storyboard-creation

작성자: halt-catch-fire

영상 및 비디오 스토리보드 제작: 샷 용어, 연속성 규칙, 패널 레이아웃 포함. 샷 유형, 카메라 각도, 움직임, 180도 규칙, 주석 형식 다룸. 사용처: 비디오 기획, 영화 사전 제작, 광고 스토리보드, 뮤직비디오 기획, 애니메이션. 트리거: storyboard, storyboarding, shot list, film planning, video planning, pre production, shot composition, camera angles, scene planning, visual script, animatic, storyboard panels, video storyboard

npx skills add https://github.com/halt-catch-fire/skills --skill storyboard-creation

Install the belt CLI skill: npx skills add belt-sh/cli

Storyboard Creation

Create visual storyboards with AI image generation via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Generate a storyboard panel
belt app run falai/flux-dev-lora --input '{
  "prompt": "storyboard panel, wide establishing shot of a modern city skyline at sunset, cinematic composition, slightly desaturated colors, film still style, 16:9 aspect ratio",
  "width": 1248,
  "height": 832
}'

# Stitch panels into a board
belt app run infsh/stitch-images --input '{
  "images": ["panel1.png", "panel2.png", "panel3.png"],
  "direction": "horizontal"
}'

Shot Types

AbbreviationNameFramingWhen to Use
ECUExtreme Close-UpEyes only, a detailIntense emotion, revealing detail
CUClose-UpFace fills frameEmotion, reaction, dialogue
MCUMedium Close-UpHead and shouldersInterviews, conversations
MSMedium ShotWaist upGeneral dialogue, action
MLSMedium Long ShotKnees upWalking, casual interaction
LSLong ShotFull bodyCharacter in environment
WSWide ShotEnvironment dominantEstablishing location, scale
EWSExtreme Wide ShotVast landscapeEpic scope, isolation, transitions

Generating Each Shot Type

# Close-Up — emotion focus
belt app run falai/flux-dev-lora --input '{
  "prompt": "close-up shot of a woman face showing concern, soft dramatic lighting from the left, shallow depth of field, cinematic film still, slightly desaturated",
  "width": 1248,
  "height": 832
}'

# Medium Shot — dialogue scene
belt app run falai/flux-dev-lora --input '{
  "prompt": "medium shot of two people talking across a table in a cafe, warm afternoon light through windows, natural composition, cinematic film still, 35mm lens look",
  "width": 1248,
  "height": 832
}'

# Wide Shot — establishing
belt app run falai/flux-dev-lora --input '{
  "prompt": "wide establishing shot of a futuristic laboratory interior, dramatic overhead lighting, long corridor with glass walls, sci-fi atmosphere, cinematic composition, anamorphic lens style",
  "width": 1248,
  "height": 832
}'

Camera Angles

AngleEffectWhen to Use
Eye LevelNeutral, naturalDefault for most scenes
High AngleSubject looks small, vulnerableShowing weakness, overview
Low AngleSubject looks powerful, dominantAuthority, heroism, threat
Bird's EyeGod-like overviewMaps, establishing geography
Worm's EyeExtreme power, aweArchitecture, towering figures
Dutch AngleUnease, disorientationTension, madness, action
Over-the-Shoulder (OTS)Viewer positioned with characterConversations, POV

Camera Movement

MovementDescriptionEmotion
PanCamera rotates horizontally (on tripod)Scanning, following, revealing
TiltCamera rotates vertically (on tripod)Revealing height, power
DollyCamera moves toward/away from subjectIntimacy (in), distance (out)
TruckCamera moves laterallyFollowing alongside, revealing
Crane/JibCamera moves up or down verticallyGrand reveals, transitions
ZoomLens focal length changes (camera stays)Focus shift, dramatic emphasis
Steadicam/GimbalSmooth handheld trackingImmersion, following action
HandheldDeliberate camera shakeUrgency, documentary feel, chaos
StaticCamera doesn't moveStability, observation, tension

In storyboards, indicate movement with arrows drawn on panels.

Continuity Rules

The 180-Degree Rule

Imagine a line (axis) between two characters in conversation. The camera must stay on ONE side of that line.

         Character A        Character B
              ●─────────────────●
             /                   \
           /     CAMERA ZONE      \
         /     (stay on this side)  \
       📷          📷          📷
     Camera 1   Camera 2   Camera 3

Crossing the line confuses the viewer about spatial relationships. Only cross intentionally (with a neutral shot in between or a visible camera move).

Match on Action

When cutting between two angles of the same action, the action must continue seamlessly:

Panel A: Hand reaches for door handle (medium shot)
Panel B: Hand grabs door handle (close-up)
         ↑ Action continues from same point

Eyeline Match

When a character looks at something, the next shot should show what they're looking at, from their approximate point of view.

Panel A: Character looks up and to the right
Panel B: The object they see, framed from slightly below-left

Screen Direction

If a character moves left-to-right in one shot, they should continue left-to-right in the next. Reversing direction implies they turned around.

Panel Layout

Standard Formats

LayoutPanelsUse For
2x3 (6 panels)6 per pageDetailed scenes, dialogue
3x3 (9 panels)9 per pageAction sequences, montages
2x2 (4 panels)4 per pageKey moments, presentations
Single1 per pageHero shots, critical moments

Panel Annotation Format

Each panel should include:

┌────────────────────────────────────┐
│ SCENE 3 — SHOT 2                   │ ← Scene and shot number
│                                    │
│   [Generated image here]           │ ← Visual
│                                    │
├────────────────────────────────────┤
│ Shot: MS, eye level                │ ← Shot type and angle
│ Movement: Slow dolly in            │ ← Camera movement
│ Duration: 4 sec                    │ ← Estimated duration
│ Action: Sarah opens the letter     │ ← What happens
│ Dialogue: "This changes everything"│ ← Any spoken lines
│ SFX: Paper rustling, clock ticking │ ← Sound effects
│ Music: Tension builds              │ ← Music cue
└────────────────────────────────────┘

Storyboard Workflow

Step 1: Shot List

Before generating images, write a shot list:

SCENE 1 — OFFICE, DAY

1.1  WS  - Establishing shot of office building exterior, morning
1.2  MS  - Sarah walks through office, carrying coffee
1.3  CU  - Sarah's face, notices something on her desk
1.4  ECU - An envelope on the desk, unfamiliar handwriting
1.5  MS  - Sarah picks up envelope, opens it
1.6  CU  - Sarah's eyes widen as she reads
1.7  ECU - Key phrase on the letter (insert text)

Step 2: Generate Panels

Use consistent style across all panels:

# Establish a consistent style prompt suffix
STYLE="cinematic film still, slightly desaturated, warm color grade, 35mm lens, shallow depth of field"

# Panel 1.1 — Wide establishing
belt app run falai/flux-dev-lora --input "{
  \"prompt\": \"wide shot of a modern glass office building exterior, morning golden hour light, people entering, $STYLE\",
  \"width\": 1248, \"height\": 832
}" --no-wait

# Panel 1.2 — Medium shot
belt app run falai/flux-dev-lora --input "{
  \"prompt\": \"medium shot of a professional woman walking through a modern open office, carrying coffee cup, morning light through windows, $STYLE\",
  \"width\": 1248, \"height\": 832
}" --no-wait

# Panel 1.3 — Close-up
belt app run falai/flux-dev-lora --input "{
  \"prompt\": \"close-up of a woman face looking down at her desk with curious expression, soft office lighting, $STYLE\",
  \"width\": 1248, \"height\": 832
}" --no-wait

Step 3: Assemble Board

# Stitch panels into rows
belt app run infsh/stitch-images --input '{
  "images": ["panel_1_1.png", "panel_1_2.png", "panel_1_3.png"],
  "direction": "horizontal"
}'

belt app run infsh/stitch-images --input '{
  "images": ["panel_1_4.png", "panel_1_5.png", "panel_1_6.png"],
  "direction": "horizontal"
}'

# Then stitch rows vertically for full page
belt app run infsh/stitch-images --input '{
  "images": ["row1.png", "row2.png"],
  "direction": "vertical"
}'

Style Consistency Tips

  • Use the same style suffix across all panels (lens, color grade, lighting)
  • Use FLUX LoRA if you need consistent characters across panels
  • Keep the same aspect ratio for all panels
  • Generate more panels than you need and select the best
  • If a panel doesn't match the style, regenerate with adjusted prompt

Common Mistakes

MistakeProblemFix
Crossing the 180-degree lineConfuses spatial relationshipsStay on one side or use neutral shot
All same shot typeVisually boring, no rhythmVary between CU, MS, WS
No establishing shotViewer doesn't know where they areStart scenes with WS or EWS
Too many shots per scenePacing drags5-8 shots per scene is typical
Inconsistent style between panelsLooks like different projectsUse same style prompt suffix
Missing annotationsPanels are ambiguousAlways note shot type, movement, action

Related Skills

npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@video-prompting-guide
npx skills add inference-sh/skills@prompt-engineering

Browse all apps: belt app list

halt-catch-fire의 다른 스킬

ai-image-generation
halt-catch-fire
We need to translate the given text from English to Korean. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. So names like GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve, inference.sh CLI, etc. should remain as is. Also numbers like 50+, 4.5. The text inside <text> is a description of an agent skill for AI image generation. We need to translate the rest naturally into Korean. Let's break it down: "Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI." -> "inference.sh CLI를 통해 GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve 및 50개 이상의 모델로 AI 이미지를 생성합니다." "Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4
creativemediaimage
ai-video-generation
halt-catch-fire
inference.sh CLI를 통해 Google Veo, Seedance 2.0, HappyHorse, Wan, Grok 및 40개 이상의 모델로 AI 비디오를 생성합니다. 모델: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. 기능: 텍스트-비디오, 이미지-비디오, 참조-비디오, 비디오 편집, 립싱크, 아바타 애니메이션, 비디오 업스케일링, 폴리 사운드. 사용처: 소셜 미디어 비디오, 마케팅 콘텐츠, 설명 비디오, 제품 데모, AI 아바타. 트리거: 비디오 생성, AI 비디오,...
creativevideomedia
twitter-automation
halt-catch-fire
We need to translate the given text from English to Korean. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "twitter-automation" is not in the text, so we don't include it. We only translate the text inside <text>. No extra labels or commentary. The text describes an agent skill for automating Twitter/X. It mentions CLI, apps like x/post-tweet, etc., capabilities, use cases, and triggers. We need to translate naturally while keeping technical terms like "inference.sh CLI", "x/post-tweet", etc. as is. Also "Twitter/X" should be preserved as is or translated? The instruction says preserve product names, so "Twitter" and "X" are product names. But "Twitter/X" might be a combined reference. I'll keep "Twitter/X" as is. Similarly "X API" should be preserved. "inference.sh CLI" is a technical term, keep as is. The list of apps: x/post-tweet, x/post-create (with media),
marketingapicommunication
ai-avatar-video
halt-catch-fire
inference.sh CLI를 통해 AI 아바타 및 토킹 헤드 영상을 생성합니다. 권장: P-Video-Avatar (가장 빠르고 저렴하며 TTS 내장). 추가: OmniHuman, Fabric, PixVerse. 오디오: Inworld TTS-2 (100개 이상 언어, 캐릭터 감정 조절), ElevenLabs, Kokoro. 기능: 오디오 기반 아바타, 텍스트-투-아바타, 립싱크 영상, 토킹 헤드 생성, 가상 프레젠터, UGC 콘텐츠. 용도: AI 프레젠터, 설명 영상, 가상 인플루언서, 더빙, 마케팅 영상, UGC 광고, 게이밍 아바타,...
videocreativemedia
agent-browser
halt-catch-fire
inference.sh를 통한 AI 에이전트용 브라우저 자동화. @e 참조를 사용하여 웹 페이지 탐색, 요소와 상호작용, 스크린샷 촬영, 비디오 녹화. 기능: 웹 스크래핑, 양식 작성, 클릭, 타이핑, 드래그 앤 드롭, 파일 업로드, JavaScript 실행. 용도: 웹 자동화, 데이터 추출, 테스트, 에이전트 브라우징, 연구. 트리거: 브라우저, 웹 자동화, 스크래핑, 탐색, 클릭, 양식 작성, 스크린샷, 웹 브라우징, Playwright, 헤드리스 브라우저, 웹 에이전트, 인터넷 서핑, 비디오 녹화
browser-automationweb-scrapingtesting
web-search
halt-catch-fire
Tavily와 Exa를 통해 inference.sh CLI로 웹 검색 및 콘텐츠 추출. 앱: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. 기능: AI 기반 검색, 콘텐츠 추출, 직접 답변, 리서치. 용도: 리서치, RAG 파이프라인, 사실 확인, 콘텐츠 수집, 에이전트. 트리거: 웹 검색, tavily, exa, search api, 콘텐츠 추출, 리서치, 인터넷 검색, ai 검색, 검색 어시스턴트, 웹 스크래핑, rag, perplexity 대안
researchweb-scrapingapi
infsh-cli
halt-catch-fire
inference.sh CLI를 통해 250개 이상의 AI 앱 실행 - 이미지 생성, 비디오 제작, LLM, 검색, 3D, Twitter 자동화. 모델: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter 등 다수. AI 앱 실행, 이미지/비디오 생성, LLM 호출, 웹 검색 또는 Twitter 자동화 시 사용. 트리거: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
developmentapicreative
landing-page-design
halt-catch-fire
랜딩 페이지 전환 최적화: 레이아웃 규칙, 히어로 섹션 디자인, CTA 심리학 포함. 어바우드 더 폴드 공식, 소셜 프루프 배치, 모바일 디자인, F-패턴 리딩을 다룹니다. 사용처: 스타트업 랜딩 페이지, 제품 페이지, SaaS 마케팅, 전환 최적화. 트리거: 랜딩 페이지, 히어로 섹션, 어바우드 더 폴드, 전환 최적화, 랜딩 페이지 디자인, CTA 버튼, 히어로 이미지, 랜딩 페이지 레이아웃, SaaS 랜딩 페이지, 제품 페이지 디자인, 전환율, 랜딩 페이지...