Use hardcore family metadata in SDXL and captions

caption_naturalizer.py

@@ -5,8 +5,10 @@ import re
 from typing import Any
 
 try:
+    from .hardcore_action_metadata import normalize_hardcore_action_family
     from .prompt_hygiene import sanitize_prose_text
 except ImportError:  # Allows local smoke tests with `python -c`.
+    from hardcore_action_metadata import normalize_hardcore_action_family
     from prompt_hygiene import sanitize_prose_text
 
 
@@ -45,6 +47,28 @@ ITEM_LABELS = (
     "Clothing",
 )
 
+ACTION_FAMILY_CAPTION_LABELS = {
+    "foreplay": "foreplay action",
+    "outercourse": "non-penetrative action",
+    "oral": "oral action",
+    "penetration": "penetrative action",
+    "toy_double": "toy-assisted double-contact action",
+    "climax": "climax action",
+}
+
+POSITION_FAMILY_CAPTION_LABELS = {
+    "penetrative": "penetrative action",
+    "foreplay": "foreplay action",
+    "interaction": "interaction beat",
+    "manual": "manual action",
+    "oral": "oral action",
+    "outercourse": "non-penetrative action",
+    "anal": "anal action",
+    "climax": "climax action",
+    "threesome": "three-person action",
+    "group": "group action",
+}
+
 
 def _clean_text(value: Any) -> str:
     text = "" if value is None else str(value)
@@ -100,6 +124,16 @@ def _human_join(parts: list[str]) -> str:
     return f"{', '.join(parts[:-1])}, and {parts[-1]}"
 
 
+def _metadata_action_label(row: dict[str, Any], default: str = "sexual pose") -> str:
+    position_family = _clean_text(row.get("position_family")).lower()
+    if position_family in POSITION_FAMILY_CAPTION_LABELS:
+        return POSITION_FAMILY_CAPTION_LABELS[position_family]
+    action_family = normalize_hardcore_action_family(row.get("action_family"))
+    if action_family in ACTION_FAMILY_CAPTION_LABELS:
+        return ACTION_FAMILY_CAPTION_LABELS[action_family]
+    return default
+
+
 def _prompt_cast_descriptors(text: str) -> str:
     return _clean_text(text).replace("Woman A / primary creator:", "Woman A:")
 
@@ -508,7 +542,7 @@ def _configured_cast_from_row(row: dict[str, Any], detail_level: str, keep_style
     if role_graph:
         parts.append(role_graph)
     if item:
-        parts.append(f"The sexual pose is {item}")
+        parts.append(f"The {_metadata_action_label(row)} is {item}")
     scene_bits = []
     if scene:
         scene_bits.append(f"set in {scene}")