Decompose every action into body mechanics (H3 drift rule)

Compressed outcome verbs ('picks up the ball') leave H3 nothing to
animate between start and end poses, so it guesses and drifts off
intent. The craft rules in both prompts and SKILL.md now require the
ordered joint-level sequence with the hand/limb named per step.
This commit is contained in:
Z User 2026-10-29 22:46:12 +00:00
parent bbce37f2a5
commit 405386a1af
3 changed files with 29 additions and 4 deletions

View File

@ -162,6 +162,11 @@ and sampler latent or the video can come out square.
concrete mid-action exit state. Never pad to a length and never hand in a thin
one-liner — a scene with every element is long enough on its own. The validator only
trips a thin-scene floor (about 100 words); there is no target band.
- Decompose every action into body mechanics: never a single outcome verb ("picks up
the ball") — write the ordered joint-level sequence ("bends his knees, grabs the
ball with his left hand, then stands back up"), naming the hand or limb for each
step. H3 plays back only what is stated; a compressed verb leaves gaps the model
fills by guessing, and guessed motion drifts off intent.
- Open by continuing the previous `_handoff` end_state ("Continue the same stride",
"without resetting the motion", "keep the incoming camera direction"); scene 1 sets the
opening. End mid-action except the final scene. No camera cuts inside a scene.

View File

@ -130,7 +130,8 @@ Shots are flat. A shot never contains a nested object.
opening) and name what carries over: the stride, the camera direction, the light,
the weather.
4. BLOCKING — the new action as concrete staging: who moves where, which hand does
what, at what pace, handling which object.
what, at what pace, handling which object — every action decomposed into its
body-mechanic steps (PROMPT CRAFT), never a single outcome verb.
5. CAMERA — one clear camera idea per scene: shot size, height, path, speed, and what
it holds in frame. No cuts inside a scene.
6. PERFORMANCE — facial-expression beats and body mechanics timed to the action.
@ -145,6 +146,14 @@ Shots are flat. A shot never contains a nested object.
differently, stride and posture growing younger — with each stage visible while motion
and camera keep flowing. The same applies to wardrobe, weather, lighting, location,
and size changes: describe the transition happening, never just the result.
- Decompose every action into body mechanics. H3 renders only the motion that is
stated, and a compressed verb leaves it nothing to animate between the start and
end poses, so it guesses — and guessed motion drifts off intent. Never write an
action as a single outcome verb: write the ordered joint-level steps that produce
it, naming the hand or limb for each step. Not "the child picks up the ball" but
"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",
"in one motion", "with practiced presses") to the step they belong to.
- 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.
- Useful continuity phrases: "Continue the same stride", "without resetting the motion",
@ -291,7 +300,8 @@ Correct reply:
style, continuity, blocking, camera, performance, texture, exit state — and no
change anywhere is stated as a bare outcome like "is now"; every transformation is
shown as a continuous on-screen progression. Length is a side effect of the
elements, never a target.
elements, never a target. Every action is decomposed into its body-mechanic steps,
never a single outcome verb like "picks up".
9. Every shot's prompt array has exactly three lines in this order:
integrated_multimodal_description: [Shot 1] ... / overall_soundscape: ... /
non_diegetic_music: ...

View File

@ -233,7 +233,8 @@ a number is as much a failure as a thin one-liner.
establishes place, light, and the first action). Name what carries over: the
stride, the camera direction, the light, the weather.
4. BLOCKING — the new action as concrete staging: who moves where, which hand
does what, at what pace, handling which object.
does what, at what pace, handling which object — every action decomposed into
its body-mechanic steps (PROMPT CRAFT), never a single outcome verb.
5. CAMERA — one clear camera idea: shot size, height, path, speed, and what it
holds in frame. No cuts inside the scene.
6. PERFORMANCE — facial-expression beats and body mechanics timed to the action.
@ -254,6 +255,14 @@ below); dialogue lives inside the description line (DIALOGUE below).
differently, stride and posture growing younger — with each stage visible while motion
and camera keep flowing. The same applies to wardrobe, weather, lighting, location,
and size changes: describe the transition happening, never just the result.
- Decompose every action into body mechanics. H3 renders only the motion that is
stated, and a compressed verb leaves it nothing to animate between the start and
end poses, so it guesses — and guessed motion drifts off intent. Never write an
action as a single outcome verb: write the ordered joint-level steps that produce
it, naming the hand or limb for each step. Not "the child picks up the ball" but
"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",
"in one motion", "with practiced presses") to the step they belong to.
- 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.
- Useful continuity phrases: "Continue the same stride", "without resetting the motion",
@ -403,7 +412,8 @@ Correct reply:
style anchor, continuity anchor, blocking, camera, performance, physical texture,
exit state — and no change anywhere is stated as a bare outcome like "is now";
every transformation is shown as a continuous on-screen progression. Length is a
side effect of the elements, never a target.
side effect of the elements, never a target. Every action is decomposed into its
body-mechanic steps, never a single outcome verb like "picks up".
7. overall_soundscape continues the previous soundscape ("the same ... continues") and
matches the picture; non_diegetic_music: is N/A unless the user asked for a score.
8. There is no <d> span anywhere unless this scene's outline row or the story gave