storyboard-creation

作者: qu-skills

影視分鏡,包含鏡頭詞彙、連貫性規則與版面配置。涵蓋鏡頭類型、攝影角度、運鏡、180度法則及註記格式。適用於:影片規劃、電影前期製作、廣告分鏡、音樂影片規劃、動畫。觸發詞: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/qu-skills/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 store

來自 qu-skills 的更多技能

ai-video-generation
qu-skills
透過 inference.sh CLI 使用 Google Veo、Seedance 2.0、HappyHorse、Wan、Grok 及 40 多種模型生成 AI 影片。模型:Veo 3.1、Veo 3、Seedance 2.0、HappyHorse 1.0、Wan 2.5、Grok Imagine Video、OmniHuman、Fabric、HunyuanVideo。功能:文字轉影片、圖片轉影片、參考轉影片、影片編輯、唇形同步、虛擬人物動畫、影片放大、擬音音效。用途:社群媒體影片、行銷內容、解說影片、產品展示、AI 虛擬人物。觸發條件:影片生成、AI 影片、...
videocreativemedia
remotion-render
qu-skills
透過 inference.sh 從 React/Remotion 元件程式碼渲染影片。傳入 TSX 程式碼,取得 MP4。支援所有 Remotion API:useCurrentFrame、useVideoConfig、spring、interpolate、AbsoluteFill、Sequence。可設定解析度、FPS、時長、編碼器。用途:程式化影片生成、動畫圖形、動態設計、資料驅動影片、React 動畫轉影片。觸發詞:remotion、從程式碼渲染影片、tsx 轉影片、react 影片、程式化影片、remotion 渲染、程式碼轉影片、動畫...
developmentvideocreative
ai-image-generation
qu-skills
透過 inference.sh CLI 使用 GPT-Image-2、FLUX、Gemini、Grok、Seedream、Reve 及 50 多種模型生成 AI 圖像。模型包括:GPT-Image-2、FLUX Dev LoRA、FLUX.2 Klein LoRA、Gemini 3 Pro Image、Grok Imagine、Seedream 4.5、Reve、ImagineArt。功能涵蓋:文字轉圖像、圖像轉圖像、修補、LoRA、圖像編輯、放大、文字渲染。適用於:AI 藝術、產品模型、概念藝術、社交媒體圖形、行銷視覺、插圖。觸發詞:flux、圖像生成、AI 圖像、文字轉...
creativemediaimage
ai-avatar-video
qu-skills
透過 inference.sh CLI 建立 AI 虛擬人偶與說話頭影片。推薦:P-Video-Avatar(最快、最便宜、內建 TTS)。另可選:OmniHuman、Fabric、PixVerse。音訊:Inworld TTS-2(100 多種語言、角色情感引導)、ElevenLabs、Kokoro。功能:音訊驅動虛擬人偶、文字轉虛擬人偶、唇形同步影片、說話頭生成、虛擬主持人、UGC 內容。用途:AI 主持人、解說影片、虛擬網紅、配音、行銷影片、UGC 廣告、遊戲虛擬人偶……
videocreativemedia
twitter-automation
qu-skills
透過 inference.sh CLI 自動化 Twitter/X 的發文、互動與用戶管理。應用程式:x/post-tweet、x/post-create(含媒體)、x/post-like、x/post-retweet、x/dm-send、x/user-follow。功能:發推文、排程內容、按讚、轉推、發送私訊、追蹤用戶、取得個人資料。用途:社群媒體自動化、內容排程、互動機器人、受眾成長、X API。觸發條件:twitter api、x api、推文自動化、發文至 twitter、twitter 機器人、社群媒體自動化、x...
api
agent-browser
qu-skills
透過 inference.sh 為 AI 代理提供瀏覽器自動化功能。可導覽網頁、使用 @e 參考與元素互動、擷取螢幕截圖、錄製影片。功能包括:網頁抓取、表單填寫、點擊、打字、拖放、檔案上傳、執行 JavaScript。適用於:網頁自動化、資料擷取、測試、代理瀏覽、研究。觸發詞:瀏覽器、網頁自動化、抓取、導覽、點擊、填寫表單、螢幕截圖、瀏覽網頁、playwright、無頭瀏覽器、網頁代理、上網、錄製影片
browser-automationweb-scrapingtesting
web-search
qu-skills
透過 inference.sh CLI 使用 Tavily 和 Exa 進行網路搜尋與內容擷取。應用:Tavily 搜尋、Tavily 擷取、Exa 搜尋、Exa 回答、Exa 擷取。功能:AI 驅動搜尋、內容擷取、直接回答、研究。用途:研究、RAG 管線、事實查核、內容彙整、代理程式。觸發詞:網路搜尋、tavily、exa、搜尋 API、內容擷取、研究、網際網路搜尋、AI 搜尋、搜尋助理、網頁抓取、rag、perplexity 替代方案
researchweb-scrapingapi
agent-tools
qu-skills
透過 inference.sh CLI 執行 250 多個 AI 應用程式 - 圖片生成、影片創作、大型語言模型、搜尋、3D、Twitter 自動化。模型:FLUX、Veo、Gemini、Grok、Claude、Seedance、OmniHuman、Tavily、Exa、OpenRouter 等。用於執行 AI 應用程式、生成圖片/影片、呼叫大型語言模型、網路搜尋或自動化 Twitter 時觸發。觸發詞: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