Back to Blog Catalog/Flagship Reference Handbook
2026 Complete Reference Guide • 25 Chapters • 100-Page Translation

The AI Video Prompt Engineering Master Handbook

A platform-neutral production guide for Text-to-Video and Image-to-Video. Stop AI glitches, master camera kinematics, control hand anatomy, and direct cinema-grade multi-clip sequences in Botock, Sora, Kling, and Runway Gen-3.

Official Botock Research Publication25 Complete Chapters9 Core Architectural Blocks25 Ready-to-Use Templates35 Min Read
High-end cinema camera with prompt engineering data matrices and optical tracking grids
Production Blueprint: Full-spectrum cinematography optics, depth tracking, and prompt parameter injectionFormat: 2.39:1 Anamorphic • Latent Physics Engine
9

The 9 Core Blocks of an AI Video Prompt

Every high-fidelity prompt in modern generative models (Botock, Kling 1.5, Sora, Luma Dream Machine, Runway Gen-3) is constructed from nine distinct semantic building blocks. Leaving any block undefined forces the model to hallucinate random values.

BLOCK 01

Shot Size & Framing

Wide shot, full shot, medium close-up, macro.

BLOCK 02

Subject Identity & Anchor

Exact age, gender, clothing texture, hair color.

BLOCK 03

Starting Coordinate Pose

Seated at frame-left, facing frame-right.

BLOCK 04

The Single Action Beat

Only ONE atomic physical change during clip.

BLOCK 05

Movement Vector & Speed

Direction, displacement, velocity (e.g. slow, 1 m/s).

BLOCK 06

Camera Kinematics & Lens

Tripod static, dolly in, tracking shot, 50mm lens.

BLOCK 07

Lighting & Environment

Golden hour rim light, volumetric fog, rainy reflections.

BLOCK 08

Audio / Dialogue / Silence

Exact line in quotes, room tone, "No music".

BLOCK 09

Exclusion Constraints

No camera motion, no talking, no smiling.

The Subject Map: Audience Perspective vs. Character Perspective

The #1 reason AI models place characters or actions on the wrong side is ambiguous directional language. Use the standard spatial conventions below:

Directive TermPrecise Spatial MeaningHandbook Writing Rule
frame-left / frame-rightLeft and right as the AUDIENCE views the display screen.Always use "frame-left" to anchor positions on screen.
character's right handThe character's biological anatomical hand. (Appears on frame-left if facing camera).Write "the character's right hand" for body mechanics.
moves toward frame-rightLinear motion vector across the screen.Never say "moves right". Always qualify with "frame-right".
Person A, Person BNeutral semantic identifiers to prevent role blending.Give each character a distinct identifier and unique wardrobe color.

Motion Intensity Calibration Table

AI video generators tend to over-animate emotions and gestures. To control subtle acting, calibrate with exact intensity vocabulary:

Intensity KeywordTarget Motion ScopeCinematic Effect
ImperceptibleA tiny shift restricted only to the iris and pupil.Subconscious tension, suppressed panic, deep concentration.
SubtleQuiet, realistic human acting; slight corner-of-mouth lift.Photorealistic natural drama; avoids cartoonish grins.
ModerateClear to any viewer; deliberate nodding or head turn.Standard conversational action and reaction shots.
RestrainedHigh emotional intensity held under strict muscular control.Grief, jaw clenching, anger held back.

Dialogue, Voice & Sound Design Syntax

Modern video generation platforms integrate audio generation directly. Without strict sound constraints, models generate generic synth music and unintelligible gibberish chatter:

Dialogue Constraints
  • • One speaker only: Never request two people talking in a 5-second clip.
  • • Exact quoted lines: Place spoken dialogue in exact quotes: "We have to leave now."
  • • Vocal delivery: Specify pitch, speed, and timbre: whispered in a low husky voice.
Sound Exclusion Directives
  • • No music: Always state AUDIO: No music. Ambient room tone only. to stop cheap synth loops.
  • • No dialogue: Prevents silent characters from moving their lips like fish.
  • • Foley precision: Name exact physical impacts: heavy leather boots crunching on wet gravel.

Production Template Library (T1 - T25)

25 Templates

Plug-and-play prompt structures taken straight from Chapter 23 of the handbook. Replace the bracketed variables with your narrative details:

T2. Basic Image-to-Video Motion AnchorImage-to-Video
BASE IMAGE: [Describe starting image].
CAMERA: Locked-off tripod, zero movement, zero tilt, zero pan.
ACTION: [Character] shifts eyes from [Position A] to [Position B] over 3 seconds and stops. Nothing else changes.
NEGATIVE: No mouth movement. No blinking. No body posture shift.
T4. Solo Speaking Close-Up ShotDialogue
CAMERA: Close-up on Person A. 50mm lens, eye-level, static tripod.
ACTION: Person A looks toward frame-left (never looking into lens) and delivers one line: "[Exact spoken sentence]".
EXPRESSION: Subtle, restrained determination. Lips finish speaking at 4 seconds and remain closed.
AUDIO: Natural human voice, crisp room ambience. No soundtrack, no background music.
T13. Hand Action Insert (Anti-Glitch)Macro Insert
CAMERA: Extreme close-up on the wooden tabletop. Macro 85mm lens, shallow depth of field.
ACTION: Person A's right hand enters from frame-right, index finger and thumb grip the brass fountain pen, and lift it 3 cm vertically.
ANATOMY: Exactly 5 fingers visible. Clean knuckles, firm grip around the pen shaft.
NEGATIVE: No morphing fingers, no floating pen, no camera motion.
T14. Cinematic Walking Tracking ShotTracking
CAMERA: Steadicam leading shot, retreating backwards at steady walking speed 2 meters ahead of the character.
ACTION: Person A walks forward in a straight line through the wet street. Boots plant firmly on asphalt with physical weight transfer.
ENVIRONMENT: Steady light rain, asphalt reflecting street lamps, volumetric haze.
NEGATIVE: No moonwalking, no sliding feet, no camera wobble.

Complete 25-Chapter Handbook Index

Browse all 25 chapters from the official handbook. Click on chapters linked to our specialized cluster deep-dive guides:

1
How Video Models Read Your Prompt
Foundations
In Master Guide
2
Describing the Picture (Image Analysis)
Image-to-Video
In Master Guide
3
The Subject Map & Left/Right Rules
Spatial Logic
In Master Guide
4
Giving Motion to a Picture
Kinematics
In Master Guide
5
Shot Sizes
Framing
Deep Dive
6
Camera Angles
Perspective
Deep Dive
7
Camera Movements (22 Core Moves)
Motion
Deep Dive
8
Lens, Focus & Depth of Field
Optics
Deep Dive
9
Lighting, Colour & Visual Style
Atmosphere
Deep Dive
10
Head, Eyes & Neck Actions
Facial
Deep Dive
11
Hand & Arm Actions (Which Finger)
Anatomy
Deep Dive
12
Torso, Legs & Whole-Body Actions
Physics
Deep Dive
13
Facial Expression & Micro-Emotions
Acting
In Master Guide
14
Dialogue, Voice & Lip-Sync
Audio
In Master Guide
15
Sound Design & Ambience
Audio
In Master Guide
16
One-Person, Two-Person & Group Scenes
Choreography
In Master Guide
17
Props & Object Interaction
Objects
In Master Guide
18
Environment, Weather & Background
Atmosphere
Deep Dive
19
Action, Fights, Magic & Creatures
Stunts
Deep Dive
20
Continuity & Multi-Clip Workflow
Editing
In Master Guide
21
Genre Recipes (Ads, Shorts, Cinema)
Use Cases
In Master Guide
22
Troubleshooting Guide (25 Common Flaws)
Debugging
In Master Guide
23
Template Library (T1 - T25)
Formulas
In Master Guide
24
Worked Examples (Image to Final Prompt)
Case Studies
In Master Guide
25
Glossary, Checklists & Golden Rules
Reference
In Master Guide

The Ten Golden Rules of AI Video Prompting

1. One Clip, One Action BeatNever ask for two major changes in 5 seconds. Split multi-action sequences into separate clips.
2. Anchor Hands to Rigid PhysicsNever let hands hover in empty air. Anchor fingers to cups, handles, coats, or steering wheels.
3. Respect Audience Frame OrientationAlways specify "frame-left" and "frame-right" instead of vague "left/right".
4. Eyes Lead the HeadIn realistic human acting, the pupils shift first; the head turns second. Prompt them sequentially.
5. Enforce Camera AnchorsIf the camera shouldn't move, explicitly state: "Tripod locked-off, zero tilt, zero pan."
6. State What Does NOT ChangeTell the model what must stay static: "Background remains still. Wardrobe remains unchanged."
7. Kill Default AI MusicAlways specify "AUDIO: No music" to prevent loud generic synth audio generation.
8. Prevent The 4th-Wall GlitchExplicitly instruct: "Subject looks at Person B; never looks into the camera lens."
9. Use Real Film Optic MillimetersReplace "blurry background" with "85mm lens at f/1.8 with shallow depth of field and circular bokeh".
10. Stitch Using Last FramesFor perfect multi-clip video continuity, feed the exact last frame of Clip 1 as the starting seed for Clip 2.