higgsfield-scene-engine

Higgsfield Scene Engine — is this scene worth generating?

[DEMO — Tigran (tig-scene-engine), 2026-06-26] [UNPROVEN HERE] These definitions are bespoke and deliberately not the textbook ones. Apply them as written; do not substitute standard screenwriting glosses, which are looser and will pass scenes this engine fails.

Why a prompter carries this. Every shot costs credits and iterations. A structurally dead scene generates just as cleanly as a live one — the model has no opinion about whether a beat earns its place — so the failure surfaces only after the footage exists and the cut does not build. This skill is the cheapest pass in the repo: it runs on text, before any generation, and its whole job is to stop you paying to render a scene that cannot work.

It decides which shots deserve the spend. higgsfield-shotlist-director turns the settled scene into shots; higgsfield-acting writes the performance inside them.

---

The five-element engine

1. Goal

The single, unchanging thing the hero is fighting for: to fix what has already been established and reach, as fast as possible, the result that resolves it. "Already established" means anything set up earlier — deep backstory, a few scenes ago, or one minute ago.

• The major goal never changes, and the hero is never wrong about it. He can be wrong about tactics, never about the goal.
• Every scene goal must be a causal link toward the story goal. Test: if you can remove the scene and the chain still holds, the scene fails. No orphan scenes.
• "What he ought to do" is not a separate thing to test — the right move is dictated by Obstacle + Stakes. A hero taking a tactic the stakes would not justify (showering while the building burns) is a flaggable inconsistency: name it as bad writing or as deliberate self-sabotage.

2. Obstacle

A strong circumstance that jeopardizes either one stage of the path or the whole goal. It threatens; it does not merely cost.