mcpField
V
video-prompting-guide

video-prompting-guide

github.com/magentoshCreative & media444 installsUpdated 12w ago
Repository

About video-prompting-guide

A guide to writing prompts for video generation through inference.sh, for creators who want to describe shots, subjects, motion, settings, and style more deliberately. It collects camera, lighting, and visual-style terms, alongside model-specific notes and an iterative workflow.

Key features

  1. 01Structure prompts by shot, subject, and action
  2. 02Review shot types and camera movements
  3. 03Use lighting and visual-style keywords
  4. 04Consult tips for different models
  5. 05Follow an iterative prompting workflow

Use cases

  1. 01Write prompts for product demo videos
  2. 02Plan nature documentary shot descriptions
  3. 03Improve urban or food video prompts
  4. 04Refine video generation descriptions iteratively

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/magentosh/superpowers --skill video-prompting-guide

After installing, type/video-prompting-guidein Claude Code to confirm it loaded.

Details

From the project README

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

Video Prompting Guide

Best practices for writing effective AI video generation prompts via inference.sh.

Video Prompting Guide

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Well-structured video prompt
belt app run google/veo-3-1-fast --input '{
  "prompt": "Cinematic tracking shot of a red sports car driving through Tokyo at night, neon lights reflecting on wet streets, rain falling, 4K, shallow depth of field"
}'

Prompt Structure Formula

[Shot Type] + [Subject] + [Action] + [Setting] + [Lighting] + [Style] + [Technical]
Example Breakdown
"Slow motion close-up of coffee being poured into a white ceramic cup,
steam rising, morning sunlight streaming through window, warm color grading,
cinematic, 4K, shallow depth of field"
  • Shot Type: Slow motion close-up
  • Subject: Coffee
  • Action: Being poured
  • Setting: White ceramic cup, window
  • Lighting: Morning sunlight
  • Style: Warm color grading, cinematic
  • Technical: 4K, shallow depth of field

Shot Types

Shot TypeDescriptionUse For
Wide shotShows entire sceneEstablishing location
Medium shotWaist-up framingConversations, actions
Close-upFace or detailEmotion, product detail
Extreme close-upSingle featureDrama, texture
Aerial shotBird's eye viewLandscapes, scale
Low angleCamera looking upPower, grandeur
High angleCamera looking downVulnerability
Dutch angleTilted cameraUnease, tension
POV shotFirst person viewImmersion

Camera Movements

MovementDescriptionEffect
Tracking shotCamera follows subjectDynamic, engaging
Dolly in/outCamera moves toward/awayFocus, reveal
PanHorizontal rotationSurvey scene
TiltVertical rotationReveal height
Crane shotVertical + horizontalDramatic reveal
HandheldSlight shakeRealism, urgency
SteadicamSmooth followingProfessional, cinematic
ZoomLens zoom in/outQuick focus change
StaticNo movementContemplation, stability

Lighting Keywords

KeywordEffect
Golden hourWarm, soft, romantic
Blue hourCool, moody, twilight
High keyBright, minimal shadows
Low keyDark, dramatic shadows
Rim lightingSubject outlined with light
BacklitLight from behind subject
Soft lightingGentle, flattering
Hard lightingSharp shadows, contrast
NeonColorful, urban, cyberpunk
Natural lightingRealistic, documentary

Style Keywords

Cinematic Styles
cinematic, film grain, anamorphic lens, letterbox,
shallow depth of field, bokeh, 35mm film,
color grading, theatrical
Visual Aesthetics
minimalist, maximalist, vintage, retro, futuristic,
cyberpunk, steampunk, noir, pastel, vibrant,
muted colors, high contrast, desaturated
Quality Keywords
4K, 8K, high resolution, photorealistic,
hyperrealistic, ultra detailed, professional,
broadcast quality, HDR

Prompt Examples by Use Case

Product Demo
belt app run google/veo-3-1-fast --input '{
  "prompt": "Smooth tracking shot around a sleek smartphone on a white pedestal, soft studio lighting, product photography style, reflections on surface, 4K, shallow depth of field"
}'
Nature Documentary
belt app run google/veo-3-1 --input '{
  "prompt": "Slow motion extreme close-up of a hummingbird hovering at a red flower, wings in motion blur, shallow depth of field, golden hour lighting, National Geographic style"
}'
Urban Lifestyle
belt app run google/veo-3 --input '{
  "prompt": "Tracking shot following a cyclist through busy city streets, morning rush hour, natural lighting, handheld camera feel, documentary style, authentic and candid"
}'
Food Content
belt app run bytedance/seedance-2-0 --input '{
  "prompt": "Close-up of chocolate sauce being drizzled over ice cream, slow motion, steam rising, soft lighting, food photography style, appetizing, commercial quality",
  "generate_audio": true
}'
Tech/Futuristic
belt app run xai/grok-imagine-video --input '{
  "prompt": "Futuristic control room with holographic displays, camera slowly pans across the space, blue and cyan lighting, sci-fi atmosphere, Blade Runner aesthetic, 4K",
  "duration": 5
}'

Common Mistakes to Avoid

MistakeProblemBetter Approach
Too vague"A nice video"Specify shot, subject, style
Too complexMultiple scenesOne scene per prompt
No motionStatic descriptionInclude camera movement or action
Conflicting styles"Minimalist maximalist"Choose one aesthetic
No lightingUndefined moodSpecify lighting conditions

Model-Specific Tips

Google Veo
  • Excels at realistic, cinematic content
  • Supports audio generation (Veo 3+)
  • Best with detailed, professional prompts
  • Frame interpolation available in 3.1
Seedance
  • Strong at dance and human motion
  • First-frame control available
  • Good for consistent character motion
  • Works well with reference images
Wan 2.5
  • Best for image-to-video
  • Animates still images naturally
  • Good motion prediction
  • Works with any image style
Grok
  • Good general-purpose video
  • Configurable duration (5-10s)
  • Creative interpretations
  • Works well with abstract concepts

Workflow: Iterative Prompting

# 1. Start with basic prompt
belt app run google/veo-3-1-fast --input '{
  "prompt": "A woman walking through a forest"
}'

# 2. Add specificity
belt app run google/veo-3-1-fast --input '{
  "prompt": "Medium tracking shot of a woman in a red dress walking through an autumn forest"
}'

# 3. Add style and technical details
belt app run google/veo-3-1-fast --input '{
  "prompt": "Cinematic medium tracking shot of a woman in a flowing red dress walking through an autumn forest, golden hour sunlight filtering through leaves, shallow depth of field, film grain, 4K"
}'

Related Skills

# Generate videos
npx skills add inference-sh/skills@ai-video-generation

# Google Veo specific
npx skills add inference-sh/skills@google-veo

# Generate images for image-to-video
npx skills add inference-sh/skills@ai-image-generation

# General prompt engineering
npx skills add inference-sh/skills@prompt-engineering

# Full platform skill
npx skills add inference-sh/skills@infsh-cli

Browse all video apps: belt app list --category video

Documentation

Comments

Markdown supported