Higgsfield Cinema

Higgsfield Cinema Studio 2.5

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.*

• Three Cinema Studio versions coexist (2.5 / 3.0 / 3.5) — user-selected, no auto-routing; always detect the version first →
• Hard 512-character prompt cap; 2.5 @ Element chips eat ~80–100 hidden chars each →
• Elements System: define @Characters/@Locations/@Props once, call everywhere →
• 3.5 main UI = three pills (Genre / Style / Camera), each Auto by default — override only with a creative reason →
• 7 confirmed 3.5 genres: General · Action · Horror · Comedy · Noir · Drama · Epic — never invent genre names →
• Style presets: 8 Color Palettes · 6 Lighting · 9 Camera Moveset Styles, or free-form Manual Style →
• Camera axes: 3 bodies · 5 lenses · focal 8/14/35/50/75mm · aperture f/1.4–f/4–f/11; two camera vocabularies coexist — vocabulary follows the selected model →
• Output enums: 7 aspect ratios incl. 21:9 · 480p/720p/1080p · duration 4–15s · Sound On/Off →
• Lead every delivered shot with the one-line settings strip (UI presets ≠ prompt text; never restate strip values in the body) →
• The UI shot counter caps internal cuts — "strictly N shots" must keep N within it (observed cap 4; API exposes no max — UI behavior, verify live) →
• Manual Style = saved ≤2,000-char block of project LAWS (grade, lighting law, texture, performance register); it replaces the preset axes →
• 480p drafts validate the prompt, NOT the take — no seed param; transfer a look via Hero Frame + start/end-frame pinning →
• Resolution matrix has two axes: shot physics × delivery context; 4K-finish pipelines master at model max res in std mode →
• Seedance fast mode cannot output 1080p — drafting in fast then "switching up" silently changes mode AND res →

Cinema Studio is Higgsfield's professional filmmaking environment — a full production

workflow for multi-shot, character-consistent cinematic content. It's fundamentally

different from single-clip generation: you're building sequences, not individual videos.

Cinema Studio vs Standard Generation

| | Standard Generation | Cinema Studio 2.5 | Cinema Studio 3.0 (Business/Team Plan) | Cinema Studio 3.5 |

|--|--------------------|--------------------|----------------------------------------|--------------------|

| Output | Single clip | Multi-shot sequence | Multi-shot sequence | Multi-shot sequence |

| Character consistency | Manual / Soul ID only | Reference Anchor system | @ reference system (up to 9 images) | @ reference system (extends 3.0) |

| AI actor generation | Not available | Soul Cast — generate actors from parameters (no photos) | Soul Cast — General (2K) / Character (4K) / Location (4K) modes, 0.125 credits | Same Soul Cast surface — see 3.0 |

| Camera control | Named presets | Director Panel (18 movements) | Director Panel + Smart (auto camera planning) | Camera Settings 4-axis panel (Camera Body / Lens / Focal Length / Aperture) — see Cinema Studio 3.5 section |

| Optical physics | Not available | Full camera body + lens stack | Not available | Available — restored via Camera Settings panel (different vocabulary from 2.5 — see Cinema Studio 3.5 section) |

| Color grading | Not available | Built-in suite (temp, contrast, grain, bloom, etc.) | Not available | Available — Color Palette axis in Style Settings panel (8 named palettes) |

| Shot structure | One prompt = one clip | Up to 6 scenes, 12s total max, per-scene config | Smart (auto) + Custom multi-shot (up to 6 scenes, 15s) | Multi-shot supported — Duration 4s–15s |

| 3D exploration | Not available | Gaussian splatting — move inside any generated image | Not available | Same as 3.0 (not available) |

| Batch generation | Not available | Grid generation — up to 16 variations per credit | Not available | Configurable Batch Size (exploration multiplier) |

| Storyboard | Not available | Higgsfield Popcorn integration | Not available | Same as 3.0 |

| Speed control | Not available | Speed Ramp (6 modes) | Speed Ramp (7 modes + Bullet Time, Hero Moment) | Not separately tested in this release — see UI for 3.5-specific surface |

| Genre | Style descriptions | 8 named genres | 7 genres (General, Action, Horror, Comedy, Noir, Drama, Epic) | Manual catalog (General, Action, Horror, Comedy, Noir, Drama, Epic + others surfaced in UI) |

| Audio | Model-dependent | On/Off | On/Off (native dual-channel stereo) | On/Off (generated alongside video) |

| Video resolution | Model-dependent | Up to 1080p | Up to 720p (may increase) | 480p / 720p / 1080p (three-tier) |

| Image resolution | Model-dependent | Up to 4K | Up to 4K (Character/Location) · Up to 2K (General) | Not separately tested in this release |

| Max video duration | Model-dependent | 12s | 15s | 15s |

| Aspect ratios | Model-dependent | 6 options | 7 options (+ 21:9 ultrawide) | 7 options (Auto, 16:9, 9:16, 4:3, 3:4, 1:1, 21:9) |

| Plan requirement | All plans | All plans | Business/Team plan only | Plan availability not separately verified in this release — see Higgsfield plan documentation |

Use Cinema Studio when:

• You need 2+ shots that must feel like the same film
• Character geometry must be locked across cuts
• You want professional optical physics (lens flare, depth of field, sensor grain) — 2.5 only
• You're building a short film, branded content, or any sequence longer than one clip

Stick with standard generation when:

• Single clip is sufficient
• Speed matters more than consistency
• Exploring ideas before committing to a full sequence

⚠ Version Detection — Ask First

Before generating any Cinema Studio output, always ask the user:

> Are you working in Cinema Studio 2.5 or Cinema Studio 3.0?

If the user has already stated their version (e.g., "I'm using 3.0" or "Cinema Studio 3.0"), remember it and don't ask again. But never assume — 2.5 and 3.0 have fundamentally different feature sets.

Why this matters:

• 2.5 has optical physics (camera body + lens stack), color grading, 3D Mode, grid generation
• 3.0 has none of those — outputting them wastes the user's time and causes confusion
• 3.0 has features 2.5 doesn't: native audio, Smart shot control, 21:9 ultrawide, 15s duration
• Speed Ramp options differ between versions
• Genre lists differ between versions

Once the version is known, use ONLY that version's output format and feature set. Never mix features from one version into output for the other.

The 10-Step Cinema Studio 2.5 Workflow

Cinema Studio 2.5 extends the pipeline in both directions: pre-production (Soul Cast +

location prompt) before generation, and post-production (color grading) after.

 1. SCRIPT        → Write or paste your scene description / shot list
 2. SOUL CAST     → (New in 2.5) Generate AI actors from parameters or use saved Elements
 3. REFERENCE     → Upload character photo → create Reference Anchor (or use Soul Cast actor)
 4. ELEMENTS      → (Optional) Define @Characters, @Locations, @Props if needed
 5. OPTICAL STACK → Select camera body + lens + focal length + aperture (image mode)
 6. HERO FRAME    → Generate a key image that defines the visual tone
 7. COLOR GRADE   → (New in 2.5) Apply color grading to keyframes before video generation
 8. CAMERA CONFIG → Set Director Panel movement + Speed Ramp + Duration in UI
 9. SHOT MODE     → Choose Single Shot / Multi-Shot Auto / Multi-Shot Manual
10. GENERATE → EXPORT → Chain into timeline or export to editing

Elements System — Define Once, Call Everywhere

Elements are Cinema Studio's reusable asset library. Create a Character, Location, or Prop

once and reference it with @ in any subsequent prompt.

Three element types:

| Type | What it stores | Call with |

|------|---------------|-----------|

| Character | Person, appearance, costume | @CharacterName |

| Location | Environment, setting, atmosphere | @LocationName |

| Prop | Object, vehicle, specific item | @PropName |

Creation workflow:

• Open Elements panel → New Element → choose type
• Upload reference image(s)
• Name the element (this becomes the @ tag)
• Add description (appearance details, key features)
• Save → now available across all shots in this project

Per-Character Emotion: In Multi-Shot mode, each character can have an **emotion setting

per scene**. The available emotions are:

| Emotion | Effect |

|---------|--------|

| Joy | Smiling, warm expression, positive energy |

| Fear | Wide eyes, tense posture, defensive body language |

| Surprise | Raised brows, open mouth, alert stance |

| Sadness | Downcast eyes, slumped posture, muted energy |

Set emotion per character per scene in the UI — this keeps expression changes out of the

prompt field and lets the model handle the subtlety of facial animation.

@ tag rule — use exactly what the user provides, nothing more

Only use @ tags for Elements the user has explicitly given you in this conversation.

If they give you @Marcus but no location or prop tags, write the location and props

as plain description. Never invent or assume @ tags for anything the user hasn't named.

Each @ tag the user gives you = they have that Element set up. Silence = they don't.

No Elements provided — write everything as description:

A woman with dark hair and a red coat walks through a narrow downtown alley at night.
She carries a worn leather briefcase. She stops under a streetlight, turns to camera.

User provides @Sarah only — use it, describe the rest:

@Sarah walks through a narrow downtown alley at night.
She carries a worn leather briefcase. She stops under a streetlight, turns to camera.

User provides @Sarah, @DowntownAlley, @LeatherBriefcase — use all three:

@Sarah walks through @DowntownAlley, carrying @LeatherBriefcase.
She stops under a streetlight, turns to camera.

Key rule: Match exactly what the user gives you. No more, no less.

Tags they give you = Element exists. Anything else = write it as description.

Element Library Surface — Source Tabs and Categories

The @ symbol opens a unified asset picker. The picker is organized as a two-dimensional structure: source tabs across the top (where the asset comes from), and element categories within the Elements tab (how project assets are grouped).

Source tabs (5):

| Tab | What's in it |

|-----|--------------|

| Uploads | Assets the user brings in directly — original photos, plates, prop shots |

| Image Generations | Prior generated stills available for reference (useful for self-referencing continuity across shots — pull a specific look or pose that emerged from a previous generation back into a new one) |

| Video Generations | Prior generated clips available for reference (useful for camera-memory or motion reference — feed a previous clip's framing or movement back into a new generation) |

| Elements | Curated/saved assets in the project library — the primary continuity surface |

| Liked | Favorited assets across the picker — fast recall for go-to references |

Element categories within the Elements tab (6):

| Category | What it groups |

|----------|----------------|

| All | Everything in the project |

| Pinned | Surfaced for quick access in this project — the user's working set for the current sequence |

| Shared | Accessible across collaborators or contexts (exact sharing scope is platform-managed) |

| Characters | Identity references — people, faces, performers |

| Locations | Environment references — rooms, exteriors, settings |

| Props | Object references — vehicles, items, set pieces |

Build the element library before generation. For a project with recurring characters, locations, or props — a short film, a series of branded videos, a multi-shot sequence — establish each recurring asset as an Element first, then reference it via @ in every shot. This is the platform-native implementation of the Reference-Based Prompt Mode discipline already documented elsewhere: references with assigned roles, not references as inspiration. See ../higgsfield-seedance/SKILL.md for the Reference-Based Prompt Mode discipline, and the existing "@ tag rule — use exactly what the user provides" guidance earlier in this section for how to use @ tags inside the prompt itself.

Cross-shot continuity tip. For continuation work, the Image Generations and Video Generations source tabs let you reference prior outputs from the same project — useful when a Character Element doesn't capture a specific look or pose that emerged from a particular generation. Pull the exact frame back in via the Generations tab rather than re-prompting from scratch.

Soul Cast — AI Actor Generation

Soul Cast is Cinema Studio 2.5's character generation system — create AI actors from

parameters instead of uploading photos. This is fundamentally different from Soul ID.

Soul Cast vs Soul ID

| | Soul Cast | Soul ID |

|--|-----------|---------|

| Input | Parameter selection | 20+ photos of real person |

| Purpose | Generate AI actors from scratch | Maintain consistency of a known face |

| Photo required | No | Yes |

| Powered by | Nano Banana 2 | — |

Soul Cast Parameter Categories (8 total)

| # | Category | Options |

|---|----------|---------|

| 1 | Genre | Action, Adventure, Comedy, Drama, Thriller, Horror, Detective, Romance, Sci-Fi, Fantasy, War, Western, Historical, Sitcom (14 options) |

| 2 | Budget | Production budget slider (in millions) — higher = refined blockbuster look, lower = raw/gritty |

| 3 | Era | Decade selection starting from 1900s — grounds character in correct time period |

| 4 | Archetype | Innocent, Everyman, Hero, Caregiver, Explorer, Rebel, Lover, Creator, Jester, Sage, Magician, Ruler (12 options) |

| 5 | Identity | Gender, race, age |

| 6 | Physical Appearance | Height, eye color, hair, facial hair, etc. |

| 7 | Details | Scars, tattoos, freckles, other imperfections |

| 8 | Outfit | Casual, Formal, High Fashion, Military, Sporty, Workwear, Vintage (7 styles) |

Key Features

• Add up to 3 Soul Cast characters per keyframe — choose from saved Elements or generate on the spot
• "Save to elements" button to reuse a specific Soul Cast actor across projects
• Every actor auto-generates a backstory + character sheet (personality traits, motivation, fear, flaw, strength)
• Designed to eliminate the "plastic/waxy" AI look — excels at skin textures and emotions
• Powered by the Nano Banana 2 model under the hood

Soul Cast Workflow

1. Open Cinema Studio → Navigate to Soul Cast panel
2. Set Genre + Era + Budget to establish the visual world
3. Select Archetype + Identity + Physical Appearance
4. Add Details (imperfections) + Outfit
5. Generate → Review backstory + character sheet
6. Save to Elements → Now available as @CharacterName across all shots
7. Repeat for additional characters (up to 3 per keyframe)

Built-in Color Grading Suite

Cinema Studio 2.5 adds a post-production color grading suite applied to keyframes

before video generation — enabling unified visual cohesion across all clips.

Controls

| Control | Effect |

|---------|--------|

| Color temperature | Warm ↔ cool shift |

| Contrast | Shadow/highlight separation |

| Saturation | Color intensity |

| Sharpness + effects | Detail enhancement |

| Highlights | Bright area control |

| Film grain | Analog texture overlay |

| Exposure | Overall brightness |

| Bloom | Highlight glow/diffusion |

Workflow

• Generate your keyframe image (Hero Frame or grid selection)
• Click the keyframe → "Colorgrade" button
• Adjust settings to taste
• Apply — grade is baked into the keyframe before video generation
• Repeat for each keyframe to maintain visual cohesion across the sequence

Tip: Grade your Hero Frame first, then match subsequent keyframes to it.

This is the post-production equivalent of a DIT (Digital Imaging Technician) on set.

Optical Physics Engine

Cinema Studio's Image Mode gives you a full camera body + lens stack. These are the

exact names from the UI (previous versions had wrong names — these are corrected).

Claude's job when building a Cinema Studio image prompt: Always recommend a specific

optical stack — body + lens + focal length + aperture — with a one-line reason why.

Never leave the optical stack blank or say "choose based on preference." Make a call.

Optical Stack Recommendations by Intent

Use the user's creative intent to select the stack. The most important signal is

what the image needs to feel like — not just the genre.

Portrait / Character Focus

| Feel | Body | Lens | Focal | Aperture | Why |

|------|------|------|-------|----------|-----|

| Warm, intimate, skin-flattering | Full-Frame Cine Digital | Warm Cinema Prime | 50mm | f/1.4 | Flattest most natural face rendering, creamy background separation |

| Artistic / swirling bokeh | Full-Frame Cine Digital | Swirl Bokeh Portrait | 50mm | f/1.4 | Distinctive background treatment isolates subject dramatically |

| Prestige / awards-film quality | Grand Format 70mm Film | Classic Anamorphic | 50mm | f/1.4 | Rich grain + horizontal bokeh = immediate cinematic credibility |

| Fashion / editorial sharp | Premium Large Format Digital | Clinical Sharp Prime | 50mm | f/4 | Maximum face detail, clinical modern look |

| Nostalgic / vintage character | Classic 16mm Film | 70s Cinema Prime | 50mm | f/1.4 | Grain + warmth + soft rendering = timeless feel |

Scene / Environment / Establishing

| Feel | Body | Lens | Focal | Aperture | Why |

|------|------|------|-------|----------|-----|

| Cinematic wide establishing | Studio Digital S35 | Compact Anamorphic | 14mm | f/4 | Industry-standard look, oval bokeh on background elements |

| Epic / spectacle | Grand Format 70mm Film | Classic Anamorphic | 14mm | f/4 | Scale + grain + strong lens character = instant epic quality |

| Documentary / real | Modular 8K Digital | Clinical Sharp Prime | 35mm | f/4 | Clean, high-DR, no optical character — feels captured not staged |

| Moody / atmospheric | Classic 16mm Film | Halation Diffusion | 35mm | f/4 | Grain + highlight glow creates organic atmosphere |

| Nature / landscape | Modular 8K Digital | Clinical Sharp Prime | 14mm | f/11 | Maximum depth, maximum detail, everything sharp |

Emotion / Tone-Driven

| Feel | Body | Lens | Focal | Aperture | Why |

|------|------|------|-------|----------|-----|

| Romance / dreamlike | Full-Frame Cine Digital | Halation Diffusion | 50mm | f/1.4 | Highlight glow + shallow focus = soft emotional warmth |

| Tension / suspense | Studio Digital S35 | Compact Anamorphic | 35mm | f/4 | Neutral but cinematic — lets the subject and lighting carry the mood |

| Dread / horror | Classic 16mm Film | Vintage Prime | 35mm | f/4 | Distortion + grain + flat rendering = unsettling realism |

| Energy / action | Studio Digital S35 | Compact Anamorphic | 35mm | f/4 | S35 + anamorphic = kinetic, industry-standard action feel |

| Melancholy / memory | Classic 16mm Film | Halation Diffusion | 50mm | f/1.4 | Softness + grain reads immediately as memory or longing |

| Surreal / abstract | Full-Frame Cine Digital | Creative Tilt Lens | 14mm | f/1.4 | Selective focus plane makes real scenes feel dreamlike or miniature |

Commercial / Functional

| Feel | Body | Lens | Focal | Aperture | Why |

|------|------|------|-------|----------|-----|

| Product / packshot | Premium Large Format Digital | Clinical Sharp Prime | 50mm | f/11 | Everything sharp, no optical distraction from the product |

| Product with lifestyle feel | Full-Frame Cine Digital | Warm Cinema Prime | 50mm | f/4 | Warm, flattering, some background separation — not clinical |

| Food / texture detail | Premium Large Format Digital | Extreme Macro | 50mm | f/4 | Maximum detail rendering for close-up texture work |

| Architecture / interior | Modular 8K Digital | Clinical Sharp Prime | 14mm | f/11 | Wide + sharp = every detail of the space visible |

| Fashion editorial | Premium Large Format Digital | Classic Anamorphic | 50mm | f/1.4 | High-end magazine look — sharp subject, cinematic background |

How Claude Should Deliver the Output

Cinema Studio has two separate inputs:

• UI dropdowns — Camera body, Lens, Focal length, Aperture, Genre, Director Panel, Speed Ramp
• Prompt field — Scene description only. No camera/lens/aperture text goes here.

Claude must always output these as two clearly separated blocks:

Block 1 — UI Settings (select these in Higgsfield before pasting the prompt)

Camera:   Full-Frame Cine Digital
Lens:     Warm Cinema Prime
Focal:    50mm
Aperture: f/1.4
Genre:    Intimate
↳ Why: Flattest, most natural face rendering. Creamy background separation
       keeps all attention on the character without any lens distortion.

Block 2 — Prompt (paste this into the Cinema Studio prompt field)

[Scene description only — no camera, lens, aperture, or genre language here]

Rule: Never put camera body names, lens names, focal lengths, apertures, or genre

names inside the prompt text. They live in the UI, not the prompt field.

Camera Body Reference

| Body | Character | Best for |

|------|-----------|----------|

| Premium Large Format Digital | Ultra-sharp, clinical modern | Commercial, fashion, product |

| Classic 16mm Film | Grain, texture, organic warmth | Drama, indie, period, horror |

| Modular 8K Digital | High dynamic range, clean | Nature, documentary, landscape, architecture |

| Full-Frame Cine Digital | Cinematic standard, versatile | Narrative, character, romance, drama |

| Studio Digital S35 | Super 35, industry standard | Action, thriller, genre, suspense |

| Grand Format 70mm Film | Epic scale, rich grain | Spectacle, prestige cinema, blockbuster |

Lens Reference

| Lens | Effect | Best for |

|------|--------|----------|

| Creative Tilt Lens | Selective focus plane, miniature effect | Surreal, abstract, stylized |

| Compact Anamorphic | Oval bokeh, subtle flare | Cinematic standard, action, thriller |

| Halation Diffusion | Glow around highlights, dreamy | Romance, memory, soft drama, horror atmosphere |

| Extreme Macro | Hyper close-up detail | Product texture, food, insects, fine detail |

| 70s Cinema Prime | Warm, slightly soft vintage character | Period pieces, nostalgia, retro |

| Warm Cinema Prime | Golden warmth, skin-flattering | Portraits, drama, lifestyle |

| Swirl Bokeh Portrait | Swirling background blur | Artistic portrait, fashion editorial |

| Vintage Prime | Classic rendering, subtle distortion | Retro, lo-fi, character, horror |

| Classic Anamorphic | Strong flare, wide horizontal bokeh | Prestige, blockbuster, fashion |

| Clinical Sharp Prime | No aberration, maximum resolution | Commercial, technical, product, documentary |

Focal Length Reference

8mm · 14mm · 35mm · 50mm

• 8mm — Ultra-wide, immersive distortion. Action POV, environment, disorientation
• 14mm — Wide, environmental, scale. Establishing shots, landscape, architecture
• 35mm — Natural human field of view. Documentary, street, two-shots, candid
• 50mm — Classic portrait compression. Character close-ups, product, single subject

Aperture Reference

• f/1.4 — Shallow depth of field. Subject sharp, background creamy bokeh. Intimacy, focus, emotion
• f/4 — Balanced. Subject sharp, background slightly soft. Most versatile, natural look
• f/11 — Deep depth of field. Everything sharp front to back. Product, landscape, architecture

Director Panel — 18 Camera Movements

⚠ Use ONLY these exact movement names in Cinema Studio output. General cinematic terms like "Crane Down", "Whip Pan", "FPV Drone", "Crash Zoom" etc. (from vocab.md) are valid for standard video generation and image prompts outside Cinema Studio, but they are NOT Director Panel options. Inside Cinema Studio, map to the closest equivalent (e.g., Crane Down → Jib Down, Crane Up → Jib Up).

All movements available in Cinema Studio's Director Panel:

| Movement | Description | Best for |

|----------|-------------|----------|

| Static | Locked off, no movement | Dialogue, tension, composition |

| Handheld | Organic shake, documentary feel | Urgency, realism, action |

| Zoom Out | Focal length pulls back | Revelation, isolation |

| Zoom In | Focal length pushes in | Intensity, focus on subject |

| Camera Follows | Tracks subject movement | Chase, pursuit, accompaniment |

| Pan Left | Horizontal sweep left | Reveal, environment scan |

| Pan Right | Horizontal sweep right | Reveal, environment scan |

| Tilt Up | Vertical sweep up | Scale, aspiration, reveal |

| Tilt Down | Vertical sweep down | Weight, consequence, ground |

| Orbit Around | 360° around subject | Isolation, drama, examination |

| Dolly In | Physical push toward subject | Emotional intimacy |

| Dolly Out | Physical pull from subject | Distance, context reveal |

| Jib Up | Camera rises on arm | Scale, context, god's eye |

| Jib Down | Camera descends on arm | Grounding, arrival |

| Drone Shot | Aerial movement | Landscape, scale, geography |

| Dolly Left | Lateral push left | Parallel tracking, reveal |

| Dolly Right | Lateral push right | Parallel tracking, reveal |

| 360 Roll | Camera rolls on axis | Disorientation, stylized |

| Auto | Model selects best movement | When unsure |

Speed Ramp

Controls temporal feel of the shot. Set per-scene in Cinema Studio.

> ⚠ Speed Ramp options differ between versions. Use ONLY the table for the version the user specified. Never output a 2.5 ramp name in 3.0 output or vice versa.

Cinema Studio 2.5 Speed Ramps (6 modes)

| Mode | Effect | Best for |

|------|--------|----------|

| Linear | Consistent speed throughout | Standard, natural |

| Slow Mo | Reduced playback speed | Impact moments, emotion |

| Speed Up | Accelerated playback | Montage, energy, passage of time |

| Impact | Fast → sudden slow at key moment | Action, hits, reveals |

| Auto | Model selects based on content | When unsure |

| Custom | Draw your own speed curve | Precise creative control |

Custom curve: Blue line with draggable nodes. Pull up = slow down, pull down = speed up.

Left = beginning of clip, right = end.

2.5-only values — NEVER use in 3.0 output: Linear, Slow Mo, Speed Up, Impact, Custom

Cinema Studio 3.0 Speed Ramps (7 modes)

| Mode | Effect | Best for |

|------|--------|----------|

| Auto | Model selects based on content | When unsure |

| Slow-mo | Reduced playback speed | Impact moments, emotion |

| Ramp Up | Gradual acceleration | Building energy, montage |

| Flash In | Fast start → ease to normal | Dramatic entrances, openings |

| Flash Out | Normal → sudden snap acceleration | Launches, exits, explosive action |

| Bullet Time | Ultra-slow at key moment, normal around it | Action hits, reveals, hero beats |

| Hero Moment | Slow build → dramatic pause → release | Character reveals, power moves |

3.0-only values — NEVER use in 2.5 output: Ramp Up, Flash In, Flash Out, Bullet Time, Hero Moment

Genre Selection

> ⚠ Genre lists differ between versions. Use ONLY the genres for the version the user specified.

Cinema Studio 2.5 Genres (8)

General · Action · Horror · Comedy · Western · Suspense · Intimate · Spectacle

Genre affects lighting defaults, color grading baseline, and motion style suggestions.

You can always override with explicit prompt language — genre is a starting point.

| Genre | Lighting default | Color tendency | Motion style |

|-------|-----------------|----------------|--------------|

| General | Neutral | Balanced | Varies |

| Action | Hard, high contrast | Desaturated, cool | Dynamic |

| Horror | Low key, harsh shadows | Desaturated, teal/green tint | Slow or sudden |

| Comedy | Bright, even | Warm, saturated | Light, energetic |

| Western | Golden hour / dusty | Warm amber | Steady, wide |

| Suspense | Low key, motivated | Cold, muted | Slow build |

| Intimate | Soft, warm | Warm, skin-flattering | Gentle |

| Spectacle | Dramatic, high contrast | Bold, saturated | Epic, sweeping |

2.5-only genres — NEVER use in 3.0 output: Western, Suspense, Intimate, Spectacle

Cinema Studio 3.0 Genres (7)

General · Action · Horror · Comedy · Noir · Drama · Epic

3.0-only genres — NEVER use in 2.5 output: Noir, Drama, Epic

Shot Modes

Single Shot

Standard generation — one prompt, one clip. Same as regular Higgsfield but with the

optical stack and Director Panel applied.

Multi-Shot Auto

Describe the full sequence in one prompt. Cinema Studio breaks it into shots automatically.

Good for: rough sequences, exploration, when you don't need per-shot control.

Example: "A woman walks into a bar, sits down, orders a drink. Bartender slides it over.
She takes a sip and stares at her reflection in the mirror behind the bottles."
→ Cinema Studio Auto generates: Establishing shot / Walk to seat / Order / Drink delivery / Reflection closeup

Multi-Shot Manual

Full per-scene control. Up to 6 scenes, each with its own:

• Prompt
• Camera movement (Director Panel)
• Speed Ramp
• Duration

⚠ 12-Second Total Runtime Cap: The combined duration of all scenes in a Multi-Shot

sequence cannot exceed 12 seconds total. Plan your per-scene durations to stay within

this limit (e.g., 6 scenes × 2s each, or 4 scenes × 3s, or 3 scenes × 4s).

Cost transparency: Multi-Shot Manual with 4 variations = 24 generations total (6 scenes × 4 variations). Plan credits accordingly.

Multi-Shot Manual workflow:

• Scene 1: Establishing shot — wide, sets location
• Scene 2: Character introduction — medium, shows protagonist
• Scene 3: Action beat — closer, movement
• Scene 4: Reaction — close-up, emotion
• Scene 5: Consequence / turn — medium or wide
• Scene 6: Resolution / button — varies

Morph-Cut and Smooth-Cut breathing room — 2-second still moments. Editors

land morph cuts and smooth cuts (transition styles in DaVinci Resolve, Premiere,

and similar editors that hide the cut by morphing similar frames) on stillness,

not on motion. If every shot starts and ends mid-action, every cut between them

has to happen mid-action too — and the model renders mid-action transitions

poorly. Build cut-friendly material by prompting an explicit 2-second

still-or-near-still moment at the start AND end of every shot. Examples

of buildable stillness: a held look, a settled pose, a held pause before motion

begins, a held breath after motion stops. The middle of the shot can be as

kinetic as the script demands; the boundaries earn the cuts. This rule is

adapted from the Mr. Core methodology and pairs with editor-side workflow in

../higgsfield-pipeline/SKILL.md § Stage 8 — Assembly.

Reference Anchor System

The Reference Anchor locks character geometry (facial structure, proportions, costume silhouette)

across all shots in a sequence — preventing the character drift that happens in standard generation.

Setup:

• Upload a clear, well-lit reference photo of your character
• Cinema Studio generates an anchor from it
• Every subsequent shot in the project references this anchor
• Combine with Soul ID for full face + geometry lock

Best practices:

• Use a front-facing, neutral expression photo for the anchor
• Avoid glasses, hats, or accessories in the anchor image if they won't always be present
• One Reference Anchor per character — add multiple if you have a cast
• The anchor persists across the whole Cinema Studio project

Location Reference Sheets

Locations deserve the same asset-first treatment as characters. If a room, alley,

vehicle interior, or exterior reappears across multiple shots, generate it once as

a standalone asset and reuse it — don't re-describe it inside each scene prompt.

Scene-by-scene re-description is the root cause of the "every shot reinterprets

the environment" failure: walls drift, furniture rearranges, scale shifts, and the

world stops feeling like a single place.

The Five-View Location Sheet

A location sheet captures the space from enough angles that the model has a

complete spatial model to draw from. Generate these five views as one asset set:

| View | What it locks |

|------|---------------|

| Straight-on wide | The overall scale, focal point, and horizon line |

| Left-angle perspective | Side geometry, depth on the left |

| Right-angle perspective | Side geometry, depth on the right |

| Reverse / opposite view | What's behind the camera in the wide — finishes the 360° footprint |

| Close-up environmental details | Texture, wear, signage, small props that anchor identity |

Use Grid Generation (2×2 or 4×4) or 3D Mode on a hero wide to produce the alt

angles from a single seed — this keeps the light and material identity consistent

across views, which is the whole point.

What to Preserve on Reuse

When you bring the location back for a new shot, lock these four properties:

architecture (walls, openings, scale), light quality (source direction, color

temperature, hardness), color treatment (palette, grade), and key environmental

details (signage, damage, specific props that make this place THIS place). Keep

these out of the scene prompt — they live in the location asset. The scene prompt

should describe only what changes: character action, camera behavior, atmospheric

motion, time-of-day shift if any.

Failure Mode This Prevents

Without a location sheet, a six-scene sequence set in "a rain-soaked alley" will

render six different alleys. Each scene prompt re-interprets "rain-soaked alley"

from scratch. With a location sheet tagged as an @ Element or loaded as a

reference, all six scenes share one alley — the puddles are in the same places,

the neon sign says the same thing, the brick wall has the same pattern.

For the camera vocabulary that pairs with location reveals (Pan, Crane, Dolly Reveal),

see ../../vocab.md.

Reference Sheet Types — Beyond Characters and Locations

Reference sheets aren't only for faces and rooms. The underlying principle is

narrower than "character or location" — a reference sheet is any asset built

once to lock a specific property of the production. Each sheet type fixes a

different axis of the work: identity, architecture, motion behavior, wardrobe,

palette, or product. If a property has to read consistently across multiple

shots, give it its own sheet. If it only matters for one shot, write it inline

and move on.

When a sheet pays for itself: if a property will appear in three or more

shots, the sheet is cheaper than re-describing it every time and dramatically

more consistent than relying on prompt text alone. Single-shot details — a

one-time prop, a background extra, a one-off lighting cue — don't earn a sheet.

The character sheet (see ../higgsfield-soul/SKILL.md → Character Sheet

Creation) and the Location Reference Sheet above already cover identity and

architecture. The three sheet types below extend the same pattern to the rest

of the production:

Motion / Camera Sheet

A short reference clip — 3–10 seconds is plenty — that captures a camera path

or motion rhythm you want repeated across multiple shots. The sheet locks the

movement signature, not the content of any single shot. Treat it as a

project-wide style anchor pulled into a generation as an @Video reference, the

way a DP would carry a "look" across an entire film.

Use cases: a music video where the same dolly-in arc punctuates every chorus;

a fight sequence where a signature whip-pan recurs at every climax beat; a

brand piece where every product shot starts on the same slow orbit. Distinct

from a Kling 3.0 Motion Control reference clip — that drives a single

generation's motion transfer. The Motion / Camera Sheet is reusable across the

whole project.

Outfit / Material Sheet

Dedicated wardrobe reference. Locks fabric texture, color values, garment fit,

fastenings, and how the material moves and folds. Generate it once with even

lighting and multiple angles, then reuse it any time the costume needs to read

identically across cuts.

Use cases: a hero costume that appears across 12 scenes; a specific jacket that

must look the same in close-up and wide shot; a uniform that recurs across an

ensemble cast. The outfit sheet is not the same as a character sheet — the

character sheet locks identity (face, build, hair, distinguishing marks), while

the outfit sheet locks what the character is wearing AND how that wardrobe

behaves in motion. Build both when you have a hero costume on a hero character.

The piano test — wardrobe complexity has a generation cost. Every detail of

wardrobe complexity — buttons, ties, jewelry, scarves, layered garments,

intricate prints, fastening hardware — costs the model rendering budget. The

piano test (adapted from the Mr. Core methodology) is the rule: if a wardrobe

element is as visually demanding for the model to render as a piano in the

frame, the model will spend its budget rendering that element instead of the

action. Strip the wardrobe to the simplest silhouette that still reads as the

character. A trench coat reads as a trench coat without the buttons rendering

correctly. A uniform reads as a uniform without the rank insignia drifting

across frames. Design the costume's *signature* — the silhouette and one

identifying feature — and let the rest go simple. Hero costumes that must

render under close-up scrutiny earn their complexity; background costumes do

not.

Palette / Mood Sheet

A color and tonal anchor for the project. Lock the visual mood across an entire

sequence: shadow density, key/fill ratio, saturation level, signature accent

colors, grade direction. Use a single curated still or a small grid of grade

references — the goal is to give every subsequent generation a consistent

palette to reach for.

Use cases: a noir piece where every scene shares the same shadow density and

warm-amber-on-cool-blue grade; a cyberpunk sequence where neon-to-base-light

ratio stays fixed across 15 cuts; a brand campaign where a signature accent

color appears in every shot regardless of subject. Pairs naturally with the

Soul Hex color system and curated moodboards in

../higgsfield-moodboard/SKILL.md.

Product Reference Sheet

When a product reappears across multiple shots — a hero SKU in a brand

campaign, a recurring prop in a narrative piece, a single item shot from a

dozen angles for ecommerce — give it the same asset-first treatment as a

character or location. Generate the product once as a multi-view reference

sheet, then call it in subsequent shots. Re-describing the product inside

each scene prompt is the root cause of "every shot reinterprets the

product": branding shifts, materials drift, geometry rearranges, and the

hero stops feeling like a single object.

The Product Reference Sheet uses a 7-part prompt scaffold. Each part fixes

one axis of the product's identity. Build the parts in order — the locks

come first, then composition, then surface treatment, then capture

parameters, then negative space.

1. Identity Lock — what the product *is*. Geometry, scale, color

values, defining proportions, distinguishing physical features. The same

discipline as a character sheet's identity block, applied to an object.

2. Branding Lock — placement, scale, color, and treatment of every

brand element on the product: logos, wordmarks, tags, stitched labels,

embossed marks. Specify position relative to product geometry (centered

front panel, left sleeve, lower right corner) and rendering style

(embroidered, screen-printed, embossed, foil-stamped).

3. Layout — the multi-view grid. Standard Product Reference Sheet

layout covers eight orthographic views plus macro close-ups:

| View | What it locks |

|------|---------------|

| Front | Primary read — branding placement, overall silhouette |

| Back | Reverse details, secondary branding, construction seams |

| Left side | Profile geometry, depth on the left |

| Right side | Profile geometry, depth on the right |

| Top | Top-down silhouette, crown / lid / opening geometry |

| Bottom | Underside details, base / sole / footprint |

| 3-quarter | Hero angle — combines front and side reads |

| Macro close-ups | Branding detail / material weave / construction join / any product-specific detail that earns its own frame |

Eight views vs. the Five-View Location Sheet's five — products need more

orthographic angles than locations because the camera is closer and the

geometry is the subject, not the environment. Macro close-ups are the

product analogue of the location sheet's close-up environmental-details

view, scaled up to one per product-specific concern.

4. Background — #DCDCDC light gray, shadowless lighting, no

gradients, no reflections. Studio product-photo convention: the

background contributes zero visual information so the product reads as

the only subject. Specify all four constraints — #DCDCDC alone without

the shadowless + no-gradients + no-reflections trio still leaves the

model room to add atmospheric noise.

5. Realism — the Material Realism block. Reusable template populated

per material; six axes that together make a surface read tactile and

physically grounded rather than rendered-flat:

• Raised structure — what stands proud of the base surface and by

how much

• Tight density — how packed the surface elements are per unit area
• Visible direction — the directionality of grain, weave, thread, or

flow across the surface

• Micro shadowing — the small shadows cast by raised elements into

the surface valleys

• Surface compression following form — how the material deforms where

it meets seams, edges, or attached elements

• Curvature integration — how the surface and its texture follow the

product's overall geometry rather than sitting on top of it

Populate the six axes with material-specific vocabulary. Embroidery,

leather, knit, satin, brushed metal, and suede each have their own value

set; the six axes stay constant.

6. Camera — default product reference package: **Canon EOS R5 +

RF 100mm f/2.8L Macro IS USM, f/8, ISO 100**. The 100mm macro lens at

f/8 holds the whole product in sharp focus from front-most edge to

back-most edge across all eight views; ISO 100 keeps sensor noise out

of the gray background. Substitute only when a specific shot needs a

different read — e.g. shallow depth of field for a hero brand-detail

macro (f/4), or a wider focal length for an oversized product

(RF 50mm).

7. Restrictions — the content-fidelity block. The Product Reference

Sheet's job is to capture the actual product, not a stylized or

reinterpreted version. This block tells the model what NOT to do with

the source: don't redesign, don't reinterpret branding, don't beautify,

don't add styling. Frame composition discipline (no environmental

context, no props) is enforced here as part of the same content-fidelity

intent; the background/lighting constraints from Section 4 handle their

own scope and don't repeat here.

• No redesign
• No stylization
• No brand reinterpretation
• No added elements
• No alternate branding
• No additional logos
• No text overlays
• No props
• No environment
• No lighting effects
• No smoothing or beautification
• No beauty retouching

The Product Reference Sheet locks the product; narrative use of the

product happens in downstream scene prompts that call this sheet as a

reference.

Hat — Worked Example

A black baseball cap with an embroidered logo, set up as a Product

Reference Sheet:

• Identity Lock — six-panel baseball cap, black cotton twill, curved

brim, adjustable strap closure, pre-curved crown, eyelets on each

panel

• Branding Lock — embroidered wordmark centered on the front panel,

white thread, 4cm wide, positioned 3cm above the brim seam

• Layout — front / back / left / right / top / bottom / 3-quarter,

plus macro close-ups of the embroidered wordmark, the panel seams,

and the strap closure

• Background — #DCDCDC light gray, shadowless lighting, no

gradients, no reflections

• Realism (Material Realism populated for embroidery):
• Raised structure — raised thread structure, thread sitting proud of

the cotton twill base

• Tight density — tight stitch density across each letterform
• Visible direction — visible thread direction following each letter's

stroke path

• Micro shadowing — micro shadowing in the stitch valleys between

thread rows

• Surface compression following form — fabric compression around the

stitching where the thread tension pulls the twill in

• Curvature integration — embroidery curvature following the

pre-curved front panel rather than sitting flat

• Camera — Canon EOS R5, RF 100mm f/2.8L Macro IS USM, f/8, ISO 100
• Restrictions — no redesign, no stylization, no brand

reinterpretation, no added elements, no smoothing or beautification

For leather / knit / satin / brushed metal / suede hero products, swap

the Material Realism block's embroidery vocabulary for the material's

own value set on each of the six axes — the scaffold is identical.

The Reference Sheet Family

| Sheet | Locks | Lives in |

|-------|-------|----------|

| Character | Identity, face, build, distinguishing marks | ../higgsfield-soul/SKILL.md (Soul ID, character sheet creation) |

| Location | Architecture, light, color treatment, key environmental details | Location Reference Sheets, above |

| Motion / Camera | Camera path or motion rhythm reused across shots | This section |

| Outfit / Material | Wardrobe — fabric, color, fit, motion behavior | This section |

| Palette / Mood | Color and tonal mood across the whole project | This section + ../higgsfield-moodboard/SKILL.md |

| Product | Product geometry, branding placement, material/surface, multi-view layout | This section |

Build the sheets the project actually needs. A short ad with one character in

one outfit doesn't need an Outfit Sheet. A 15-shot music video with three

recurring camera moves and a tight color palette absolutely does.

Hero Frame

A Hero Frame is a key image you generate before committing to video — it defines the

visual tone, lighting, color, and composition of your sequence.

Why it matters: Generating a Hero Frame first costs ~1 credit. Adjusting the video

after generation costs full video credits. Get the look right on the image first.

Hero Frame workflow:

• Describe your opening shot with full optical stack
• Generate as image (Soul 2.0 or Nano Banana 2)
• Review: Is the lighting right? Color? Character look?
• Iterate on image until it's exactly right
• Use as the first frame / style reference for video generation

Hero Frame as style lock:

Once you have a Hero Frame you love, use it as a reference upload for your first video

shot. Describe the match in the prompt as atmosphere and lighting language — not as

camera/genre instructions (those go in the UI settings):

The same overcast midday light as the reference image.
Muted, desaturated tones. The character enters from the left side of frame.

Higgsfield Popcorn — Storyboard Integration

Popcorn is Higgsfield's storyboard tool. Use it to plan a sequence visually before

committing to Cinema Studio generation.

Popcorn → Cinema Studio workflow:

• Open Popcorn → describe your story / scene breakdown
• Popcorn generates a visual storyboard with shot descriptions
• Review shot order, camera angles, key moments
• Export storyboard → import into Cinema Studio as shot list
• Configure each shot: optical stack, Director Panel, Speed Ramp
• Generate in Multi-Shot Manual mode using the storyboard as your script

When to use Popcorn first:

• Any sequence longer than 3 shots
• When you're not sure of the shot order
• Client or collaborator needs to approve the structure before generation
• Complex action sequences with many camera angles

Keyframe Interpolation — Start/End Frames

Define exactly where a shot begins and ends. Eliminates morphing artifacts that happen

when the model guesses the transition.

Setup:

• Start Frame: Upload or generate the first frame of the shot
• End Frame: Upload or generate the last frame of the shot
• Cinema Studio interpolates the motion between them

Best uses:

• Precise character entrances / exits
• Object reveals with exact start and end position
• Match cuts between shots (end frame of shot A = start frame of shot B)
• Controlled camera moves where position must be exact

3D Mode — Gaussian Splatting

Cinema Studio can build a 3D version of any generated image using Gaussian splatting.

Once active, you can move inside the frame — shift perspective, orbit the scene, and find

a composition that didn't exist in the original 2D generation.

How it works:

• Generate an image in Cinema Studio (any model, any optical stack)
• Activate 3D Mode on the generated image
• Cinema Studio reconstructs the scene as a 3D Gaussian splat
• Use the virtual camera to move freely — orbit, push in, shift angle
• Capture your preferred composition as a new frame
• Use that frame as a start frame for video generation

When to use 3D Mode:

• You love the generation but want a different camera angle
• You need a reverse shot or over-the-shoulder from the same scene
• You're building a virtual camera move through a static scene
• You want to explore parallax and depth before committing to video

Workflow tip: Generate a Hero Frame → enter 3D Mode → find 2–3 different angles →

use each as start frames for different shots in your Multi-Shot Manual sequence. One

generation becomes multiple shots.

Grid Generation — Batch Variations

Instead of generating one image at a time, Cinema Studio can produce **2×2, 3×3, or 4×4

grids** — up to 16 variations from a single generation, charged as one credit.

Grid sizes:

| Grid | Variations | Cost |

|------|-----------|------|

| 2×2 | 4 images | 1 generation credit |

| 3×3 | 9 images | 1 generation credit |

| 4×4 | 16 images | 1 generation credit |

When to use Grid Generation:

• Exploring compositions — generate 16 options, pick the best one
• Character sheet creation — multiple poses/angles in one pass
• A/B testing visual direction before committing to video
• Cost-efficient iteration — spend 1 credit, get up to 16 options

Workflow with grids:

• Write your prompt + configure optical stack
• Select grid size (2×2 through 4×4)
• Generate — all variations appear grouped together
• Select the best variation(s)
• Use as Hero Frame, start frame, or enter 3D Mode on any individual result

Resolution Settings

Cinema Studio supports explicit resolution control for image generation:

| Setting | Resolution | Best for |

|---------|-----------|----------|

| 1K | 1024px | Fast iteration, concept exploration |

| 2K | 2048px | Standard quality, most workflows |

| 4K | 4096px | Final delivery, print, hero assets |

Rule of thumb: Start at 1K–2K for exploration and grid generation. Switch to 4K only

for your final selected composition. Higher resolution = longer generation time and more

credits.

Frame Extraction Loop — Build, Animate, Extract, Repeat

One of Cinema Studio 2.5's most powerful workflows is the frame extraction loop. You

can extract the start frame or end frame from any generated video and feed it back into

the image workflow — creating an iterative creative cycle.

The loop:

1. GENERATE IMAGE → Hero Frame or grid selection
2. ANIMATE        → Turn image into video (any model)
3. EXTRACT FRAME  → Pull the start or end frame from the video
4. FEED BACK      → Use extracted frame as a new start image
5. REPEAT         → Animate again from the new starting point

Why this matters:

• The end frame of a video often produces compositions you'd never prompt directly
• Extracted frames carry the model's physics — natural motion blur, weight, momentum
• Chaining extract → animate creates organic visual evolution
• End frame of shot A becomes start frame of shot B — seamless continuity

Best uses:

• Building long sequences that feel connected without multi-shot mode
• Discovering unexpected compositions from model-generated endpoints
• Creating transformation sequences (character aging, day-to-night, etc.)
• Match-cutting between scenes using extracted frames as anchors

Object & Person Insertion

Cinema Studio 2.5 can insert characters and objects into a scene that weren't present

in the original start frame. This was essentially impossible before — the model would

ignore new subjects or break the scene trying to add them.

How it works:

• Generate or upload your base scene (the environment)
• In the prompt, describe the character or object entering the scene
• Cinema Studio composites the new subject into the existing environment
• The insertion respects lighting, perspective, and scale of the original scene

Best for:

• Adding a character walking into an establishing shot
• Placing props or vehicles into an existing environment
• Building up scene complexity across multiple generations
• "What if" exploration — same scene with different subjects

Prompt pattern for insertion:

[Describe the existing scene briefly]. A man in a dark overcoat enters from the left
side of frame, walking toward the center. He carries a briefcase.

Tip: The more specific you are about the entry point (left, right, background,

foreground) and the action, the cleaner the insertion.

Clustering — Automatic Generation Grouping

All generations from the same prompt are automatically clustered (grouped together) in

Cinema Studio's interface. This means:

• Every variation from a grid generation stays in one visual group
• Iterative re-generations of the same prompt are easy to compare
• Long projects stay organized without manual folder management
• You can quickly scan clusters to pick the best result from each prompt

Tip: Use clustering to your advantage — generate multiple variations of each key shot,

then pick winners from each cluster before assembling the final sequence.

Cinema Studio Output Format

Core rule: Everything selectable in the Higgsfield UI stays out of the prompt.

The prompt field is for scene description only — pure visual storytelling language.

What goes where

| Belongs in UI (dropdowns) | Belongs in Prompt field |

|--------------------------|------------------------|

| Camera body | Character appearance and action |

| Lens | Environment and atmosphere |

| Focal length | What happens in the scene |

| Aperture | Lighting and mood description |

| Genre | Emotion and tone |

| Director Panel movement | Everything the eye sees |

| Speed Ramp | |

| Duration | |

IMAGE MODE Output Format (Cinema Studio 2.5 only)

━━━ UI SETTINGS (select in Higgsfield) ━━━━━━━━━━━━━━━━━━
Camera:   [body name]
Lens:     [lens name]
Focal:    [focal length]
Aperture: [aperture]
↳ Why: [one sentence — what this stack gives the image and why]

━━━ PROMPT (paste into Cinema Studio) ━━━━━━━━━━━━━━━━━━━
[Scene description only. No camera/lens/aperture language.]

Image Mode example:

━━━ UI SETTINGS (select in Higgsfield) ━━━━━━━━━━━━━━━━━━
Camera:   Grand Format 70mm Film
Lens:     Classic Anamorphic
Focal:    50mm
Aperture: f/1.4
↳ Why: 70mm grain + anamorphic flare gives instant prestige cinema quality.
       f/1.4 puts the harbour out of focus, keeping all weight on the detective.

━━━ PROMPT (paste into Cinema Studio) ━━━━━━━━━━━━━━━━━━━
A weathered detective stands at the edge of a rain-soaked harbour dock at night.
An old leather briefcase sits at his feet, open, papers scattered by the wind.
He stares at the horizon, collar turned up against the driving rain.
Harbour lights fracture on the black water below.

SINGLE SHOT Video Output Format (Cinema Studio 2.5)

━━━ UI SETTINGS (select in Higgsfield) ━━━━━━━━━━━━━━━━━━
Genre:      [genre]
Movement:   [Director Panel movement]
Speed Ramp: [mode]
Duration:   [seconds]

━━━ PROMPT (paste into Cinema Studio) ━━━━━━━━━━━━━━━━━━━
[Scene description only. No movement, genre, speed ramp, or duration language.]

Single Shot example:

━━━ UI SETTINGS (select in Higgsfield) ━━━━━━━━━━━━━━━━━━
Genre:      Suspense
Movement:   Dolly Out
Speed Ramp: Slow Mo
Duration:   8s

━━━ PROMPT (paste into Cinema Studio) ━━━━━━━━━━━━━━━━━━━
A weathered detective stands at the edge of a rain-soaked harbour dock at night.
An old leather briefcase sits at his feet, open, papers scattered by the wind.
He stares at the horizon, collar turned up against the driving rain.
Harbour lights fracture on the black water below.
He reaches down and slowly closes the briefcase.

MULTI-SHOT AUTO Video Output Format (Cinema Studio 2.5)

Same structure as Single Shot — one UI settings block, one prompt. The user describes

the full scene in the prompt and Cinema Studio breaks it into shots automatically.

━━━ UI SETTINGS (select in Higgsfield) ━━━━━━━━━━━━━━━━━━
Genre:      [genre]
Movement:   [Director Panel movement — or Auto if varied]
Speed Ramp: [mode]
Duration:   [total seconds]

━━━ PROMPT (paste into Cinema Studio) ━━━━━━━━━━━━━━━━━━━
[Full scene description. Let Cinema Studio break it into shots.
No movement, genre, speed ramp, or duration language in here.]

Multi-Shot Auto example:

━━━ UI SETTINGS (select in Higgsfield) ━━━━━━━━━━━━━━━━━━
Genre:      Suspense
Movement:   Auto
Speed Ramp: Linear
Duration:   15s

━━━ PROMPT (paste into Cinema Studio) ━━━━━━━━━━━━━━━━━━━
A weathered detective pushes open the door of a rain-soaked bar and steps inside.
He scans the room — empty except for a bartender polishing glasses at the far end.
He walks slowly to the bar and sits down. The bartender slides a drink without a word.
The detective picks it up, stares at his reflection in the mirror behind the bottles.
He sets it down without drinking.

MULTI-SHOT MANUAL Video Output Format (Cinema Studio 2.5)

One UI settings block per scene. One prompt per scene. Six scenes = six pairs.

Each scene is fully self-contained — the user configures and pastes them one at a time.

━━━ SCENE 1 — [short scene title] ━━━━━━━━━━━━━━━━━━━━━━━
UI SETTINGS
  Genre:      [genre]
  Movement:   [movement]
  Speed Ramp: [mode]
  Duration:   [seconds]

PROMPT
[Scene 1 description only.]

━━━ SCENE 2 — [short scene title] ━━━━━━━━━━━━━━━━━━━━━━━
UI SETTINGS
  Genre:      [genre]
  Movement:   [movement]
  Speed Ramp: [mode]
  Duration:   [seconds]

PROMPT
[Scene 2 description only.]

[...continue for each scene]

Multi-Shot Manual example — 3 scenes (same pattern scales to 6):

━━━ SCENE 1 — Arrival ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
UI SETTINGS
  Genre:      Suspense
  Movement:   Handheld
  Speed Ramp: Linear
  Duration:   5s

PROMPT
A weathered detective steps through the door of a dimly lit bar.
Rain drips from his coat. He pauses, eyes adjusting to the dark.
The bar is nearly empty. A jukebox plays quietly in the corner.

━━━ SCENE 2 — The Walk ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
UI SETTINGS
  Genre:      Suspense
  Movement:   Camera Follows
  Speed Ramp: Linear
  Duration:   4s

PROMPT