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.
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 Type |
Description |
Use For |
| Wide shot |
Shows entire scene |
Establishing location |
| Medium shot |
Waist-up framing |
Conversations, actions |
| Close-up |
Face or detail |
Emotion, product detail |
| Extreme close-up |
Single feature |
Drama, texture |
| Aerial shot |
Bird's eye view |
Landscapes, scale |
| Low angle |
Camera looking up |
Power, grandeur |
| High angle |
Camera looking down |
Vulnerability |
| Dutch angle |
Tilted camera |
Unease, tension |
| POV shot |
First person view |
Immersion |
Camera Movements
| Movement |
Description |
Effect |
| Tracking shot |
Camera follows subject |
Dynamic, engaging |
| Dolly in/out |
Camera moves toward/away |
Focus, reveal |
| Pan |
Horizontal rotation |
Survey scene |
| Tilt |
Vertical rotation |
Reveal height |
| Crane shot |
Vertical + horizontal |
Dramatic reveal |
| Handheld |
Slight shake |
Realism, urgency |
| Steadicam |
Smooth following |
Professional, cinematic |
| Zoom |
Lens zoom in/out |
Quick focus change |
| Static |
No movement |
Contemplation, stability |
Lighting Keywords
| Keyword |
Effect |
| Golden hour |
Warm, soft, romantic |
| Blue hour |
Cool, moody, twilight |
| High key |
Bright, minimal shadows |
| Low key |
Dark, dramatic shadows |
| Rim lighting |
Subject outlined with light |
| Backlit |
Light from behind subject |
| Soft lighting |
Gentle, flattering |
| Hard lighting |
Sharp shadows, contrast |
| Neon |
Colorful, urban, cyberpunk |
| Natural lighting |
Realistic, 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
| Mistake |
Problem |
Better Approach |
| Too vague |
"A nice video" |
Specify shot, subject, style |
| Too complex |
Multiple scenes |
One scene per prompt |
| No motion |
Static description |
Include camera movement or action |
| Conflicting styles |
"Minimalist maximalist" |
Choose one aesthetic |
| No lighting |
Undefined mood |
Specify 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
1---
2name: video-prompting-guide
3description: "Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts"
4allowed-tools: Bash(belt *)
5metadata:
6 source: https://skillmd.com/skills/101-skills/video-prompting-guide
7---
8
9> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
10
11# Video Prompting Guide
12
13Best practices for writing effective AI video generation prompts via [inference.sh](https://inference.sh).
14
15
16
17## Quick Start
18
19> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
20
21```bash
22belt login
23
24# Well-structured video prompt
25belt app run google/veo-3-1-fast --input '{
26 "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"
27}'
28```
29
30
31## Prompt Structure Formula
32
33```
34[Shot Type] + [Subject] + [Action] + [Setting] + [Lighting] + [Style] + [Technical]
35```
36
37### Example Breakdown
38
39```
40"Slow motion close-up of coffee being poured into a white ceramic cup,
41steam rising, morning sunlight streaming through window, warm color grading,
42cinematic, 4K, shallow depth of field"
43```
44
45- **Shot Type**: Slow motion close-up
46- **Subject**: Coffee
47- **Action**: Being poured
48- **Setting**: White ceramic cup, window
49- **Lighting**: Morning sunlight
50- **Style**: Warm color grading, cinematic
51- **Technical**: 4K, shallow depth of field
52
53## Shot Types
54
55| Shot Type | Description | Use For |
56|-----------|-------------|---------|
57| Wide shot | Shows entire scene | Establishing location |
58| Medium shot | Waist-up framing | Conversations, actions |
59| Close-up | Face or detail | Emotion, product detail |
60| Extreme close-up | Single feature | Drama, texture |
61| Aerial shot | Bird's eye view | Landscapes, scale |
62| Low angle | Camera looking up | Power, grandeur |
63| High angle | Camera looking down | Vulnerability |
64| Dutch angle | Tilted camera | Unease, tension |
65| POV shot | First person view | Immersion |
66
67## Camera Movements
68
69| Movement | Description | Effect |
70|----------|-------------|--------|
71| Tracking shot | Camera follows subject | Dynamic, engaging |
72| Dolly in/out | Camera moves toward/away | Focus, reveal |
73| Pan | Horizontal rotation | Survey scene |
74| Tilt | Vertical rotation | Reveal height |
75| Crane shot | Vertical + horizontal | Dramatic reveal |
76| Handheld | Slight shake | Realism, urgency |
77| Steadicam | Smooth following | Professional, cinematic |
78| Zoom | Lens zoom in/out | Quick focus change |
79| Static | No movement | Contemplation, stability |
80
81## Lighting Keywords
82
83| Keyword | Effect |
84|---------|--------|
85| Golden hour | Warm, soft, romantic |
86| Blue hour | Cool, moody, twilight |
87| High key | Bright, minimal shadows |
88| Low key | Dark, dramatic shadows |
89| Rim lighting | Subject outlined with light |
90| Backlit | Light from behind subject |
91| Soft lighting | Gentle, flattering |
92| Hard lighting | Sharp shadows, contrast |
93| Neon | Colorful, urban, cyberpunk |
94| Natural lighting | Realistic, documentary |
95
96## Style Keywords
97
98### Cinematic Styles
99
100```
101cinematic, film grain, anamorphic lens, letterbox,
102shallow depth of field, bokeh, 35mm film,
103color grading, theatrical
104```
105
106### Visual Aesthetics
107
108```
109minimalist, maximalist, vintage, retro, futuristic,
110cyberpunk, steampunk, noir, pastel, vibrant,
111muted colors, high contrast, desaturated
112```
113
114### Quality Keywords
115
116```
1174K, 8K, high resolution, photorealistic,
118hyperrealistic, ultra detailed, professional,
119broadcast quality, HDR
120```
121
122## Prompt Examples by Use Case
123
124### Product Demo
125
126```bash
127belt app run google/veo-3-1-fast --input '{
128 "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"
129}'
130```
131
132### Nature Documentary
133
134```bash
135belt app run google/veo-3-1 --input '{
136 "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"
137}'
138```
139
140### Urban Lifestyle
141
142```bash
143belt app run google/veo-3 --input '{
144 "prompt": "Tracking shot following a cyclist through busy city streets, morning rush hour, natural lighting, handheld camera feel, documentary style, authentic and candid"
145}'
146```
147
148### Food Content
149
150```bash
151belt app run bytedance/seedance-2-0 --input '{
152 "prompt": "Close-up of chocolate sauce being drizzled over ice cream, slow motion, steam rising, soft lighting, food photography style, appetizing, commercial quality",
153 "generate_audio": true
154}'
155```
156
157### Tech/Futuristic
158
159```bash
160belt app run xai/grok-imagine-video --input '{
161 "prompt": "Futuristic control room with holographic displays, camera slowly pans across the space, blue and cyan lighting, sci-fi atmosphere, Blade Runner aesthetic, 4K",
162 "duration": 5
163}'
164```
165
166## Common Mistakes to Avoid
167
168| Mistake | Problem | Better Approach |
169|---------|---------|-----------------|
170| Too vague | "A nice video" | Specify shot, subject, style |
171| Too complex | Multiple scenes | One scene per prompt |
172| No motion | Static description | Include camera movement or action |
173| Conflicting styles | "Minimalist maximalist" | Choose one aesthetic |
174| No lighting | Undefined mood | Specify lighting conditions |
175
176## Model-Specific Tips
177
178### Google Veo
179
180- Excels at realistic, cinematic content
181- Supports audio generation (Veo 3+)
182- Best with detailed, professional prompts
183- Frame interpolation available in 3.1
184
185### Seedance
186
187- Strong at dance and human motion
188- First-frame control available
189- Good for consistent character motion
190- Works well with reference images
191
192### Wan 2.5
193
194- Best for image-to-video
195- Animates still images naturally
196- Good motion prediction
197- Works with any image style
198
199### Grok
200
201- Good general-purpose video
202- Configurable duration (5-10s)
203- Creative interpretations
204- Works well with abstract concepts
205
206## Workflow: Iterative Prompting
207
208```bash
209# 1. Start with basic prompt
210belt app run google/veo-3-1-fast --input '{
211 "prompt": "A woman walking through a forest"
212}'
213
214# 2. Add specificity
215belt app run google/veo-3-1-fast --input '{
216 "prompt": "Medium tracking shot of a woman in a red dress walking through an autumn forest"
217}'
218
219# 3. Add style and technical details
220belt app run google/veo-3-1-fast --input '{
221 "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"
222}'
223```
224
225## Related Skills
226
227```bash
228# Generate videos
229npx skills add inference-sh/skills@ai-video-generation
230
231# Google Veo specific
232npx skills add inference-sh/skills@google-veo
233
234# Generate images for image-to-video
235npx skills add inference-sh/skills@ai-image-generation
236
237# General prompt engineering
238npx skills add inference-sh/skills@prompt-engineering
239
240# Full platform skill
241npx skills add inference-sh/skills@infsh-cli
242```
243
244Browse all video apps: `belt app list --category video`
245
246## Documentation
247
248- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
249- [Video Generation Guide](https://inference.sh/blog/guides/video-generation) - Comprehensive video guide
250