Higgsfield Prompt

Higgsfield Prompt Engineering

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.

• 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; 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 prompts (30–100 words) win; Subject + Action must sit in the first 20–30 words [→](#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, then cranes up to reveal the
skyline. Cinematic style, cold blue tones, 16:9.

Timestamped (use only for precise multi-beat sequences)

Only use when exact timing of separate actions matters — e.g., a transformation, a multi-phase action sequence, or a beat-synced music video. Maps to Cinema Studio 3.0's Custom multi-shot mode.

0–3s: Wide establishing shot. The fighter stands alone in the ring, chest heaving.
3–6s: Crash Zoom In on his face. Sweat on his brow, jaw clenched.
6–10s: 360 Orbit as he raises his fists. Crowd noise rises.

---

High-Performing Prompt Patterns

> The #1 mistake in video prompting: over-describing appearance and under-describing > behavior. Give your subject something to DO. Give them an internal state that creates > visible behavior. A verb that describes motion or intention is more important than > adjectives.

Specificity beats generality:

• ❌ "the camera moves dramatically"
• ✅ "camera Dolly Zoom In — subject stays the same size as the background rushes forward"

Active verbs carry the scene:

• ❌ "a woman is in an alley"
• ✅ "a woman darts through a rain-soaked alley, coat flapping, boots splashing"

Name the camera control: Higgsfield understands its own preset names. Always use them explicitly.

• ❌ "the camera slowly circles"
• ✅ "360 Orbit around the subject"

Lead with subject, end with style: Subject → Action → Camera → Style is the most reliable order.

Keep it under 200 words: Focused prompts outperform exhaustive ones. One clear intention > ten vague details.

Cinema Studio: Keep it under 512 characters: Cinema Studio has a hard 512-character limit on prompts (both 2.5 and 3.0).

• 2.5: @ Element chips consume ~80–100 hidden characters each. With 2 @ tags, keep visible text under ~250 chars.
• 3.0: @ references (images/video/audio) are media attachments, not inline metadata — they consume less hidden space. Keep visible text under ~350–400 chars with references, ~450–500 without.

See the Cinema Studio skill for full character budget details.

---

The Pre-Prompt Checklist

Before writing any prompt, answer these five questions. Vague prompts like "give me something cinematic" tell the AI nothing.

| Question | What to specify | |----------|----------------| | Who? | Subject + appearance (e.g. "a man in a leather jacket") | | Where? | Environment + atmosphere (e.g. "in a narrow aircraft galley, cold blue light") | | What's happening? | 1 primary action (e.g. "punches his opponent") | | Camera movement? | Named preset (e.g. "Handheld") or Cinema Studio Director Panel | | Mood/Genre? | Style + color grade, or Cinema Studio genre selection |

---

One Action Per Scene

AI models can replicate real-life physics — but only so much at once. Asking for multiple complex actions in one clip overwhelms the model.

Rule: 1 primary action per clip, with 1–2 secondary actions max.

Break complex sequences into separate shots and stitch them in a video editor, or use Multi-Shot Manual mode to prompt each scene separately.

Fast Motion Trick: If fast motion keeps morphing or breaking, generate the scene in Slow Mo first, then speed it up in post (CapCut, Premiere, DaVinci). The model renders cleaner physics in slow motion.

---

Generic-Emotion Decomposition — Which kind of X?

Never leave a generic emotion in a prompt. "Sad" / "angry" / "surprised" / "scared" / "thoughtful" / "in love" — each is at least three or four distinct physical realizations, and the model renders a different version depending on which one your prompt invites. A prompt that says only "she looks surprised" produces a different shot every regeneration and degrades adherence across batches.

The rule: decompose the generic emotion into specific muscle movements, breath, eyes, and skin. If you can't decompose confidently, ask the user to choose a variant.

Clarification template — offer when the script or user supplies a generic emotion you cannot decompose without inventing detail:

> Which kind of surprise? > (a) Light positive — eyebrows lift, lips part softly, slow inhale > through the nose, no other movement. > (b) Shock — sharp inhale through the mouth, eyes widen, body > freezes in place, hand involuntarily lifts to chest. > (c) Disbelief — slow blink, head tilts a fraction, lips press > together, only one eyebrow lifts. > (d) Surprise-with-joy — eye light shifts (catchlight reads), > smile builds gradually, shoulders relax.

Same shape applies to any generic adjective — "tense" / "sad" / "angry" / "scared" / "thoughtful" / "in love" each decomposes into 3-5 distinct physical realizations. The decomposed prompt produces a performance; the generic prompt produces AI-video.

> Preset library alternative. For named micro-expression presets > that drop into a prompt without first-principles decomposition, > see ../higgsfield-soul/SKILL.md § Micro-Expressions. The catalog > covers most common emotional registers with locked physical > descriptors. Use the decompose-from-first-principles rule above > when no preset matches; use the preset library when one does.

Layered emotion states

Single-axis decomposition (above) names one register: angry / sad / surprised. Layered emotion names a composite state where two registers stack — anxious determination, tired tenderness, bitter amusement, cornered calculation. Production-team practice finds the model renders layered states better than single registers when the layering is described as one channel modulating another: the dominant state plus the underlying state plus the visible tell.

• Anxious determination — set jaw + locked gaze (determination)

with shallow chest breath and a single hand at the side flexing open-closed (anxiety underneath).

• Tired tenderness — soft micro-smile + half-closed eyes

(tenderness) with the body weight settled, slow blink interval (tiredness underneath).

• Bitter amusement — one-sided smirk + eye-shine (amusement)

with no smile crinkles at the eye corners (bitterness underneath).

Compose layered states by stacking decomposed physical realizations from the single-axis catalog. The dominant state goes in the face; the underlying state goes in breath, posture, and hand-state; the visible tell sits in the eyes.

For finer control, layer a tiny detail on top of an existing emotional cue: Roco is very upset, and his lower lip trembles. The base emotion gets the broad performance; the tiny detail gives the model a specific physical cue to render. Production-team discipline holds that the model renders the simple-emotion-plus- tiny-detail compound better than either an over-decomposed prompt or a too-generic one.

---

Identity vs. Motion Separation Rule

When a prompt involves Soul ID or any character who must stay consistent across shots, always split the output into two clearly labeled blocks:

Identity Block — Static visual descriptors ONLY

• Face features, skin tone, body type, distinguishing marks
• Clothing, accessories, color palette
• NO motion, NO camera, NO temporal language

Motion Block — Temporal and camera ONLY

• Camera movement, action choreography, speed
• Environmental motion, atmospheric changes
• NO character appearance repetition

Bad (mixed) — identity drifts:

A woman with sharp cheekbones and auburn hair in a blue trench coat runs through
a rain-soaked alley, her coat flapping, sharp cheekbones catching the neon light,
camera chasing her at full speed, her auburn hair streaming behind her.

Good (separated) — identity stays locked:

Identity Block:

The Soul ID character — sharp cheekbones, auburn hair shoulder-length,
wearing a blue trench coat with silver buttons, lean athletic build.

Motion Block:

She runs through a rain-soaked alley, coat flapping behind her.
Camera: Action Run — low behind, matching pace.
Neon reflections streak across wet concrete.
Style: Cinematic, cold blue shadows, warm neon accents. 16:9.

When to apply this rule:

• Always when Soul ID is active
• Always in multi-shot sequences where the same character appears
• Always when camera movement is involved alongside a character
• In Cinema Studio, identity goes in the @ Element definition; motion goes in the prompt

> Camera matches emotion, not just identity. The Motion Block describes WHAT > the character does and HOW the camera moves. The quality of the camera motion > — jittery handheld for anger, smooth handheld breathing for calm, static + slow > push for revelation — should track the focal character's emotional state. See > ../higgsfield-camera/SKILL.md § Camera-Emotion Sync for the 6-emotion movement > map and the emotional-arcs-within-a-shot pattern. For decomposing the underlying > generic emotion before picking a camera prescription, see § Generic-Emotion > Decomposition above.

---

Conflict resolution between sub-skills

Sub-skills can legitimately nominate different things for the same shot. higgsfield-camera § Camera-Emotion Sync nominates handheld-slow-low for sadness; higgsfield-prompt § Scene Archetype Router permits locked dolly-in for the Atmosphere archetype where mood-is-the-content. When two sub-skills nominate different camera moves (or motion presets, or style registers) for the same scene, resolve in this order:

1. Explicit user direction wins. If the user said "slow push-in," that's the camera move. The agent's job is to make that direction work with the rest of the structure, not to override it.
2. Scene archetype next. If the user did not specify, pick the archetype-recommended move (Atmosphere → static / slow push-in / locked-off; Action → handheld / whip-pan / FPV; Dialogue → shoulder-coverage / push-in on emotion).
3. Emotion-sync register last. Camera-Emotion Sync nominations are the default tiebreaker when archetype is unclear.

When the resolution is non-obvious, surface it. Tell the user which sub-skill nominated what and why you picked one over the other — this is meta-correct behavior and lets the user override. Silent picking is the failure mode; transparent picking is the discipline.

---

Common Prompt Mistakes

| Mistake | Fix |

…

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: OSideMedia
• Source: OSideMedia/higgsfield-ai-prompt-skill
• License: MIT
• Homepage: https://higgsfield.ai

Install and usage instructions live in the source repository linked above.