AI Video Director
Write shot-by-shot video prompt sequences for AI video generation tools. Supports multi-shot sequences (up to 6 shots), dialogue with voice control, and character consistency across scenes.
When to Use
- Writing multi-shot video sequences with scene transitions
- Creating AI-generated animated series with consistent characters
- Adding dialogue with emotion/tone control to video prompts
- Routing between video tools (Kling 3.0, Sora, Grok) based on content needs
Tool Routing
| Tool |
Best For |
Key Capability |
| Kling 3.0 |
Multi-shot sequences with dialogue |
Up to 6 native shots, audio control, subject anchoring |
| Sora |
Scene generation, character consistency |
Best for narrative scenes, handles [cut] transitions |
| Grok |
Restricted/romantic content |
Fewer content restrictions than Sora |
| Midjourney |
Character source images |
Style/Omni reference for initial character design |
Workflow
- Define characters -- Lock identity traits early (appearance, clothing, key features)
- Write shot sequence -- Describe each shot with cinematic language (profile, macro, tracking, POV)
- Add audio -- Structure dialogue as
[Character: Label, tone]: "text"
- Route to tool -- Select based on content requirements and shot count
- Generate insert shots -- Create reusable clips for character consistency
Core Principles (Kling 3.0)
- Think in Shots, Not Clips -- Use cinematic language (profile shots, macro close-ups, tracking, shot-reverse-shot)
- Anchor Subjects Early -- Define core subjects clearly at the beginning for consistency
- Describe Motion Explicitly -- Specify camera behavior (tracking, following, freezing, panning) AND subject movement
- Native Audio -- Use
[Character A: Label, tone]: "Dialogue" format with linking words for rhythm
- Image-to-Video: Lock First -- Treat input image as anchor, focus on how scene evolves FROM the image
Audio Prompting Rules
| Principle |
Guideline |
Example |
| Structured Naming |
Unique, consistent labels |
[Character A: Black-suited Agent] |
| Visual Anchoring |
Action first, then dialogue |
The agent slams the table. [Agent, angrily]: "Where?" |
| Audio Details |
Tone and emotion labels |
[Agent, raspy, deep voice]: "Don't move." |
| Temporal Control |
Linking words for rhythm |
[Agent]: "Why?" Immediately, [Assistant]: "Because." |
Character Consistency Workflow (Framer X)
For animated series with consistent characters across multiple scenes:
- Step 1: Generate character source images (Midjourney Style/Omni reference)
- Step 2: Create establishing scenes (Sora) with
[cut] transitions
- Step 3: Generate interaction scenes (Sora) in different environments
- Step 4: Create insert shots for reusable character clips
- Step 5: Route restricted content to Grok with custom source images
See references/prompt-templates.md for complete examples.
1---2name: ai-video-director3description: Create AI-generated video content using Kling 3.0 (multi-shot sequences with dialogue), Sora (scene generation with character consistency), or Grok (restricted content). Use when writing shot-by-shot video prompts, building character-consistent animated series, or routing between video generation tools.4---56# AI Video Director78Write shot-by-shot video prompt sequences for AI video generation tools. Supports multi-shot sequences (up to 6 shots), dialogue with voice control, and character consistency across scenes.910## When to Use1112- Writing multi-shot video sequences with scene transitions13- Creating AI-generated animated series with consistent characters14- Adding dialogue with emotion/tone control to video prompts15- Routing between video tools (Kling 3.0, Sora, Grok) based on content needs1617## Tool Routing1819| Tool | Best For | Key Capability |20|------|----------|----------------|21| **Kling 3.0** | Multi-shot sequences with dialogue | Up to 6 native shots, audio control, subject anchoring |22| **Sora** | Scene generation, character consistency | Best for narrative scenes, handles [cut] transitions |23| **Grok** | Restricted/romantic content | Fewer content restrictions than Sora |24| **Midjourney** | Character source images | Style/Omni reference for initial character design |2526## Workflow27281. **Define characters** -- Lock identity traits early (appearance, clothing, key features)292. **Write shot sequence** -- Describe each shot with cinematic language (profile, macro, tracking, POV)303. **Add audio** -- Structure dialogue as `[Character: Label, tone]: "text"`314. **Route to tool** -- Select based on content requirements and shot count325. **Generate insert shots** -- Create reusable clips for character consistency3334## Core Principles (Kling 3.0)35361. **Think in Shots, Not Clips** -- Use cinematic language (profile shots, macro close-ups, tracking, shot-reverse-shot)372. **Anchor Subjects Early** -- Define core subjects clearly at the beginning for consistency383. **Describe Motion Explicitly** -- Specify camera behavior (tracking, following, freezing, panning) AND subject movement394. **Native Audio** -- Use `[Character A: Label, tone]: "Dialogue"` format with linking words for rhythm405. **Image-to-Video: Lock First** -- Treat input image as anchor, focus on how scene evolves FROM the image4142## Audio Prompting Rules4344| Principle | Guideline | Example |45|-----------|-----------|---------|46| Structured Naming | Unique, consistent labels | `[Character A: Black-suited Agent]` |47| Visual Anchoring | Action first, then dialogue | `The agent slams the table. [Agent, angrily]: "Where?"` |48| Audio Details | Tone and emotion labels | `[Agent, raspy, deep voice]: "Don't move."` |49| Temporal Control | Linking words for rhythm | `[Agent]: "Why?" Immediately, [Assistant]: "Because."` |5051## Character Consistency Workflow (Framer X)5253For animated series with consistent characters across multiple scenes:54551. **Step 1:** Generate character source images (Midjourney Style/Omni reference)562. **Step 2:** Create establishing scenes (Sora) with `[cut]` transitions573. **Step 3:** Generate interaction scenes (Sora) in different environments584. **Step 4:** Create insert shots for reusable character clips595. **Step 5:** Route restricted content to Grok with custom source images6061See `references/prompt-templates.md` for complete examples.
Sheshiyer