diff --git a/core/dr-face/src/detect.rs b/core/dr-face/src/detect.rs
index e1d9881..e6727a9 100644
--- a/core/dr-face/src/detect.rs
+++ b/core/dr-face/src/detect.rs
@@ -46,13 +46,13 @@ pub struct DetectOptions {
     /// it is measured on the aligned crop rather than the box. This one exists
     /// only to throw away the obviously hopeless before paying for a warp, so
     /// it is deliberately set *below* what the real floor will accept: the
-    /// aligned crop spans roughly 1.3x the box's shorter edge, so 48 here
-    /// cannot reject a face that would have cleared 64 there.
+    /// aligned crop spans roughly 1.3x the box's shorter edge, so 24 here
+    /// cannot reject a face that would have cleared 32 there.
     pub min_face_px: f32,
     /// Smallest face the embedder may be given, in **source pixels across the
     /// aligned crop** — `crop_px` in the catalog.
     ///
-    /// The honest statement of "a face must be at least 64x64", because this is
+    /// The honest statement of "a face must be at least 32x32", because this is
     /// the number of real pixels behind the 112x112 the model actually sees.
     /// The box's own size is not that: the ArcFace template reaches past the
     /// box for forehead and chin, so a 64-pixel box and a 64-pixel crop are
@@ -74,6 +74,26 @@ pub struct DetectOptions {
     /// and a caller cannot enable one gate while forgetting the other.
     ///
     /// Zero disables it, which is what a measurement run wants.
+    ///
+    /// # It has to move with the size floor
+    ///
+    /// The two are coupled, because an upsampled face scores low here whatever
+    /// its original sharpness. Measured over the reference library, with the
+    /// size floor at 32 source pixels:
+    ///
+    /// | min sharpness | of what the size floor left, this removes |
+    /// |---|---|
+    /// | 0.002 | 3% |
+    /// | 0.005 | 8% |
+    /// | 0.010 | 16% |
+    /// | 0.020 | 27% |
+    ///
+    /// At a 64-pixel floor, 0.020 removed 7% — the same *kind* of face, the
+    /// large-but-soft one this gate exists for. Holding 0.020 while dropping
+    /// the size floor to 32 would have thrown away a quarter of the newly
+    /// admitted faces for being small rather than for being blurred, undoing
+    /// most of the point of lowering it. 0.005 removes 8% at 32, which is the
+    /// same job.
     pub min_sharpness: f32,
 }
 
@@ -82,9 +102,9 @@ impl Default for DetectOptions {
         Self {
             confidence: 0.5,
             nms_iou: 0.4,
-            min_face_px: 48.0,
-            min_source_px: 64.0,
-            min_sharpness: 0.020,
+            min_face_px: 24.0,
+            min_source_px: 32.0,
+            min_sharpness: 0.005,
         }
     }
 }
diff --git a/ui/dr-ui/examples/face_index.rs b/ui/dr-ui/examples/face_index.rs
index 1e9ac70..7c1f4a9 100644
--- a/ui/dr-ui/examples/face_index.rs
+++ b/ui/dr-ui/examples/face_index.rs
@@ -464,13 +464,14 @@ fn report_quality(
     println!("{}", "-".repeat(52));
     for (min_px, min_sharp) in [
         (0.0_f32, 0.0_f32),
-        (64.0, 0.0),
-        (0.0, 0.010),
-        (64.0, 0.005),
+        (32.0, 0.0),
+        (32.0, 0.002),
+        (32.0, 0.005),
+        (32.0, 0.010),
+        (32.0, 0.020),
+        (48.0, 0.005),
         (64.0, 0.010),
         (64.0, 0.020),
-        (80.0, 0.010),
-        (96.0, 0.010),
     ] {
         let by_size = found.iter().filter(|f| f.0 < min_px).count();
         let by_blur = found