Higgsfield Acting Director

Higgsfield Acting Director

[OFFICIAL — Higgsfield "Hell Grind" open-source brief] — the performance system behind Higgsfield's 95-minute AI feature film, adapted to this repo's prompt surfaces. That tag covers the untagged text only: § The layer above the pillars, the silent-listener task, the eye-task paragraph and the voice-bible note each carry their own tag and are not from the brief (label legend: ../shared/provenance.md).

The core axiom of the entire system: acting is BEHAVIOR under pressure, not a display of emotion. A character wants something, something is in the way, and they act to get it. Emotion is a byproduct of that struggle — never the thing you write directly.

This is a layer on top of ../higgsfield-seedance/SKILL.md: the paragraph this skill produces goes into the PERFORMANCE / CHARACTER ACTING block of an otherwise normal Seedance prompt. It does not change camera, light, wardrobe, or grade.

QUICK FACTS

Generated-checked block (scripts/build_index.py verifies anchors). Routing aids — read the linked sections for the rules.

• Write the objective (a verb aimed at a partner), never the state — "make him confess", never "be angry" →
• 2–4 beat changes per scene, each one visible in behavior: a pause, a posture change, a tempo change, a shift of gaze. Unchanged behavior for the whole shot = played flat →
• Listening beats speaking. The reaction starts before the partner's line ends; a hard question earns a micro-pause before the answer →
• The body carries the biography: center of gravity, tempo, openness, breath — set all four before any psychology →
• Business — a physical task the hands are doing — kills theatricality; the strongest accent in a scene is the moment the character stops it →
• Distance is drama; a change of distance is a beat change. Status is what you DO, and status breaks are the most interesting thing in a performance →
• The master profile is 150–220 words, one paragraph, fixed block order, written once per character and then rewritten per scene — never pasted →
• Every tic carries a trigger; every mask carries a crack — at least one "However, when X…" clause per profile →
• Eye life is mandatory and never optional — give the eyes a task aimed at the partner, then saccades, blink quality, eyes-lead-thought; catchlights only make the task legible, they never fix a dead stare. Dead eyes are the number-one tell of AI acting →
• Scene adaptation transforms, never deletes: a behavior that can't physically happen is displaced into another outlet, not removed →
• The voice prompt is locked — one per character, from one voice bible, never adapted per scene; on 2.0 pasted verbatim into the audio field each time they speak, on 2.5 written in the character's role sentence, not the audio field, because the reused sheet carries the voice (once per prompt or once per project is OPEN, no default — P2-2) →
• States, not transitions. Models fail process and nail state: "mid-throw, arm extended", not "reaches in, pulls out, winds up" — for a peak reached through a reversing process; simple same-direction motion that must fill the clip is chained instead →
• Ensemble reactions travel in a wave, never in sync; the strong are still and quiet, the weak fidget and shout →
• 15 named bad-acting symptoms with prompt-level fixes, and a 0–5 self-check scale — aim every hero shot at 4+ →

Where this sits among the repo's performance tools