higgsfield-seedance

# Higgsfield Seedance Director

## QUICK FACTS
*Generated-checked block (build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- The filter is an LLM reading full-scene intent, not a keyword blacklist — describe a SCENE, not a subject; fix the voice first [→](#the-filter-model-read-this-first)
- Instant fail (<10s) = filter rejection; delayed fail (>30s) = infra/complexity — never regenerate an instant fail unchanged [→](#instant-fail-vs-delayed-fail-the-diagnostic)
- Six slots, in order: Camera + Subject + Action + Setting + Style + Lighting; missing 3+ slots is where flags come from [→](#the-seedance-prompt-formula)
- Five prompt modes: Reference-Based / Continuation / Expand Shot / Edit Shot / Transformation — pick the mode before writing [→](#seedance-20-prompt-modes)
- Hard engine rules (age-blind, exit-frame = cut, off-screen = nonexistent, no reflections, ≤3 tracked characters, double-contrast cuts) + high-risk shot table: `ENGINE-RULES.md` in this directory
- Reference roles: Character / Last-Frame / Environment / Prop — role determines what the prompt may re-describe [→](#reference-roles)
- Working modes: Exploration / Continuation / Bridging / Repair (distinct from prompt modes) [→](#working-modes-vs-prompt-modes-two-taxonomies)
- Layer 1 briefing vs Layer 2 production prompt — never paste Layer 1 into the prompt box [→](#two-layer-prompt-authoring)
- Always preflight: `python3 seedance_lint.py --preflight --model seedance_2_0 "<prompt>"` — enums come from `../../specs/model-specs.json` (fast+1080p and Kling 21:9 are auto-caught) [→](#pre-flight-linter)
- 480p drafts validate the prompt, NOT the take — no seed param; pin Hero Frame + start/end frames to carry a look [→](#drafts-validate-the-prompt-not-the-take)
- ZH prompts: hard 1,800-char cap; ZH antislop list enforced by the linter [→](#multi-language-prompt-workarounds)
- Flagged prompt → rewrite playbook per linter rule, then voice pass [→](#the-rewrite-playbook)
- Repeated flags → full loop-breaker procedure + LOG THE OUTCOME (`--confirmed` / `add-quality`) [→](#when-the-user-is-already-in-a-failure-loop)


Use this skill whenever the user wants a Seedance 2.0 / Seedance Pro prompt, OR
whenever a Seedance generation has been blocked, flagged, or silently failed.
This skill's job is to stop credit waste on filter rejections.

> **Engine rules (read with this file):** the hard rendering constraints of the
> Seedance 2.0 engine — age-blind characters, exit-frame = implicit cut,
> off-screen = nonexistent, no reflection shots, ≤3 tracked characters, the
> double-contrast cut rule — live in `ENGINE-RULES.md` in this directory,
> together with the high-risk shot table (reflections, same-character doubles,
> crowds, text rendering) and its mitigations. This SKILL.md is the
> `EN-director` *profile* of that rule core; the `ZH-house` and
> `bilingual-JSON` profiles (`../../docs/Seedance 2 Skill.md`) obey the same
> core. Flag high-risk shot types at authoring time — never silently break a
> rule the project's hero image happens to conflict with.

---

## The Filter Model — Read This First

Seedance 2.0's content filter is **not** a keyword blacklist. It is a language
model that reads the full prompt as a single scene and judges intent and context.
Most users burn hours swapping individual words — that loop does not work.

The filter compares two things:

- **A prompt that reads like a filmmaker describing a shot** → tends to pass.
- **A prompt that reads like a note to a friend** → tends to fail.

A word that looks sensitive in isolation can sit inside a well-constructed
cinematic prompt without issue — the filter reads the full picture. A prompt
with no picture to read (no setting, no visual purpose, no narrative logic)
gives the filter nothing to work with, and it errs on the side of caution.

**Practical rule:** the prompt must describe a **scene**, not a **subject**.
Fix the voice first, then fix the words.

---

## Instant Fail vs. Delayed Fail — the Diagnostic

This single heuristic saves time on every failure:

| Failure timing | Meaning | What to do |
|----------------|---------|------------|
| **< 10 seconds** (instant) | Content filter rejection — prompt never reached the GPU | Rewrite for voice + remove risk tokens. Do not regenerate unchanged. |
| **> 30 seconds** (delayed) | Infrastructure, timeout, or complexity — prompt passed the filter but the render failed | Simplify action density, cut length, try again |

If the user is seeing **instant fails in a loop**, it is a filter issue — never
a GPU issue. Stop them from regenerating before the rewrite.

---

## The Seedance Prompt Formula

Every Seedance prompt should hit these six slots, in this order:

```
[Camera movement] + [Subject] + [Action] + [Setting] + [Style] + [Lighting]
```

All six are technically optional — but a prompt that includes all six almost
never gets flagged, because the filter has full context to interpret every
word. A prompt missing 3+ slots is where flags come from.

### Minimum viable Seedance prompt

> **Slow dolly-in on a figure in a dark overcoat standing alone at the end of
> a rain-slick alley. Cold teal shadows, single practical streetlamp, shallow
> depth of field.**

Camera ✓ Subject ✓ Action ✓ Setting ✓ Style ✓ Lighting ✓ — all six slots, ~30
words, passes the filter because the scene is fully legible.

---

## Seedance 2.0 Prompt Modes

Seedance 2.0 exposes five generation modes that each take the six-slot formula
but apply it to a different starting point. Picking the right mode is upstream of
prompt writing — the same sentence will produce different results in different
modes, because each mode reads the prompt as a different kind of instruction.

### Reference-Based

The prompt builds a scene around a source image that carries the visual identity —
character, wardrobe, palette, sometimes composition. The prompt's job is NOT to
re-describe what the