higgsfield-prompt

# Higgsfield Prompt Engineering

## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- MCSLA = Model, Camera, Subject, Look, Action — the five layers of every prompt [→](#the-mcsla-formula)
- I2V: describe ONLY what moves or changes, never what's already in the image [→](#image-to-video-i2v)
- Keep prompts under 200 words — **short-form MCSLA regime only**; block-scaffold production prompts replace the cap with structural lint (HARD RULE 8 carve-out); Cinema Studio has a hard 512-character cap [→](#high-performing-prompt-patterns)
- 1 primary action per clip, 1–2 secondary max; Fast Motion Trick: render in Slow Mo, speed up in post [→](#one-action-per-scene)
- Never leave a generic emotion ("sad"/"angry") in a prompt — decompose into muscle movements, breath, eyes, skin [→](#generic-emotion-decomposition-which-kind-of-x)
- Soul ID / recurring characters: split every prompt into Identity Block + Motion Block — never mix them [→](#identity-vs-motion-separation-rule)
- Conflict order when sub-skills disagree: explicit user direction > scene archetype > emotion-sync [→](#conflict-resolution-between-sub-skills)
- Aspect ratio is a per-model enum set in the UI/header, never in the prompt body — verify via `../../specs/model-specs.yaml` [→](#common-prompt-mistakes)
- Never combine Dolly In + Dolly Out in one shot; @ Elements for static scenes, plain text for action [→](#common-prompt-mistakes)
- Iterate by changing exactly ONE variable per regeneration [→](#the-iteration-rule-change-one-variable-at-a-time)
- 6-Pass Diagnostic order: Subject → Action → Camera → Style → Audio → Output; most failures land on Pass 1–2 [→](#when-you-dont-know-whats-wrong-yet-the-6-pass-diagnostic-sequence)
- Seedance short-form: 30–100 words win; Subject + Action in the first 20–30 words. Block-scaffold production briefs run 218–2,059-word medians by register — see `../higgsfield-seedance/SKILL.md` § Official Prompt Architecture [→](#the-directors-formula-mcsla-mapping)
- Genre length targets: Product 30–50w, Lifestyle 40–60w, Drama 60–100w, Music Video 50–80w, Anime 50–90w [→](#genre-router-prompt-length-lead-with-targets)
- Kill slop words (beautiful, stunning, epic, amazing) — replace with concrete visuals/physics [→](#anti-slop-vocabulary)
- Seedance/CS 3.0 has NO negative-prompt syntax — phrase as positive constraints [→](#no-negative-prompts)
- Dialogue cap: ~25–30 spoken words fit in 15 seconds — keep the power-shift line, convert the rest to behavior [→](#dialogue-archetypes)
- Engine limits: ≤3 characters tracked across cuts; exit-frame = gone; off-screen = nonexistent; avoid reflections [→](#character-spatial-rules)
- Every cut must change BOTH shot size AND camera character [→](#double-contrast-cut-rule-mandatory)
- Age-blind rule: never boy/girl/child/kid/young/teen/little — describe by role, clothing, action [→](#age-blind-character-rule)
- Scenes start already in progress unless the user says "starts with…" or "ends with…" [→](#default-in-medias-res)


## The MCSLA Formula

Every high-performing Higgsfield prompt is built on five layers. Think of it as the
cinematographer's checklist — fill in each layer and the model has everything it needs.

| Letter | Element | Description | Example |
|--------|---------|-------------|---------|
| **M** | Model | Which generation engine | "Use Kling 2.6" |
| **C** | Camera | Named camera control | "FPV Drone shot weaving through the alley" |
| **S** | Subject | Who/what + appearance | "A woman in a sand-colored suit, sharp eyes" |
| **L** | Look | Style + color + lighting | "Cinematic, golden hour, anamorphic flare" |
| **A** | Action | What happens in the scene | "She turns slowly, wind lifting her coat" |

---

## Prompt Types

### Text-to-Video (T2V)
Start from nothing — describe the entire scene from scratch.
Best for: establishing scenes, abstract concepts, environments without a specific character.

```
[Subject + appearance].
[Environment — location, time, weather, atmosphere].
[Action — what happens and how].
[Camera — named control].
[Look — style + color grade].
```

**Example:**
```
A lone astronaut stands on the surface of a red desert planet, helmet visor reflecting
twin moons rising on the horizon. Dust spirals slowly in the thin atmosphere.
She turns to face the camera, gloved hand raised in a slow salute.
Camera: slow Crane Up revealing the vast emptiness behind her.
Style: Cinematic, desaturated orange and deep blue, 2.35:1 anamorphic.
```

---

### Image-to-Video (I2V)
Animate a provided still image. The image defines the starting frame.
Best for: character consistency, product shots, portrait animation, storyboard bring-to-life.

```
[Reference the input image as the first frame].
[Describe what should move, change, or animate — not what is already visible].
[Camera — named control].
[Style/atmosphere cues].
```

**Example:**
```
Starting from the provided image as the first frame.
The woman's hair lifts gently in the wind. She blinks slowly and turns her gaze
slightly to the left, a faint smile forming.
Camera: subtle Dolly In toward her face.
Style: Cinematic, warm afternoon light, shallow depth of field.
```

**Key rule for I2V:** Do NOT re-describe what is already in the image. Only describe
what should *change* or *animate*. Over-describing the static elements confuses the model.
This applies equally to @ Image references in Seedance/Cinema Studio 3.0 — describe
ONLY motion and camera movement, never what's already visible.

---

## Narrative Structure

### Fluid Narrative (preferred for most use cases)
Write the scene as continuous action. No timestamps. Most natural for Higgsfield.

```
A detective pushes open the door to the rain-soaked rooftop, coat whipping in the wind.
She steps to the edge and looks down at the city below — a thousand lights blurring
through the downpour. Camera dollies slowly behind her,