Strip legacy anchor style note

README.md

@@ -57,11 +57,11 @@
   - Builds one H3 prompt block per beat, with quick controls for per-shot timing, continuity, ref behavior, anchor additions, soundscape, and music while staying compatible with direct text editing.
 
 - `Dumas H3 Prompt Curator`
-  - Inputs: `action_prompt`, `anatomy_guard`, optional `anchor`, optional `soundscape`, optional `ref_1` through `ref_9`
+  - Inputs: `action_prompt`, `anatomy_guard`, `subject_count_guard`, optional `anchor`, optional `soundscape`, optional `ref_1` through `ref_9`
   - Outputs: `prompt`, `ref_image_1` through `ref_image_9`, `reference_count`, `debug`
   - Builds one standalone MiniMax H3 prompt from your final action text plus structured character/location references.
   - The action text can mention references by character/location name, alias, `<Picture N>`, or `<refN>`. Only mentioned references are emitted, and the output images are compacted/renumbered so skipped inputs do not leave gaps.
-  - Adds curated reference context, optional anatomy guard text, anchor/style text, and `overall_soundscape:` text while respecting MiniMax H3's reference-generation shape: one prompt plus up to nine reference images.
+  - Adds curated reference context, anatomy guard text, optional subject-count guard text, anchor/style text, and `overall_soundscape:` text while respecting MiniMax H3's reference-generation shape: one prompt plus up to nine reference images.
 
 - `Dumas H3 Shot Length`
   - Inputs: `shot_seconds`, `fps`, optional `cap_to_h3_max`
@@ -85,13 +85,15 @@
 
 - `Dumas Character Helper`
   - Inputs: `image1`, `image2`, picture IDs, character identity fields, `general`, `wardrobe`
-  - Outputs: `image1`, `image2`, `reference_prompt`, `wardrobe`
-  - Restores the original general-purpose helper shape: pass two images through unchanged and emit prompt text/wardrobe text for manual wiring.
+  - Outputs: `image1`, `image2`, `reference_prompt`, `wardrobe`, `reference1`, `reference2`
+  - Restores the original general-purpose helper shape while also emitting two structured `REFERENCE` objects for the prompt curator.
+  - The structured references carry the same character name, alias, age, height, gender, nationality, occupation, accent, wardrobe, and notes, so mentioning the character name in `Dumas H3 Prompt Curator` can include both helper images and the character facts automatically.
 
 - `Dumas Location Helper`
   - Inputs: `image1`, `image2`, picture IDs, `location_id`, `name`, `alias`, `description`, `general`
-  - Outputs: `image1`, `image2`, `reference_prompt`
-  - Matching general-purpose helper for environments/locations: pass two images through unchanged and emit location reference prompt text.
+  - Outputs: `image1`, `image2`, `reference_prompt`, `reference1`, `reference2`
+  - Matching general-purpose helper for environments/locations: pass two images through unchanged, emit location reference prompt text, and provide two structured `REFERENCE` objects for the prompt curator.
+  - The structured references carry the same location name, alias, description, and notes, so mentioning the location name in `Dumas H3 Prompt Curator` can include both helper images and the location context automatically.
 
 - `Dumas Anchor Style`
   - Inputs: `anchor_style`, `style_description`
@@ -261,7 +263,7 @@ decr  -> use index - 1
 
 `Dumas H3 Plan Attach Scene Images` and `Dumas H3 Plan Extract Scene Images` are a companion pair for `ComfyUI-MiniMaxH3-Contex-Loop` and the local `ref2v` lane. The upstream H3 plan node cannot dynamically grow nine new image sockets for every JSON-defined scene, so Dumas stores scene image bindings beside the plan using a lightweight token and an in-memory registry. That keeps `plan.json` archiving intact while still letting you wire up nine IMAGE sockets per scene through chained helper nodes.
 
-`Dumas Character Helper` is the restored two-image/text helper for general H3 workflows, and `Dumas Location Helper` mirrors it for scene/environment references. The structured `Dumas Character Reference` and `Dumas Location Reference` nodes remain available separately for workflows that want a single `REFERENCE` socket. `Dumas H3 Prompt Curator` consumes those structured references, assigns the final `<Picture N>` numbering, and outputs only the compacted images the prompt actually mentions.
+`Dumas Character Helper` is the restored two-image/text helper for general H3 workflows, and `Dumas Location Helper` mirrors it for scene/environment references. Both helpers also emit structured `REFERENCE` sockets for the curator. The structured `Dumas Character Reference` and `Dumas Location Reference` nodes remain available separately for workflows that want a single `REFERENCE` socket. `Dumas H3 Prompt Curator` consumes those structured references, assigns the final `<Picture N>` numbering, and outputs only the compacted images the prompt actually mentions.
 
 `Dumas Strip Iteration Suffix` keeps the part before the first underscore and drops the rest. Names like `char123_pose_final.png` become `char123.png`, while names with no underscore such as `char123.png` are left untouched.
 

dumas_image_nodes.py

@@ -27,6 +27,12 @@ _H3_PLAN_IMAGE_BINDINGS_CAP = 128
 _H3_PLAN_IMAGE_SLOTS = 9
 _FOLDER_IMAGE_EXTS = (".png", ".jpg", ".jpeg", ".webp", ".bmp", ".gif", ".tiff", ".tif")
 _ANCHOR_STYLE_H3_NOTE = ""
+_ANCHOR_STYLE_LEGACY_NOTE_RE = re.compile(
+    r"\s*Keep this anchor focused on persistent camera language, lighting, "
+    r"texture, environment treatment, and tone; do not name characters or "
+    r"describe one-off actions\.?",
+    re.I,
+)
 _H3_PROMPT_REF_SLOTS = 9
 _H3_PROMPT_MAX_CHARS = 7000
 _PICTURE_TAG_RE = re.compile(r"<\s*picture[\s_\-]*(\d+)\s*>", re.I)
@@ -36,6 +42,10 @@ _ANATOMY_GUARD_TEXT = (
     "and two legs with two feet. Limbs stay attached to the correct body and move "
     "only with the person they belong to."
 )
+_SUBJECT_COUNT_FALLBACK_TEXT = (
+    "Only include the people explicitly described in the action. Do not invent "
+    "extra people, doubles, duplicate bodies, background performers, or extra faces."
+)
 _ANCHOR_STYLE_PRESETS = OrderedDict(
     [
         (
@@ -416,6 +426,11 @@ def _anchor_style_description(style_name):
     return _ANCHOR_STYLE_PRESETS.get(str(style_name or "").strip().lower(), "")
 
 
+def _clean_anchor_style_text(text):
+    cleaned = _ANCHOR_STYLE_LEGACY_NOTE_RE.sub("", str(text or ""))
+    return re.sub(r"[ \t]{2,}", " ", cleaned).strip()
+
+
 def _clean_input_token_value(value):
     cleaned = ""
     if value is not None:
@@ -1131,13 +1146,51 @@ def _reference_context(ref, compact_picture_number):
     return " ".join(part for part in parts if part).strip()
 
 
+def _subject_count_guard_text(selected_refs):
+    character_labels = []
+    seen_characters = set()
+    for picture_number, (_slot, ref) in enumerate(selected_refs or (), 1):
+        if ref.get("kind") != "character":
+            continue
+        name = _reference_text(ref.get("name")) or _reference_text(ref.get("id"))
+        key = (_reference_text(ref.get("id")) or name or f"picture-{picture_number}").lower()
+        if key in seen_characters:
+            continue
+        seen_characters.add(key)
+        label = f"<Picture {picture_number}>"
+        if name:
+            label = f"{label} {name}"
+        character_labels.append(label)
+    if not character_labels:
+        return _SUBJECT_COUNT_FALLBACK_TEXT
+    if len(character_labels) == 1:
+        return (
+            f"The shot contains exactly one named character: {character_labels[0]}. "
+            "Do not create any extra people, doubles, duplicate bodies, background "
+            "performers, or extra faces."
+        )
+    return (
+        f"The shot contains exactly {len(character_labels)} named characters: "
+        + ", ".join(character_labels)
+        + ". Do not create any extra people, doubles, duplicate bodies, background "
+          "performers, or extra faces."
+    )
+
+
 def _append_prompt_section(parts, label, text):
     clean = _reference_text(text)
     if clean:
         parts.append(f"{label}: {clean}")
 
 
-def curate_h3_prompt(action_prompt, anchor="", soundscape="", refs=(), anatomy_guard="auto"):
+def curate_h3_prompt(
+    action_prompt,
+    anchor="",
+    soundscape="",
+    refs=(),
+    anatomy_guard="auto",
+    subject_count_guard="auto",
+):
     normalized_refs = _normalize_prompt_refs(refs)
     selected = _selected_prompt_refs(action_prompt, normalized_refs)
     picture_map = {slot_number: index for index, (slot_number, _ref) in enumerate(selected, 1)}
@@ -1151,6 +1204,10 @@ def curate_h3_prompt(action_prompt, anchor="", soundscape="", refs=(), anatomy_g
     _append_prompt_section(prompt_parts, "Action", action)
     if anatomy_guard == "on" or (anatomy_guard == "auto" and any(ref.get("kind") == "character" for _slot, ref in selected)):
         _append_prompt_section(prompt_parts, "Anatomy guard", _ANATOMY_GUARD_TEXT)
+    if subject_count_guard == "on" or (
+        subject_count_guard == "auto" and any(ref.get("kind") == "character" for _slot, ref in selected)
+    ):
+        _append_prompt_section(prompt_parts, "Subject count guard", _subject_count_guard_text(selected))
     _append_prompt_section(prompt_parts, "overall_soundscape", soundscape)
 
     prompt = "\n\n".join(prompt_parts).strip()
@@ -1919,8 +1976,8 @@ class DumasCharacterHelperNode:
         "IMAGE sockets plus simple identity fields, while passing both images "
         "through unchanged."
     )
-    RETURN_TYPES = ("IMAGE", "IMAGE", "STRING", "STRING")
-    RETURN_NAMES = ("image1", "image2", "reference_prompt", "wardrobe")
+    RETURN_TYPES = ("IMAGE", "IMAGE", "STRING", "STRING", _REFERENCE_TYPE, _REFERENCE_TYPE)
+    RETURN_NAMES = ("image1", "image2", "reference_prompt", "wardrobe", "reference1", "reference2")
     FUNCTION = "build_character_text"
     CATEGORY = "Dumas/MiniMax"
 
@@ -2081,7 +2138,36 @@ class DumasCharacterHelperNode:
             name,
             alias,
         )
-        return (image1, image2, text, wardrobe_text)
+        facts = {
+            "gender": _normalize_free_text(gender),
+            "age": str(_parse_positive_int(age) or ""),
+            "nationality": _normalize_free_text(nationality),
+            "occupation": _normalize_free_text(occupation),
+            "height_feet": str(height_feet or "").strip(),
+            "height_inches": str(height_inches or "").strip(),
+            "accent": _normalize_free_text(accent),
+        }
+        common = {
+            "kind": "character",
+            "explicit_id": character_id,
+            "name": name,
+            "aliases": alias,
+            "description": general,
+            "wardrobe": wardrobe,
+            "general": general,
+            "facts": facts,
+        }
+        reference1 = make_reference(
+            image=image1,
+            summary="Primary full-body character reference.",
+            **common,
+        )
+        reference2 = make_reference(
+            image=image2,
+            summary="Secondary facial character reference.",
+            **common,
+        )
+        return (image1, image2, text, wardrobe_text, reference1, reference2)
 
 
 class DumasLocationHelperNode:
@@ -2089,8 +2175,8 @@ class DumasLocationHelperNode:
         "Build a general location reference prompt from two IMAGE sockets plus "
         "simple environment fields, while passing both images through unchanged."
     )
-    RETURN_TYPES = ("IMAGE", "IMAGE", "STRING")
-    RETURN_NAMES = ("image1", "image2", "reference_prompt")
+    RETURN_TYPES = ("IMAGE", "IMAGE", "STRING", _REFERENCE_TYPE, _REFERENCE_TYPE)
+    RETURN_NAMES = ("image1", "image2", "reference_prompt", "reference1", "reference2")
     FUNCTION = "build_location_text"
     CATEGORY = "Dumas/MiniMax"
 
@@ -2178,7 +2264,26 @@ class DumasLocationHelperNode:
             description,
             general,
         )
-        return (image1, image2, text)
+        common = {
+            "kind": "location",
+            "explicit_id": location_id,
+            "name": name,
+            "aliases": alias,
+            "description": description,
+            "general": general,
+            "facts": {},
+        }
+        reference1 = make_reference(
+            image=image1,
+            summary="Primary location reference.",
+            **common,
+        )
+        reference2 = make_reference(
+            image=image2,
+            summary="Secondary location reference.",
+            **common,
+        )
+        return (image1, image2, text, reference1, reference2)
 
 
 class DumasCharacterReferenceNode:
@@ -2526,12 +2631,22 @@ class DumasH3PromptCuratorNode:
                 "anatomy_guard": (
                     ["auto", "on", "off"],
                     {
-                        "default": "auto",
+                        "default": "on",
                         "tooltip": (
                             "Add the anatomy guard. Auto adds it when a character reference is used."
                         ),
                     },
                 ),
+                "subject_count_guard": (
+                    ["auto", "on", "off"],
+                    {
+                        "default": "auto",
+                        "tooltip": (
+                            "Add a guard against extra people, duplicate bodies, or extra faces. "
+                            "Auto adds it when a character reference is used."
+                        ),
+                    },
+                ),
             },
             "optional": optional,
         }
@@ -2540,6 +2655,7 @@ class DumasH3PromptCuratorNode:
         self,
         action_prompt,
         anatomy_guard,
+        subject_count_guard,
         anchor="",
         soundscape="",
         ref_1=None,
@@ -2558,6 +2674,7 @@ class DumasH3PromptCuratorNode:
             soundscape=soundscape,
             refs=(ref_1, ref_2, ref_3, ref_4, ref_5, ref_6, ref_7, ref_8, ref_9),
             anatomy_guard=anatomy_guard,
+            subject_count_guard=subject_count_guard,
         )
 
 
@@ -2598,9 +2715,9 @@ class DumasAnchorStyleNode:
         }
 
     def build_anchor(self, anchor_style, style_description):
-        text = str(style_description or "").strip()
+        text = _clean_anchor_style_text(style_description)
         if not text:
-            text = _anchor_style_description(anchor_style)
+            text = _clean_anchor_style_text(_anchor_style_description(anchor_style))
         return (text,)
 
 

tests/test_dumas_image_nodes.py

@@ -386,6 +386,17 @@ class DumasImageNodeTests(unittest.TestCase):
         self.assertIn("Dave is also known as The Locksmith", result[2])
         self.assertIn("is 41 years old", result[2])
         self.assertEqual(result[3], "Dave = weathered red flight jacket, grey cargo shorts, black boots")
+        self.assertIs(result[4]["image"], image1)
+        self.assertIs(result[5]["image"], image2)
+        self.assertEqual(result[4]["id"], "char-dave")
+        self.assertEqual(result[5]["id"], "char-dave")
+        self.assertEqual(result[4]["name"], "Dave")
+        self.assertEqual(result[4]["aliases"], ["The Locksmith"])
+        self.assertEqual(result[4]["facts"]["age"], "41")
+        self.assertEqual(result[4]["facts"]["height_feet"], "6")
+        self.assertEqual(result[4]["facts"]["height_inches"], "2")
+        self.assertEqual(result[4]["wardrobe"], "weathered red flight jacket, grey cargo shorts, black boots")
+        self.assertEqual(len(result), 6)
 
     def test_location_helper_matches_character_helper_shape_without_wardrobe(self):
         node = self.image_nodes.DumasLocationHelperNode()
@@ -410,7 +421,17 @@ class DumasImageNodeTests(unittest.TestCase):
         self.assertIn("Coffee Shop is also known as Cafe Interior", result[2])
         self.assertIn("Warm tungsten lighting, narrow counter, rainy front window.", result[2])
         self.assertIn("Evening ambience, cramped but cozy.", result[2])
-        self.assertEqual(len(result), 3)
+        self.assertIs(result[3]["image"], image1)
+        self.assertIs(result[4]["image"], image2)
+        self.assertEqual(result[3]["kind"], "location")
+        self.assertEqual(result[4]["kind"], "location")
+        self.assertEqual(result[3]["id"], "coffee-shop-01")
+        self.assertEqual(result[4]["id"], "coffee-shop-01")
+        self.assertEqual(result[3]["name"], "Coffee Shop")
+        self.assertEqual(result[3]["aliases"], ["Cafe Interior"])
+        self.assertEqual(result[3]["description"], "Warm tungsten lighting, narrow counter, rainy front window")
+        self.assertEqual(result[3]["general"], "Evening ambience, cramped but cozy")
+        self.assertEqual(len(result), 5)
 
     def test_soundscape_helper_defaults_to_selected_preset_description(self):
         node = self.image_nodes.DumasSoundscapeHelperNode()
@@ -448,6 +469,7 @@ class DumasImageNodeTests(unittest.TestCase):
         result = node.curate_prompt(
             action_prompt="Dave runs from the Coffee Shop into the rain.",
             anatomy_guard="auto",
+            subject_count_guard="auto",
             anchor="grounded handheld thriller",
             soundscape="steady rain",
             ref_1=dave,
@@ -460,6 +482,8 @@ class DumasImageNodeTests(unittest.TestCase):
         self.assertIn("<Picture 2> Coffee Shop", prompt)
         self.assertIn("Action: Dave runs from the Coffee Shop into the rain.", prompt)
         self.assertIn("Anatomy guard:", prompt)
+        self.assertIn("Subject count guard:", prompt)
+        self.assertIn("exactly one named character: <Picture 1> Dave", prompt)
         self.assertIs(result[1], dave_image)
         self.assertIs(result[2], cafe_image)
         self.assertIsNone(result[3])
@@ -478,6 +502,7 @@ class DumasImageNodeTests(unittest.TestCase):
         result = node.curate_prompt(
             action_prompt="<Picture 1> Maya crosses to <ref3> as the wind rises.",
             anatomy_guard="off",
+            subject_count_guard="off",
             ref_1=first,
             ref_2=second,
             ref_3=third,
@@ -491,6 +516,99 @@ class DumasImageNodeTests(unittest.TestCase):
         self.assertIsNone(result[3])
         self.assertEqual(result[10], 2)
 
+    def test_h3_prompt_curator_can_force_subject_count_without_character_refs(self):
+        node = self.image_nodes.DumasH3PromptCuratorNode()
+
+        result = node.curate_prompt(
+            action_prompt="A locked-off shot of the empty corridor.",
+            anatomy_guard="off",
+            subject_count_guard="on",
+        )
+
+        self.assertIn("Subject count guard:", result[0])
+        self.assertIn("Only include the people explicitly described", result[0])
+        self.assertEqual(result[10], 0)
+
+    def test_h3_prompt_curator_treats_helper_image_pair_as_one_character(self):
+        helper = self.image_nodes.DumasCharacterHelperNode()
+        curator = self.image_nodes.DumasH3PromptCuratorNode()
+        image1 = FakeTensorBatch()
+        image2 = FakeTensorBatch()
+        helper_result = helper.build_character_text(
+            image1=image1,
+            image2=image2,
+            image1_picture_id="1",
+            image2_picture_id="2",
+            character_id="char_dave",
+            name="Dave",
+            alias="The Locksmith",
+            gender="male",
+            age="41",
+            nationality="English",
+            occupation="detective",
+            height_feet="6",
+            height_inches="2",
+            accent="English",
+            general="Tired eyes, cropped brown hair",
+            wardrobe="weathered red flight jacket",
+        )
+
+        result = curator.curate_prompt(
+            action_prompt="Dave checks the locked door.",
+            anatomy_guard="on",
+            subject_count_guard="auto",
+            ref_1=helper_result[4],
+            ref_2=helper_result[5],
+        )
+
+        self.assertIs(result[1], image1)
+        self.assertIs(result[2], image2)
+        self.assertEqual(result[10], 2)
+        self.assertIn("Character facts for <Picture 1> Dave", result[0])
+        self.assertIn("41 years old", result[0])
+        self.assertIn("6 foot 2 tall", result[0])
+        self.assertIn("exactly one named character: <Picture 1> Dave", result[0])
+        self.assertNotIn("exactly 2 named characters", result[0])
+
+    def test_h3_prompt_curator_uses_location_helper_references_by_name(self):
+        helper = self.image_nodes.DumasLocationHelperNode()
+        curator = self.image_nodes.DumasH3PromptCuratorNode()
+        image1 = FakeTensorBatch()
+        image2 = FakeTensorBatch()
+        helper_result = helper.build_location_text(
+            image1=image1,
+            image2=image2,
+            image1_picture_id="1",
+            image2_picture_id="2",
+            location_id="coffee_shop",
+            name="Coffee Shop",
+            alias="Cafe Interior",
+            description="Warm tungsten lighting, narrow counter, rainy front window",
+            general="Evening ambience, cramped but cozy",
+        )
+
+        result = curator.curate_prompt(
+            action_prompt="A slow push through the Coffee Shop as rain streaks the windows.",
+            anatomy_guard="on",
+            subject_count_guard="auto",
+            ref_1=helper_result[3],
+            ref_2=helper_result[4],
+        )
+
+        self.assertIs(result[1], image1)
+        self.assertIs(result[2], image2)
+        self.assertEqual(result[10], 2)
+        self.assertIn("<Picture 1> Coffee Shop", result[0])
+        self.assertIn("<Picture 2> Coffee Shop", result[0])
+        self.assertIn("Location context for <Picture 1> Coffee Shop", result[0])
+        self.assertIn("Warm tungsten lighting", result[0])
+        self.assertNotIn("Subject count guard:", result[0])
+
+    def test_h3_prompt_curator_defaults_anatomy_guard_to_on(self):
+        required = self.image_nodes.DumasH3PromptCuratorNode.INPUT_TYPES()["required"]
+
+        self.assertEqual(required["anatomy_guard"][1]["default"], "on")
+
     def test_helper_node_mappings_use_general_purpose_helpers(self):
         mappings = self.image_nodes.NODE_CLASS_MAPPINGS
         display = self.image_nodes.NODE_DISPLAY_NAME_MAPPINGS
@@ -570,6 +688,19 @@ class DumasImageNodeTests(unittest.TestCase):
         self.assertIn("real time", result[0])
         self.assertNotIn("persistent camera language", result[0])
 
+    def test_anchor_style_node_strips_legacy_persistent_anchor_note(self):
+        node = self.image_nodes.DumasAnchorStyleNode()
+        legacy = (
+            "Gritty handheld realism. Keep this anchor focused on persistent camera "
+            "language, lighting, texture, environment treatment, and tone; do not "
+            "name characters or describe one-off actions."
+        )
+
+        result = node.build_anchor("cinematic action movie", legacy)
+
+        self.assertEqual(result[0], "Gritty handheld realism.")
+        self.assertNotIn("persistent camera language", result[0])
+
     def test_anchor_style_node_prefers_manual_description_edits(self):
         node = self.image_nodes.DumasAnchorStyleNode()
         custom = "Lo-fi pirate broadcast with smeared highlights and anxious zoom corrections."