Add H3 prompt curator
This commit is contained in:
@@ -27,6 +27,15 @@ _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 = ""
|
||||
_H3_PROMPT_REF_SLOTS = 9
|
||||
_H3_PROMPT_MAX_CHARS = 7000
|
||||
_PICTURE_TAG_RE = re.compile(r"<\s*picture[\s_\-]*(\d+)\s*>", re.I)
|
||||
_REF_TAG_RE = re.compile(r"<\s*ref[\s_\-]*(\d+)\s*>", re.I)
|
||||
_ANATOMY_GUARD_TEXT = (
|
||||
"Each person has one head, two arms, two hands with five fingers on each hand, "
|
||||
"and two legs with two feet. Limbs stay attached to the correct body and move "
|
||||
"only with the person they belong to."
|
||||
)
|
||||
_ANCHOR_STYLE_PRESETS = OrderedDict(
|
||||
[
|
||||
(
|
||||
@@ -346,6 +355,47 @@ _ANCHOR_STYLE_PRESETS = OrderedDict(
|
||||
),
|
||||
]
|
||||
)
|
||||
_SOUNDSCAPE_PRESETS = OrderedDict(
|
||||
[
|
||||
(
|
||||
"quiet interior",
|
||||
"quiet indoor room tone, faint ventilation and distant household ambience",
|
||||
),
|
||||
(
|
||||
"rainy street",
|
||||
"steady rain, wet pavement, distant traffic hum",
|
||||
),
|
||||
(
|
||||
"cafe",
|
||||
"low room tone, faint glassware, cutlery, and muted conversation",
|
||||
),
|
||||
(
|
||||
"city night",
|
||||
"distant traffic hum, occasional horn, night air",
|
||||
),
|
||||
(
|
||||
"forest",
|
||||
"wind in leaves, distant birds, soft natural ambience",
|
||||
),
|
||||
(
|
||||
"industrial",
|
||||
"large interior reverb, distant metal ticks, low machine hum",
|
||||
),
|
||||
(
|
||||
"silent",
|
||||
"no dialogue, no vocals, only the natural ambient bed of the scene",
|
||||
),
|
||||
("custom", ""),
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
def _soundscape_options():
|
||||
return list(_SOUNDSCAPE_PRESETS.keys())
|
||||
|
||||
|
||||
def _soundscape_description(soundscape_name):
|
||||
return _SOUNDSCAPE_PRESETS.get(soundscape_name, "")
|
||||
_LOAD_IMAGES_FOLDER_DEFAULT_STATE = {
|
||||
"version": 1,
|
||||
"folder": "",
|
||||
@@ -920,6 +970,206 @@ def normalize_reference(value, picture_id=None, allow_image_fallback=True):
|
||||
)
|
||||
|
||||
|
||||
def _reference_text(value):
|
||||
return " ".join(str(value or "").split()).strip()
|
||||
|
||||
|
||||
def _reference_sentence(value):
|
||||
text = _reference_text(value)
|
||||
if text and text[-1] not in ".!?":
|
||||
text += "."
|
||||
return text
|
||||
|
||||
|
||||
def _reference_name_keys(ref):
|
||||
names = []
|
||||
for key in ("name", "id"):
|
||||
value = _reference_text(ref.get(key))
|
||||
if value:
|
||||
names.append(value)
|
||||
for alias in ref.get("aliases") or []:
|
||||
value = _reference_text(alias)
|
||||
if value:
|
||||
names.append(value)
|
||||
seen = set()
|
||||
out = []
|
||||
for name in names:
|
||||
key = name.lower()
|
||||
if key in seen:
|
||||
continue
|
||||
seen.add(key)
|
||||
out.append(name)
|
||||
return out
|
||||
|
||||
|
||||
def _reference_image(ref):
|
||||
if not isinstance(ref, dict):
|
||||
return None
|
||||
return ref.get("image")
|
||||
|
||||
|
||||
def _normalize_prompt_refs(raw_refs):
|
||||
refs = []
|
||||
for slot_number, raw in enumerate(raw_refs or (), 1):
|
||||
if raw is None:
|
||||
refs.append(None)
|
||||
continue
|
||||
try:
|
||||
ref = normalize_reference(raw, picture_id=slot_number, allow_image_fallback=False)
|
||||
except Exception:
|
||||
refs.append(None)
|
||||
continue
|
||||
if _reference_image(ref) is None:
|
||||
refs.append(None)
|
||||
else:
|
||||
refs.append(ref)
|
||||
return refs
|
||||
|
||||
|
||||
def _explicit_reference_tags(text):
|
||||
return sorted(
|
||||
{
|
||||
int(match.group(1))
|
||||
for pattern in (_PICTURE_TAG_RE, _REF_TAG_RE)
|
||||
for match in pattern.finditer(text or "")
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def _name_matches_reference(text, ref):
|
||||
haystack = str(text or "")
|
||||
for name in _reference_name_keys(ref):
|
||||
if re.search(r"\b" + re.escape(name) + r"\b", haystack, re.I):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _selected_prompt_refs(action_prompt, refs):
|
||||
selected = []
|
||||
seen_slots = set()
|
||||
for slot_number in _explicit_reference_tags(action_prompt):
|
||||
if not (1 <= slot_number <= len(refs)):
|
||||
continue
|
||||
ref = refs[slot_number - 1]
|
||||
if ref is None:
|
||||
continue
|
||||
selected.append((slot_number, ref))
|
||||
seen_slots.add(slot_number)
|
||||
for slot_number, ref in enumerate(refs, 1):
|
||||
if slot_number in seen_slots or ref is None:
|
||||
continue
|
||||
if _name_matches_reference(action_prompt, ref):
|
||||
selected.append((slot_number, ref))
|
||||
seen_slots.add(slot_number)
|
||||
return selected
|
||||
|
||||
|
||||
def _replace_reference_tags(text, picture_map):
|
||||
def repl(match):
|
||||
original = int(match.group(1))
|
||||
compacted = picture_map.get(original)
|
||||
if compacted is None:
|
||||
return ""
|
||||
return f"<Picture {compacted}>"
|
||||
|
||||
rewritten = _PICTURE_TAG_RE.sub(repl, str(text or ""))
|
||||
rewritten = _REF_TAG_RE.sub(repl, rewritten)
|
||||
return re.sub(r"[ \t]{2,}", " ", rewritten).strip()
|
||||
|
||||
|
||||
def _reference_fact_sentence(ref, label):
|
||||
if ref.get("kind") != "character":
|
||||
return ""
|
||||
facts = dict(ref.get("facts") or {})
|
||||
bits = []
|
||||
aliases = [_reference_text(alias) for alias in (ref.get("aliases") or []) if _reference_text(alias)]
|
||||
if aliases:
|
||||
bits.append(f"also known as {aliases[0]}")
|
||||
for key in ("gender", "nationality", "occupation"):
|
||||
value = _reference_text(facts.get(key))
|
||||
if value:
|
||||
bits.append(value if key != "occupation" else f"works as {value}")
|
||||
age = _parse_positive_int(facts.get("age"))
|
||||
if age is not None:
|
||||
bits.append(f"{age} years old")
|
||||
feet = _reference_text(facts.get("height_feet"))
|
||||
inches = _reference_text(facts.get("height_inches"))
|
||||
if feet and inches:
|
||||
bits.append(f"{feet} foot {inches} tall")
|
||||
elif feet:
|
||||
bits.append(f"{feet} foot tall")
|
||||
accent = _reference_text(facts.get("accent"))
|
||||
if accent:
|
||||
bits.append(f"speaks with a {accent} accent")
|
||||
if not bits:
|
||||
return ""
|
||||
return f"Character facts for {label}: " + ", ".join(bits) + "."
|
||||
|
||||
|
||||
def _reference_context(ref, compact_picture_number):
|
||||
label_name = _reference_text(ref.get("name")) or _reference_text(ref.get("id")) or "this reference"
|
||||
label = f"<Picture {compact_picture_number}> {label_name}"
|
||||
parts = [_reference_sentence(_reference_summary(ref.get("kind"), label_name, compact_picture_number))]
|
||||
description = _reference_sentence(ref.get("description"))
|
||||
wardrobe = _reference_sentence(ref.get("wardrobe"))
|
||||
general = _reference_sentence(ref.get("general"))
|
||||
facts = _reference_fact_sentence(ref, label)
|
||||
if ref.get("kind") == "location":
|
||||
if description:
|
||||
parts.append(f"Location context for {label}: {description}")
|
||||
if general:
|
||||
parts.append(f"Location notes for {label}: {general}")
|
||||
else:
|
||||
if facts:
|
||||
parts.append(facts)
|
||||
if description:
|
||||
parts.append(f"Persistent appearance for {label}: {description}")
|
||||
if wardrobe:
|
||||
parts.append(f"Persistent wardrobe/style for {label}: {wardrobe}")
|
||||
if general:
|
||||
parts.append(f"Character notes for {label}: {general}")
|
||||
return " ".join(part for part in parts if part).strip()
|
||||
|
||||
|
||||
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"):
|
||||
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)}
|
||||
action = _replace_reference_tags(action_prompt, picture_map)
|
||||
|
||||
prompt_parts = []
|
||||
_append_prompt_section(prompt_parts, "Scene anchor", anchor)
|
||||
if selected:
|
||||
contexts = [_reference_context(ref, picture_number) for picture_number, (_slot, ref) in enumerate(selected, 1)]
|
||||
_append_prompt_section(prompt_parts, "Reference context", " ".join(contexts))
|
||||
_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)
|
||||
_append_prompt_section(prompt_parts, "overall_soundscape", soundscape)
|
||||
|
||||
prompt = "\n\n".join(prompt_parts).strip()
|
||||
if len(prompt) > _H3_PROMPT_MAX_CHARS:
|
||||
prompt = prompt[: _H3_PROMPT_MAX_CHARS - 3].rstrip() + "..."
|
||||
images = [_reference_image(ref) for _slot, ref in selected]
|
||||
images.extend([None] * (_H3_PROMPT_REF_SLOTS - len(images)))
|
||||
debug = (
|
||||
f"Selected {len(selected)} reference(s): "
|
||||
+ ", ".join(
|
||||
f"input {slot}-><Picture {index}> {_reference_text(ref.get('name')) or ref.get('id')}"
|
||||
for index, (slot, ref) in enumerate(selected, 1)
|
||||
)
|
||||
if selected
|
||||
else "Selected 0 references."
|
||||
)
|
||||
return (prompt, *images[:_H3_PROMPT_REF_SLOTS], len(selected), debug)
|
||||
|
||||
|
||||
def _parse_positive_int(value):
|
||||
text = str(value or "").strip()
|
||||
if not text:
|
||||
@@ -2163,6 +2413,154 @@ class DumasLocationReferenceNode:
|
||||
)
|
||||
|
||||
|
||||
class DumasSoundscapeHelperNode:
|
||||
DESCRIPTION = (
|
||||
"Choose a soundscape preset, auto-fill its editable description, and pass "
|
||||
"the final soundscape text downstream for MiniMax H3 prompts."
|
||||
)
|
||||
RETURN_TYPES = ("STRING",)
|
||||
RETURN_NAMES = ("soundscape",)
|
||||
FUNCTION = "build_soundscape"
|
||||
CATEGORY = "Dumas/MiniMax"
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
default_soundscape = "quiet interior"
|
||||
return {
|
||||
"required": {
|
||||
"soundscape": (
|
||||
_soundscape_options(),
|
||||
{
|
||||
"default": default_soundscape,
|
||||
"tooltip": "Preset title used to seed the editable soundscape description.",
|
||||
},
|
||||
),
|
||||
"soundscape_description": (
|
||||
"STRING",
|
||||
{
|
||||
"default": _soundscape_description(default_soundscape),
|
||||
"multiline": True,
|
||||
"tooltip": (
|
||||
"Editable environmental audio description. Whatever text is here "
|
||||
"is what the node outputs to the soundscape socket."
|
||||
),
|
||||
},
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
def build_soundscape(self, soundscape, soundscape_description):
|
||||
text = str(soundscape_description or "").strip()
|
||||
if not text:
|
||||
text = _soundscape_description(soundscape)
|
||||
return (text,)
|
||||
|
||||
|
||||
class DumasH3PromptCuratorNode:
|
||||
DESCRIPTION = (
|
||||
"Curate one MiniMax H3 prompt from an action textbox, anchor text, "
|
||||
"soundscape text, and up to nine structured references. References are "
|
||||
"compacted so only mentioned names, aliases, or explicit <Picture N>/<refN> "
|
||||
"tags are sent onward."
|
||||
)
|
||||
RETURN_TYPES = ("STRING",) + ("IMAGE",) * _H3_PROMPT_REF_SLOTS + ("INT", "STRING")
|
||||
RETURN_NAMES = (
|
||||
"prompt",
|
||||
"ref_image_1",
|
||||
"ref_image_2",
|
||||
"ref_image_3",
|
||||
"ref_image_4",
|
||||
"ref_image_5",
|
||||
"ref_image_6",
|
||||
"ref_image_7",
|
||||
"ref_image_8",
|
||||
"ref_image_9",
|
||||
"reference_count",
|
||||
"debug",
|
||||
)
|
||||
FUNCTION = "curate_prompt"
|
||||
CATEGORY = "Dumas/MiniMax"
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
optional = {
|
||||
"anchor": (
|
||||
"STRING",
|
||||
{
|
||||
"forceInput": True,
|
||||
"tooltip": "Optional anchor/style text, usually from Dumas Anchor Style.",
|
||||
},
|
||||
),
|
||||
"soundscape": (
|
||||
"STRING",
|
||||
{
|
||||
"forceInput": True,
|
||||
"tooltip": "Optional soundscape text, usually from Dumas Soundscape Helper.",
|
||||
},
|
||||
),
|
||||
}
|
||||
for slot in range(1, _H3_PROMPT_REF_SLOTS + 1):
|
||||
optional[f"ref_{slot}"] = (
|
||||
_REFERENCE_TYPE,
|
||||
{
|
||||
"tooltip": (
|
||||
f"Optional structured reference {slot}. The curator only outputs "
|
||||
"it if the action prompt mentions its name/alias or an explicit "
|
||||
f"<Picture {slot}>/<ref{slot}> tag."
|
||||
)
|
||||
},
|
||||
)
|
||||
return {
|
||||
"required": {
|
||||
"action_prompt": (
|
||||
"STRING",
|
||||
{
|
||||
"default": "",
|
||||
"multiline": True,
|
||||
"tooltip": (
|
||||
"Write the final shot action here using character/location names. "
|
||||
"Mention a reference by name, alias, <Picture N>, or <refN> to use it."
|
||||
),
|
||||
},
|
||||
),
|
||||
"anatomy_guard": (
|
||||
["auto", "on", "off"],
|
||||
{
|
||||
"default": "auto",
|
||||
"tooltip": (
|
||||
"Add the anatomy guard. Auto adds it when a character reference is used."
|
||||
),
|
||||
},
|
||||
),
|
||||
},
|
||||
"optional": optional,
|
||||
}
|
||||
|
||||
def curate_prompt(
|
||||
self,
|
||||
action_prompt,
|
||||
anatomy_guard,
|
||||
anchor="",
|
||||
soundscape="",
|
||||
ref_1=None,
|
||||
ref_2=None,
|
||||
ref_3=None,
|
||||
ref_4=None,
|
||||
ref_5=None,
|
||||
ref_6=None,
|
||||
ref_7=None,
|
||||
ref_8=None,
|
||||
ref_9=None,
|
||||
):
|
||||
return curate_h3_prompt(
|
||||
action_prompt,
|
||||
anchor=anchor,
|
||||
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,
|
||||
)
|
||||
|
||||
|
||||
class DumasAnchorStyleNode:
|
||||
DESCRIPTION = (
|
||||
"Choose an anchor-style preset, auto-fill its full description, and pass "
|
||||
@@ -2214,6 +2612,8 @@ NODE_CLASS_MAPPINGS = {
|
||||
"DumasH3PlanExtractSceneImages": DumasH3PlanExtractSceneImagesNode,
|
||||
"DumasCharacterReference": DumasCharacterReferenceNode,
|
||||
"DumasLocationReference": DumasLocationReferenceNode,
|
||||
"DumasSoundscapeHelper": DumasSoundscapeHelperNode,
|
||||
"DumasH3PromptCurator": DumasH3PromptCuratorNode,
|
||||
"DumasAnchorStyle": DumasAnchorStyleNode,
|
||||
"DumasCharacterHelper": DumasCharacterHelperNode,
|
||||
"DumasLocationHelper": DumasLocationHelperNode,
|
||||
@@ -2228,6 +2628,8 @@ NODE_DISPLAY_NAME_MAPPINGS = {
|
||||
"DumasH3PlanExtractSceneImages": "Dumas H3 Plan Extract Scene Images",
|
||||
"DumasCharacterReference": "Dumas Character Reference",
|
||||
"DumasLocationReference": "Dumas Location Reference",
|
||||
"DumasSoundscapeHelper": "Dumas Soundscape Helper",
|
||||
"DumasH3PromptCurator": "Dumas H3 Prompt Curator",
|
||||
"DumasAnchorStyle": "Dumas Anchor Style",
|
||||
"DumasCharacterHelper": "Dumas Character Helper",
|
||||
"DumasLocationHelper": "Dumas Location Helper",
|
||||
|
||||
Reference in New Issue
Block a user