Full look every scene; 'nude' for uncovered body parts, never 'bare'

H3 needs every aspect of the look restated per scene, and uncovered
skin is steered by the skin-state word 'nude' (tank-top with nude
arms), not 'bare'. Added to both prompts' subject anchor + craft
rules + self-checks and SKILL.md; the validator prints a non-blocking
note when a description line uses 'bare'.
This commit is contained in:
Z User 2026-10-29 23:18:56 +00:00
parent 405386a1af
commit fa764ec933
4 changed files with 37 additions and 8 deletions

View File

@ -153,8 +153,11 @@ and sampler latent or the video can come out square.
- The `prompt` array has EXACTLY three lines in this order; every scene is its own single - The `prompt` array has EXACTLY three lines in this order; every scene is its own single
H3 generation, so the bracket number is always `[Shot 1]`: H3 generation, so the bracket number is always `[Shot 1]`:
`integrated_multimodal_description:` / `overall_soundscape:` / `non_diegetic_music:`. `integrated_multimodal_description:` / `overall_soundscape:` / `non_diegetic_music:`.
- The description line is self-sufficient: re-state `<Subject 1>`, the full wardrobe, and - The description line is self-sufficient: re-state `<Subject 1>` and the full look in
the visual style in EVERY scene — nothing is shared between scenes or from a prefix. EVERY scene — identity, hair, build, every garment head to toe, footwear, and the
visual style — nothing is shared between scenes or from a prefix. Name every body
part the clothing leaves uncovered and call uncovered skin "nude", never "bare"
("a man wearing a white tank-top with nude arms").
- Scene composition, not word count: the description line must carry every element — - Scene composition, not word count: the description line must carry every element —
subject anchor (`<Subject 1>` and wardrobe restated), style anchor, continuity anchor subject anchor (`<Subject 1>` and wardrobe restated), style anchor, continuity anchor
(opens inside the previous end_state), blocking, one camera idea, performance beats, (opens inside the previous end_state), blocking, one camera idea, performance beats,

View File

@ -124,7 +124,9 @@ Shots are flat. A shot never contains a nested object.
- Compose every scene from the same eight elements, and never chase a word count — - Compose every scene from the same eight elements, and never chase a word count —
chase the elements. A description that genuinely carries them comes out long enough chase the elements. A description that genuinely carries them comes out long enough
on its own; padding to a number is as much a failure as a thin one-liner: on its own; padding to a number is as much a failure as a thin one-liner:
1. SUBJECT ANCHOR — <Subject 1> restated: identity, wardrobe head to toe, hair, build. 1. SUBJECT ANCHOR — <Subject 1> restated: identity, every aspect of how they look,
wardrobe head to toe, hair, build — naming every body part the clothing leaves
uncovered, using "nude" for uncovered skin (PROMPT CRAFT).
2. STYLE ANCHOR — the one consistent look: medium, lighting quality, palette. 2. STYLE ANCHOR — the one consistent look: medium, lighting quality, palette.
3. CONTINUITY ANCHOR — open inside the previous scene's end state (scene 1 sets the 3. CONTINUITY ANCHOR — open inside the previous scene's end state (scene 1 sets the
opening) and name what carries over: the stride, the camera direction, the light, opening) and name what carries over: the stride, the camera direction, the light,
@ -154,6 +156,13 @@ Shots are flat. A shot never contains a nested object.
"the child bends his knees, grabs the ball with his left hand, then stands back "the child bends his knees, grabs the ball with his left hand, then stands back
up". Doors, straps, buttons, trays, lifts — same rule. Attach pace words ("slowly", up". Doors, straps, buttons, trays, lifts — same rule. Attach pace words ("slowly",
"in one motion", "with practiced presses") to the step they belong to. "in one motion", "with practiced presses") to the step they belong to.
- Describe the complete look in every scene: every aspect of how the person looks —
face, hair, build, each garment head to toe, footwear — because nothing carries
over between scenes. Any body part the clothing leaves uncovered must be named and
called "nude", never "bare": not "a man wearing a white tank-top" but "a man
wearing a white tank-top with nude arms"; likewise nude legs under shorts, nude
shoulders under a sleeveless top, nude feet in sandals. "Nude" is the reliable
skin-state word for uncovered body parts; "bare" is not.
- One string per line in the prompt array. A shot's array holds exactly the three AUDIO - One string per line in the prompt array. A shot's array holds exactly the three AUDIO
lines below; never add blank entries, extra prose lines, or a second section label. lines below; never add blank entries, extra prose lines, or a second section label.
- Useful continuity phrases: "Continue the same stride", "without resetting the motion", - Useful continuity phrases: "Continue the same stride", "without resetting the motion",
@ -295,7 +304,8 @@ Correct reply:
6. Every duration_seconds is between 2 and 15. 6. Every duration_seconds is between 2 and 15.
7. Scene 1 sets an opening; every later scene continues the previous final action; every 7. Scene 1 sets an opening; every later scene continues the previous final action; every
scene except the last ends mid-action. Every description line is self-sufficient: it scene except the last ends mid-action. Every description line is self-sufficient: it
re-states who <Subject 1> is, wardrobe, and visual style, because the prefix is empty. re-states who <Subject 1> is, the full look, and visual style, because the prefix is
empty, naming every uncovered body part as "nude" — never "bare".
8. Every description line carries every element of a scene composition — subject, 8. Every description line carries every element of a scene composition — subject,
style, continuity, blocking, camera, performance, texture, exit state — and no style, continuity, blocking, camera, performance, texture, exit state — and no
change anywhere is stated as a bare outcome like "is now"; every transformation is change anywhere is stated as a bare outcome like "is now"; every transformation is

View File

@ -226,8 +226,10 @@ element is a failed scene. Do not chase a word count — chase the elements. A
description that genuinely carries them comes out long enough on its own; padding to description that genuinely carries them comes out long enough on its own; padding to
a number is as much a failure as a thin one-liner. a number is as much a failure as a thin one-liner.
1. SUBJECT ANCHOR — <Subject 1> restated: identity, wardrobe head to toe, hair, 1. SUBJECT ANCHOR — <Subject 1> restated: identity, every aspect of how they look,
build. Nothing is shared between scenes or from a prefix. wardrobe head to toe, hair, build — and name every body part the clothing leaves
uncovered, using "nude" for uncovered skin (PROMPT CRAFT). Nothing is shared
between scenes or from a prefix.
2. STYLE ANCHOR — the one consistent look: medium, lighting quality, palette. 2. STYLE ANCHOR — the one consistent look: medium, lighting quality, palette.
3. CONTINUITY ANCHOR — open inside the previous end_state (scene 1 instead 3. CONTINUITY ANCHOR — open inside the previous end_state (scene 1 instead
establishes place, light, and the first action). Name what carries over: the establishes place, light, and the first action). Name what carries over: the
@ -263,6 +265,13 @@ below); dialogue lives inside the description line (DIALOGUE below).
"the child bends his knees, grabs the ball with his left hand, then stands back "the child bends his knees, grabs the ball with his left hand, then stands back
up". Doors, straps, buttons, trays, lifts — same rule. Attach pace words ("slowly", up". Doors, straps, buttons, trays, lifts — same rule. Attach pace words ("slowly",
"in one motion", "with practiced presses") to the step they belong to. "in one motion", "with practiced presses") to the step they belong to.
- Describe the complete look in every scene: every aspect of how the person looks —
face, hair, build, each garment head to toe, footwear — because each scene is a
separate generation and nothing carries over. Any body part the clothing leaves
uncovered must be named and called "nude", never "bare": not "a man wearing a
white tank-top" but "a man wearing a white tank-top with nude arms"; likewise nude
legs under shorts, nude shoulders under a sleeveless top, nude feet in sandals.
"Nude" is the reliable skin-state word for uncovered body parts; "bare" is not.
- One string per line in the prompt array: exactly the three AUDIO lines; never add - One string per line in the prompt array: exactly the three AUDIO lines; never add
blank entries, extra prose lines, or a second section label. blank entries, extra prose lines, or a second section label.
- Useful continuity phrases: "Continue the same stride", "without resetting the motion", - Useful continuity phrases: "Continue the same stride", "without resetting the motion",
@ -404,8 +413,9 @@ Correct reply:
the user asked). id and duration_seconds match your outline row. the user asked). id and duration_seconds match your outline row.
3. The prompt array has exactly three lines in AUDIO order, and line 1 starts with 3. The prompt array has exactly three lines in AUDIO order, and line 1 starts with
"integrated_multimodal_description: [Shot 1]". "integrated_multimodal_description: [Shot 1]".
4. The description line is self-sufficient: it re-states <Subject 1>, the full wardrobe, 4. The description line is self-sufficient: it re-states <Subject 1>, the full look
and the visual style. (identity, hair, build, every garment head to toe, footwear), and the visual
style, naming every uncovered body part as "nude" — never "bare".
5. The description opens by continuing the PREVIOUS HANDOFF's end_state (scene 1 sets 5. The description opens by continuing the PREVIOUS HANDOFF's end_state (scene 1 sets
the opening instead) and ends mid-action — except the final outline scene. the opening instead) and ends mid-action — except the final outline scene.
6. The description line carries every element of a scene composition — subject anchor, 6. The description line carries every element of a scene composition — subject anchor,

View File

@ -185,6 +185,9 @@ def check_h3_sections(plan):
wc = len(lines[0].split()) wc = len(lines[0].split())
assert "<Subject 1>" in lines[0], \ assert "<Subject 1>" in lines[0], \
f"shot {idx}: description line must re-state <Subject 1> (prefix is empty)" f"shot {idx}: description line must re-state <Subject 1> (prefix is empty)"
if re.search(r"\bbare\b", lines[0], re.I):
print(f" note: shot {idx} description says 'bare' - call uncovered body "
f"parts 'nude' (e.g. 'nude arms')")
dur = float(shot.get("duration_seconds", dur = float(shot.get("duration_seconds",
plan.get("defaults", {}).get("duration_seconds", 15))) plan.get("defaults", {}).get("duration_seconds", 15)))
floor = THIN_FLOOR_LONG if dur >= 10 else THIN_FLOOR_SHORT floor = THIN_FLOOR_LONG if dur >= 10 else THIN_FLOOR_SHORT
@ -271,6 +274,9 @@ def validate_fragment(obj, index=1, total=None, prev_handoff=None, expect=None):
f"sound, exit state)") f"sound, exit state)")
if "<Subject 1>" not in desc: if "<Subject 1>" not in desc:
raise ValueError(f"{where}: description must re-state <Subject 1> (prefix is empty)") raise ValueError(f"{where}: description must re-state <Subject 1> (prefix is empty)")
if re.search(r"\bbare\b", desc, re.I):
print(f" note: {where} description says 'bare' - call uncovered body parts "
f"'nude' (e.g. 'nude arms')")
if " is now " in desc.lower(): if " is now " in desc.lower():
raise ValueError(f"{where}: change stated as bare outcome instead of shown progression") raise ValueError(f"{where}: change stated as bare outcome instead of shown progression")
if "<d>" in ssc or "</d>" in ssc: if "<d>" in ssc or "</d>" in ssc: