diff --git a/image_actions.py b/image_actions.py
index a397699..dde73f1 100644
--- a/image_actions.py
+++ b/image_actions.py
@@ -223,6 +223,15 @@ def labels_for(category):
     return [label for label, (_, group, _) in ACTIONS.items() if group == category]
 
 
+POSE_NOTES = {
+    "Position - missionary": "She is on her back, he is above her between her legs; NOT cowgirl, NOT sitting, NOT from behind.",
+    "Position - cowgirl": "She is on top of him, he lies on his back; NOT missionary, NOT standing.",
+    "Position - doggy style": "She is on hands and knees, he kneels behind; NOT on her back.",
+    "Position - spooning": "Both lie on their sides, he is behind her back; NOT sitting.",
+    "Oral - cunnilingus": "She lies on her back, he kneels between her legs; NOT standing.",
+}
+
+
 def brief(action, people, camera="auto", place="auto", lighting="auto", outfit="as in the image", style="auto",
           notes="", overrides="", source="input image", instructions=""):
     """The action block appended to the writer's user text."""
@@ -240,6 +249,10 @@ def brief(action, people, camera="auto", place="auto", lighting="auto", outfit="
         lines.append("Keep the identity, face and body of the person from the input image unchanged.")
     if place != "auto":
         lines.append(f"Place: {PLACES[place]}")
+    if count == 2:
+        lines.append("Replace the source pose and furniture entirely: no chair, no upright sitting. Both bodies are horizontal on a bed or the floor unless the action says standing.")
+    if count == 2 and camera == "auto":
+        camera = "side view, full bodies"
     if camera != "auto":
         lines.append(f"Camera: {CAMERAS[camera]}")
     if lighting != "auto":
@@ -254,6 +267,8 @@ def brief(action, people, camera="auto", place="auto", lighting="auto", outfit="
         lines.append(f"Overrides: {overrides.strip()}")
     if action not in ("Position - footjob", "Position - intercrural, between the thighs", "Position - standing 69", "Position - scissoring"):
         lines.append("Show the point where the bodies join.")
+    if action in POSE_NOTES:
+        lines.append(f"Pose: {POSE_NOTES[action]}")
     if instructions.strip():
         lines.append(f"Extra instructions: {instructions.strip()}")
     lines.append("The pose is exactly this arrangement, held still as one frozen frame; do not change it or add another subject. Expand the arrangement with concrete visual detail while keeping every element exactly.")
diff --git a/pyproject.toml b/pyproject.toml
index 556bf04..30f6036 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,7 +1,7 @@
 [project]
 name = "ComfyUI-PromptForge"
 description = "ComfyUI prompt enhancement suite: model/config node with GPU-aware auto settings, prompt enhancer with a preset catalog, and a standalone config finder."
-version = "1.28.28"
+version = "1.28.29"
 license = { file = "LICENSE" }
 dependencies = [
     "transformers",