.0,  # unused for corner="bc" (horizontally centered)
+    margin_bottom_frac=MARGIN_BOTTOM_FRAC,
+    max_saturation=MAX_SATURATION,
+    logo_min_luma=LOGO_MIN_LUMA,
+    tophat_delta=TOPHAT_DELTA,
+    morph_open_size=5,
+    detect_min_coverage=DETECT_MIN_COVERAGE,
+    detect_ncc_threshold=DETECT_NCC_THRESHOLD,
+    detect_frontend="tophat",
+    scale_basis="width",
+    ladder=_LADDER,
+    alpha_width_frac=_ALPHA_WIDTH_FRAC,
+    alpha_height_frac=_ALPHA_HEIGHT_FRAC,
+    min_gw=8,
+    # STRICT ONLY: small cohort, the relaxed band is unmeasured.
+    provenance_ncc_factor=1.0,
+)
+
+LibLibDetection = TextMarkDetection
+
+
+def _alpha_template() -> NDArray[Any] | None:
+    """The bundled LibLibAI alpha template (float [0,1]), or None."""
+    return _text_mark_engine.load_alpha_template(_CONFIG.asset_name)
+
+
+def _glyph_silhouette() -> NDArray[Any] | None:
+    """Binary "LibLibAI" silhouette (255 = glyph) from the alpha map, or None."""
+    return _text_mark_engine.glyph_silhouette(_CONFIG.asset_name)
+
+
+def _template_match_score(box_mask: NDArray[Any], scale_base: int) -> float:
+    """TM_CCOEFF_NORMED of the LibLibAI glyph silhouette against ``box_mask``."""
+    return _text_mark_engine.template_match_score(box_mask, scale_base, _CONFIG)
+
+
+class LibLibEngine(TextMarkEngine):
+    """Detect/localize the visible LibLibAI wordmark (bottom-center; localize -> fill)."""
+
+    # Per-mark size floor: the wordmark template is 0.10 of the frame width, so
+    # below ~480px short side it degrades under ~48px -- the one full-corpus
+    # false fire with the final Arial template was a 200x200 icon (0.444, above
+    # the gate, on a 20px template; measured 2026-07-22). The smallest true
+    # carrier in the cohort is 768px.
+    _MIN_SHORT_SIDE = 480
+
+    def __init__(self) -> None:
+        super().__init__(_CONFIG)
+
+    def detect(self, image: NDArray[Any] | None, *, provenance: bool = False) -> TextMarkDetection:
+        if image is None or not image.size or min(image.shape[:2]) < self._MIN_SHORT_SIDE:
+            return TextMarkDetection()
+        return super().detect(image, provenance=provenance)
+
+    def footprint_mask(
+        self, image: NDArray[Any] | None, *, force: bool = False, dilate: int | None = None
+    ) -> NDArray[Any] | None:
+        """Full-frame mask of the logo + wordmark, bounded by the detector's match box.
+
+        The base class's blob-bbox footprint is wrong in both directions here: the
+        blob bleeds UP into bright background structure (on the 768x1024 cohort
+        frame it reached y 931 and the fill ate the shirt's own print) and it does
+        not own the triangle logo anyway. The match box bounds the wordmark exactly
+        (that is what the NCC localized); the logo sits its own height to the LEFT
+        of the text (measured on the cohort zoom: logo ~1.0x the glyph height, gap
+        ~0.3x), so the footprint is the match box extended left by ~1.3 heights.
+        """
+        if image is None or image.size == 0:
+            return None
+        from remove_ai_watermarks import image_io, region_eraser
+
+        image = image_io.to_bgr(image)
+        h, w = image.shape[:2]
+        if h < 32 or w < 64:
+            return None
+        loc = self.locate(image)
+        bx, by, bw, bh = loc.bbox
+        if force:
+            rx1, ry1, rx2, ry2 = bx, by, min(w, bx + bw), min(h, by + bh)
+        else:
+            if not self.detect(image).detected:
+                return None
+            _, box = self._tophat_best(image, loc)
+            if box is None:
+                return None
+            gx0, gy0, gx1, gy1 = box
+            gh = gy1 - gy0 + 1
+            pad = max(3, int(0.25 * gh))
+            rx1 = max(0, bx + gx0 - int(1.3 * gh))  # the triangle logo, left of the text
+            ry1 = max(0, by + gy0 - pad)
+            rx2 = min(w, bx + gx1 + 1 + pad)
+            ry2 = min(h, by + gy1 + 1 + pad)
+        if rx1 >= rx2 or ry1 >= ry2:
+            return None
+        d = dilate if dilate is not None else max(3, int(0.02 * bw))
+        return region_eraser.boxes_to_mask((h, w), [(rx1, ry1, rx2 - rx1, ry2 - ry1)], dilate=d)
+
+
+def load_image_bgr(path: str | Path) -> NDArray[Any]:
+    """Read an image as BGR ndarray (helper for scripts/tests)."""
+    from remove_ai_watermarks import image_io
+
+    img = image_io.imread(path)
+    if img is None:
+        raise FileNotFoundError(f"Failed to read image: {path}")
+    return img

src/remove_ai_watermarks/runninghub_engine.py

@@ -0,0 +1,180 @@
+"""RunningHub visible watermark detector/localizer.
+
+RunningHub (a hosted ComfyUI platform, USCC 91340100MAEB4N8H76) stamps its
+generations with a faint light-gray "RunningHub AI生成" text mark in the
+**top-left** corner -- the China TC260 explicit AIGC label, but placed top-left
+(unlike the GB 45438-2025 house style bottom-right of Doubao/Qwen/Kling) and
+rendered in a mid-gray that the white top-hat front-end suppresses to clean-arm
+levels.
+
+Detection therefore uses the ``gray`` front-end (raw-grayscale silhouette NCC,
+see ``TextMarkConfig.detect_frontend``); removal is the shared **localize ->
+fill** (the detector's best-match box feeds :meth:`footprint_mask` ->
+``region_eraser``). This module supplies only RunningHub's tuned
+:class:`TextMarkConfig` (``assets/runninghub_alpha.png`` -- a font-rendered
+synthetic silhouette from ``scripts/render_vendor_silhouettes.py``, never cut
+from an upload).
+
+EVERY tuned number below was measured on the vendor cohort (73 TC260 carriers
+whose producer USCC names the entity, harvested 2026-07-22 by
+``scripts/vendor_cohort_harvest.py``), NOT inherited from Doubao:
+
+  * Only ~4 of the 73 cohort frames carry a visible mark (the rest are
+    metadata-only TC260 carriers -- the platform labels frames it does not
+    stamp), so recall of visible marks is 4/4 but the cohort fire rate is not
+    a recall estimate. Positions/geometry are consistent across the positives.
+  * The mark's width is ~0.32 of the frame WIDTH (0.319 measured on 832/1080/
+    1536-wide frames) at ~0.008/0.006 x/y margins; the locate box below covers
+    it with NCC slack.
+  * ``alpha_height_frac`` comes from the silhouette aspect (0.128) at the
+    measured width (0.27 * 1.25 rung ~= 0.3375 >= 0.32), per the standing rule
+    that it is measured, not inherited.
+  * STRICT ONLY (``provenance_ncc_factor`` 1.0): raw gray NCC is
+    contrast-DEPENDENT and the sub-gate band of a corner-anchored gray match is
+    unmeasured beyond the clean arm, so no provenance relaxation exists.
+  * Gate 0.34: on 283 hand-labelled clean frames (cohort-contamination-guarded)
+    corner-anchored gray NCC p99 is 0.264 / max 0.304, while the 4 positives
+    score 0.38-0.54. 0.34 sits above the clean max with a small margin; the
+    positives are few, so the margin is deliberately thin on the recall side.
+"""
+# The module-level _alpha_template / _glyph_silhouette / _template_match_score below
+# are thin test-facing shims (imported by tests/), so pyright's src-only pass sees them
+# as unused; the use is cross-module.
+# pyright: reportUnusedFunction=false
+
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING, Any
+
+from remove_ai_watermarks import _text_mark_engine
+from remove_ai_watermarks._text_mark_engine import TextMarkConfig, TextMarkDetection, TextMarkEngine
+
+logger = logging.getLogger(__name__)
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from numpy.typing import NDArray
+
+# Locate geometry as a fraction of the image WIDTH (the measured basis: every
+# positive is portrait, where width == short side). The mark hugs the top-left
+# corner (~0.008 of width off the left edge, ~0.006 of height off the top).
+WM_WIDTH_FRAC = 0.45
+WM_HEIGHT_FRAC = 0.10
+MARGIN_LEFT_FRAC = 0.002
+MARGIN_TOP_FRAC = 0.002
+
+# Glyph appearance fields are unused by the gray front-end (it never binarizes)
+# and kept only for config parity with the other text marks.
+MAX_SATURATION = 55
+LOGO_MIN_LUMA = 150
+TOPHAT_DELTA = 12
+
+DETECT_MIN_COVERAGE = 0.04  # unused by the gray front-end (kept for config parity)
+# Calibrated 2026-07-22 on the vendor cohort vs 283 hand-labelled clean frames:
+# corner-anchored gray NCC, clean p99 0.264 / max 0.304; positives 0.38-0.54.
+DETECT_NCC_THRESHOLD = 0.34
+
+# Detection-silhouette geometry (fraction of the image width), measured on the
+# positives: mark width is ~0.320 of width on all three frame sizes (266px at 832,
+# 345px at 1080, 491px at 1536), and the NCC is razor-sharp in size (0.537 on-size,
+# 0.223 at +5.6% -- the same comb behaviour Qwen measured), so the nominal sits
+# exactly on the measured size with a TIGHT ladder around it, not the shared 3 rungs
+# (whose nearest rung landed 5.6% off and collapsed the match to 0.22).
+_ALPHA_WIDTH_FRAC = 0.32
+_ALPHA_HEIGHT_FRAC = 0.04
+_LADDER = (0.95, 1.0, 1.05)
+
+_CONFIG = TextMarkConfig(
+    name="RunningHub",
+    asset_name="runninghub_alpha.png",
+    corner="tl",
+    margin_floor=4,
+    width_frac=WM_WIDTH_FRAC,
+    height_frac=WM_HEIGHT_FRAC,
+    margin_x_frac=MARGIN_LEFT_FRAC,
+    margin_bottom_frac=MARGIN_TOP_FRAC,  # top margin for corner="tl"
+    max_saturation=MAX_SATURATION,
+    logo_min_luma=LOGO_MIN_LUMA,
+    tophat_delta=TOPHAT_DELTA,
+    morph_open_size=5,
+    detect_min_coverage=DETECT_MIN_COVERAGE,
+    detect_ncc_threshold=DETECT_NCC_THRESHOLD,
+    detect_frontend="gray",
+    scale_basis="width",  # measured: mark width tracks the frame width (0.32)
+    ladder=_LADDER,
+    alpha_width_frac=_ALPHA_WIDTH_FRAC,
+    alpha_height_frac=_ALPHA_HEIGHT_FRAC,
+    min_gw=8,
+    # STRICT ONLY: contrast-dependent gray NCC; the relaxed band is unmeasured.
+    provenance_ncc_factor=1.0,
+)
+
+RunningHubDetection = TextMarkDetection
+
+
+def _alpha_template() -> NDArray[Any] | None:
+    """The bundled RunningHub alpha template (float [0,1]), or None."""
+    return _text_mark_engine.load_alpha_template(_CONFIG.asset_name)
+
+
+def _glyph_silhouette() -> NDArray[Any] | None:
+    """Binary "RunningHub AI生成" silhouette (255 = glyph) from the alpha map, or None."""
+    return _text_mark_engine.glyph_silhouette(_CONFIG.asset_name)
+
+
+def _template_match_score(box_mask: NDArray[Any], scale_base: int) -> float:
+    """TM_CCOEFF_NORMED of the RunningHub glyph silhouette against ``box_mask``."""
+    return _text_mark_engine.template_match_score(box_mask, scale_base, _CONFIG)
+
+
+class RunningHubEngine(TextMarkEngine):
+    """Detect/localize the visible RunningHub "RunningHub AI生成" mark (top-left; localize -> fill)."""
+
+    def __init__(self) -> None:
+        super().__init__(_CONFIG)
+
+    # Anchor window for the match position, as a fraction of the FRAME: the true
+    # mark hugs the corner (measured x 0.008-0.014, y 0.005-0.007 of the frame on
+    # every cohort positive), while the full-corpus false fires (hair, shelves,
+    # window frames, CJK banners -- 37 of 42009 outside-cohort frames at the 0.34
+    # gate, 2026-07-22 sweep) match off-anchor at x 0.013-0.150 / y 0.009-0.045.
+    # No NCC gate separates them (false max 0.384 vs two positives at 0.381), but
+    # position does: every false fire sits outside this window, every positive
+    # inside. Contrast-dependent raw-gray NCC keys on "some text-like structure
+    # anywhere in the box"; the anchor is what makes it about THIS mark.
+    _ANCHOR_MAX_X = 0.025
+    _ANCHOR_MAX_Y = 0.015
+
+    def detect(self, image: NDArray[Any], *, provenance: bool = False) -> TextMarkDetection:
+        det = super().detect(image, provenance=provenance)
+        if not det.detected:
+            return det
+        loc = self.locate(image)
+        _, box = self._gray_best(image, loc)
+        if box is None:
+            det.detected = False
+            return det
+        h, w = image.shape[:2]
+        ax = (loc.x + box[0]) / w
+        ay = (loc.y + box[1]) / h
+        if ax > self._ANCHOR_MAX_X or ay > self._ANCHOR_MAX_Y:
+            logger.debug(
+                "RunningHub detect: score %.3f but match off-anchor (x=%.3f y=%.3f); demoting.",
+                det.confidence,
+                ax,
+                ay,
+            )
+            det.detected = False
+        return det
+
+
+def load_image_bgr(path: str | Path) -> NDArray[Any]:
+    """Read an image as BGR ndarray (helper for scripts/tests)."""
+    from remove_ai_watermarks import image_io
+
+    img = image_io.imread(path)
+    if img is None:
+        raise FileNotFoundError(f"Failed to read image: {path}")
+    return img

src/remove_ai_watermarks/watermark_registry.py

@@ -24,6 +24,9 @@ Entries:
   - ``kling`` -- Kuaishou Kling "可灵AI 3.0" text strip, bottom-right.
   - ``samsung`` -- Samsung Galaxy AI "Contenuti generati dall'AI" strip, bottom-left.
   - ``jimeng_pill`` -- Jimeng-basic "AI生成" pill, top-left (capture-less).
+  - ``runninghub`` -- RunningHub "RunningHub AI生成" text, top-left (gray front-end).
+  - ``baidu`` -- Baidu "百度 AI生成" text + white tag, bottom-right.
+  - ``liblib`` -- LibLibAI "LibLibAI" wordmark, bottom-center.
 """
 
 from __future__ import annotations
@@ -88,6 +91,9 @@ _PRODUCT_OF: dict[str, str] = {
     "qwen": "qwen",
     "kling": "kling",
     "samsung": "samsung",
+    "runninghub": "runninghub",
+    "baidu": "baidu",
+    "liblib": "liblib",
 }
 
 
@@ -373,6 +379,18 @@ def _engine(key: str) -> Any:
             from remove_ai_watermarks.pill_engine import PillEngine
 
             _engines[key] = PillEngine()
+        elif key == "runninghub":
+            from remove_ai_watermarks.runninghub_engine import RunningHubEngine
+
+            _engines[key] = RunningHubEngine()
+        elif key == "baidu":
+            from remove_ai_watermarks.baidu_engine import BaiduEngine
+
+            _engines[key] = BaiduEngine()
+        elif key == "liblib":
+            from remove_ai_watermarks.liblib_engine import LibLibEngine
+
+            _engines[key] = LibLibEngine()
         else:  # pragma: no cover - guarded by the registry keys
             raise KeyError(key)
     return _engines[key]
@@ -517,6 +535,9 @@ _REGISTRY: tuple[KnownMark, ...] = (
     _text_mark("qwen", "Qwen 千问AI生成 text", "bottom-right"),
     _text_mark("kling", "Kling 可灵AI 3.0 text", "bottom-right"),
     _text_mark("samsung", "Samsung Galaxy AI text", "bottom-left"),
+    _text_mark("runninghub", "RunningHub AI生成 text", "top-left"),
+    _text_mark("baidu", "Baidu 百度 AI生成 text", "bottom-right"),
+    _text_mark("liblib", "LibLibAI wordmark", "bottom-center"),
     KnownMark("jimeng_pill", "Jimeng AI生成 pill", "top-left", True, _pill_detect, _pill_mask, _pill_features),
 )
 
@@ -597,7 +618,7 @@ def _keep_pill(keys: set[str], *, provenance: frozenset[str], footprint_flat: bo
     Doubao detection; a Qwen image likewise (another vendor's bottom-right mark naming
     its own product), so a confident Qwen detection suppresses the pill the same way.
     No confirmation at all -> never remove (blocks false fires on non-Jimeng content)."""
-    if "doubao" in keys or "qwen" in keys or "kling" in keys:
+    if "doubao" in keys or "qwen" in keys or "kling" in keys or "runninghub" in keys or "baidu" in keys:
         return False
     if "jimeng" in keys:
         return True