Install the belt CLI skill: npx skills add belt-sh/cli
Image to Video
Convert still images to animated videos via inference.sh CLI.
Quick Start
Requires inference.sh CLI (belt). Install instructions
belt login
# Generate a still image
belt app run falai/flux-dev-lora --input '{
"prompt": "serene mountain lake at sunset, snow-capped peaks reflected in still water, golden hour light, landscape photography",
"width": 1248,
"height": 832
}'
# Animate it
belt app run falai/wan-2-5-i2v --input '{
"prompt": "gentle ripples on the lake surface, clouds slowly drifting, warm light shifting, birds flying in the distance",
"image": "path/to/lake-image.png"
}'
Model Selection
| Model |
App ID |
Best For |
Motion Style |
| Wan 2.5 i2v |
falai/wan-2-5-i2v |
Realistic motion, natural movement |
Photorealistic, subtle |
| WAN-I2V (Pruna) |
pruna/wan-i2v |
Economical, fast, 480p/720p |
Natural, efficient |
| Seedance 2.0 |
bytedance/seedance-2-0 |
Up to 1080p, sync audio, all input types |
Versatile, high quality |
| Seedance 2.0 Fast |
bytedance/seedance-2-0-fast |
Fast variant, same capabilities |
Versatile, fast |
| Fabric 1.0 |
falai/fabric-1-0 |
Cloth, fabric, liquid, flowing materials |
Physics-based flow |
| Grok Imagine Video |
xai/grok-imagine-video |
General animation, text-guided |
Versatile |
When to Use Each
| Scenario |
Best Model |
Why |
| Landscape with water/clouds |
Wan 2.5 i2v |
Best at natural, realistic motion |
| Portrait with subtle expression |
Wan 2.5 i2v |
Maintains face fidelity |
| Product with fabric/cloth |
Fabric 1.0 |
Specialized in material physics |
| Flag waving, curtain flowing |
Fabric 1.0 |
Cloth simulation |
| Illustrated/artistic image |
Seedance 2.0 |
Matches stylized content |
| General "bring to life" |
Seedance 2.0 |
Good all-rounder, up to 1080p |
| Quick test/iteration |
Seedance 2.0 Fast |
Faster generation |
Motion Types
Camera Movement
| Movement |
Prompt Keyword |
Effect |
| Push in / Dolly forward |
"slow dolly forward", "camera pushes in" |
Increasing intimacy/focus |
| Pull out / Dolly back |
"camera pulls back", "slow zoom out" |
Reveal, context |
| Pan left/right |
"camera pans slowly to the right" |
Scanning, following |
| Tilt up/down |
"camera tilts upward" |
Revealing height |
| Orbit |
"camera orbits around the subject" |
3D exploration |
| Crane up |
"camera rises upward" |
Grand reveal |
| Static |
(no camera movement prompt) |
Subject motion only |
Subject Motion
| Type |
Prompt Examples |
| Natural elements |
"water rippling", "clouds drifting", "leaves rustling in breeze" |
| Hair/clothing |
"hair blowing gently in wind", "dress fabric flowing" |
| Atmospheric |
"fog slowly rolling", "dust particles floating in light beams" |
| Character |
"person slowly turns to camera", "subtle breathing motion" |
| Mechanical |
"gears turning", "clock hands moving" |
| Liquid |
"coffee steam rising", "paint dripping", "water pouring" |
Prompting Best Practices
The Golden Rule: Subtle > Dramatic
AI video models produce better results with gentle, subtle motion than dramatic action. Requesting too much movement causes distortion and artifacts.
❌ "person running and jumping over obstacles while the camera spins"
✅ "person slowly walking forward, gentle breeze, camera follows alongside"
❌ "explosion with debris flying everywhere"
✅ "candle flame flickering gently, warm ambient light shifting"
❌ "fast zoom into the eyes with dramatic camera shake"
✅ "slow dolly forward toward the subject, subtle focus shift"
Prompt Structure
[Camera movement] + [Subject motion] + [Atmospheric effects] + [Mood/pace]
Examples by Scenario
# Landscape animation
belt app run falai/wan-2-5-i2v --input '{
"prompt": "gentle camera pan right, water reflecting moving clouds, trees swaying slightly in breeze, warm golden light, peaceful and slow",
"image": "landscape.png"
}'
# Portrait animation
belt app run falai/wan-2-5-i2v --input '{
"prompt": "subtle breathing motion, slight head turn, natural eye blink, hair moving gently, soft ambient lighting shifts",
"image": "portrait.png"
}'
# Product shot animation
belt app run bytedance/seedance-2-0 --input '{
"prompt": "slow 360 degree orbit around the product, gentle spotlight movement, subtle reflections shifting, premium product showcase, smooth motion",
"image": "product.png",
"generate_audio": true
}'
# Fabric/cloth animation
belt app run falai/fabric-1-0 --input '{
"prompt": "fabric flowing and rippling in gentle wind, natural cloth physics, soft movement",
"image": "fabric-scene.png"
}'
# Architectural visualization
belt app run falai/wan-2-5-i2v --input '{
"prompt": "slow dolly forward through the entrance, slight camera tilt upward, ambient light filtering through windows, dust particles in light beams",
"image": "building-interior.png"
}'
Duration Guidelines
| Duration |
Quality |
Use For |
| 2-3 seconds |
Highest quality |
GIFs, looping backgrounds, cinemagraphs |
| 4-5 seconds |
High quality |
Social media posts, product reveals |
| 6-8 seconds |
Good quality |
Short clips, transitions |
| 10+ seconds |
Quality degrades |
Avoid unless stitching shorter clips |
Extending Duration
For longer videos, generate multiple short clips and stitch:
# Generate 3 clips from the same image with progressive motion
belt app run falai/wan-2-5-i2v --input '{
"prompt": "slow pan left, gentle water motion",
"image": "scene.png"
}' --no-wait
belt app run falai/wan-2-5-i2v --input '{
"prompt": "continuing pan, clouds shifting, light changing",
"image": "scene.png"
}' --no-wait
# Stitch together
belt app run infsh/media-merger --input '{
"media": ["clip1.mp4", "clip2.mp4"]
}'
The Full Workflow
Still-to-Final-Video Pipeline
# 1. Generate source image (best quality)
belt app run bytedance/seedream-4-5 --input '{
"prompt": "cinematic landscape, misty mountains at dawn, lake in foreground, dramatic clouds, golden hour, 4K quality, professional photography",
"size": "2K"
}'
# 2. Animate the image
belt app run falai/wan-2-5-i2v --input '{
"prompt": "gentle mist rolling through the valley, lake surface rippling, clouds slowly moving, birds in distance, warm light shifting",
"image": "landscape.png"
}'
# 3. Upscale video if needed
belt app run falai/topaz-video-upscaler --input '{
"video": "animated-landscape.mp4"
}'
# 4. Add ambient audio
belt app run infsh/hunyuanvideo-foley --input '{
"video": "animated-landscape.mp4",
"prompt": "gentle nature ambience, distant birds, soft wind, water lapping"
}'
# 5. Merge video with audio
belt app run infsh/video-audio-merger --input '{
"video": "upscaled-landscape.mp4",
"audio": "ambient-audio.mp3"
}'
Cinemagraph Effect
A cinemagraph is a still photo where only one element moves (e.g., waterfall moving in an otherwise frozen scene). To achieve this:
- Generate the still image with the motion element clearly defined
- Prompt for motion only in that specific element
- Keep to 2-4 seconds for seamless looping
belt app run falai/wan-2-5-i2v --input '{
"prompt": "only the waterfall is moving, everything else remains perfectly still, water cascading smoothly, rest of scene frozen",
"image": "waterfall-scene.png"
}'
Common Mistakes
| Mistake |
Problem |
Fix |
| Too much motion requested |
Distortion, artifacts, warping |
Subtle > dramatic, always |
| Wrong model for content type |
Poor results |
Use selection guide above |
| Clips too long (10s+) |
Quality degrades significantly |
Keep to 3-5 seconds, stitch if needed |
| No camera movement specified |
Random/unpredictable motion |
Always specify camera behavior |
| Conflicting motion directions |
Chaotic, unnatural |
One primary motion direction |
| Low-res source image |
Low-res video output |
Start with highest quality source |
| Complex action scenes |
Models can't handle |
Keep motion simple and natural |
Related Skills
npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@p-video
npx skills add inference-sh/skills@video-prompting-guide
npx skills add inference-sh/skills@prompt-engineering
Browse all apps: belt app list
1---
2name: image-to-video
3description: "Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image"
4allowed-tools: Bash(belt *)
5metadata:
6 source: https://skillmd.com/skills/101-skills/image-to-video
7---
8
9> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
10
11# Image to Video
12
13Convert still images to animated videos via [inference.sh](https://inference.sh) CLI.
14
15## Quick Start
16
17> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
18
19```bash
20belt login
21
22# Generate a still image
23belt app run falai/flux-dev-lora --input '{
24 "prompt": "serene mountain lake at sunset, snow-capped peaks reflected in still water, golden hour light, landscape photography",
25 "width": 1248,
26 "height": 832
27}'
28
29# Animate it
30belt app run falai/wan-2-5-i2v --input '{
31 "prompt": "gentle ripples on the lake surface, clouds slowly drifting, warm light shifting, birds flying in the distance",
32 "image": "path/to/lake-image.png"
33}'
34```
35
36
37## Model Selection
38
39| Model | App ID | Best For | Motion Style |
40|-------|--------|----------|-------------|
41| **Wan 2.5 i2v** | `falai/wan-2-5-i2v` | Realistic motion, natural movement | Photorealistic, subtle |
42| **WAN-I2V (Pruna)** | `pruna/wan-i2v` | Economical, fast, 480p/720p | Natural, efficient |
43| **Seedance 2.0** | `bytedance/seedance-2-0` | Up to 1080p, sync audio, all input types | Versatile, high quality |
44| **Seedance 2.0 Fast** | `bytedance/seedance-2-0-fast` | Fast variant, same capabilities | Versatile, fast |
45| **Fabric 1.0** | `falai/fabric-1-0` | Cloth, fabric, liquid, flowing materials | Physics-based flow |
46| **Grok Imagine Video** | `xai/grok-imagine-video` | General animation, text-guided | Versatile |
47
48### When to Use Each
49
50| Scenario | Best Model | Why |
51|----------|-----------|-----|
52| Landscape with water/clouds | **Wan 2.5 i2v** | Best at natural, realistic motion |
53| Portrait with subtle expression | **Wan 2.5 i2v** | Maintains face fidelity |
54| Product with fabric/cloth | **Fabric 1.0** | Specialized in material physics |
55| Flag waving, curtain flowing | **Fabric 1.0** | Cloth simulation |
56| Illustrated/artistic image | **Seedance 2.0** | Matches stylized content |
57| General "bring to life" | **Seedance 2.0** | Good all-rounder, up to 1080p |
58| Quick test/iteration | **Seedance 2.0 Fast** | Faster generation |
59
60## Motion Types
61
62### Camera Movement
63
64| Movement | Prompt Keyword | Effect |
65|----------|---------------|--------|
66| Push in / Dolly forward | "slow dolly forward", "camera pushes in" | Increasing intimacy/focus |
67| Pull out / Dolly back | "camera pulls back", "slow zoom out" | Reveal, context |
68| Pan left/right | "camera pans slowly to the right" | Scanning, following |
69| Tilt up/down | "camera tilts upward" | Revealing height |
70| Orbit | "camera orbits around the subject" | 3D exploration |
71| Crane up | "camera rises upward" | Grand reveal |
72| Static | (no camera movement prompt) | Subject motion only |
73
74### Subject Motion
75
76| Type | Prompt Examples |
77|------|----------------|
78| Natural elements | "water rippling", "clouds drifting", "leaves rustling in breeze" |
79| Hair/clothing | "hair blowing gently in wind", "dress fabric flowing" |
80| Atmospheric | "fog slowly rolling", "dust particles floating in light beams" |
81| Character | "person slowly turns to camera", "subtle breathing motion" |
82| Mechanical | "gears turning", "clock hands moving" |
83| Liquid | "coffee steam rising", "paint dripping", "water pouring" |
84
85## Prompting Best Practices
86
87### The Golden Rule: Subtle > Dramatic
88
89AI video models produce better results with **gentle, subtle motion** than dramatic action. Requesting too much movement causes distortion and artifacts.
90
91```
92❌ "person running and jumping over obstacles while the camera spins"
93✅ "person slowly walking forward, gentle breeze, camera follows alongside"
94
95❌ "explosion with debris flying everywhere"
96✅ "candle flame flickering gently, warm ambient light shifting"
97
98❌ "fast zoom into the eyes with dramatic camera shake"
99✅ "slow dolly forward toward the subject, subtle focus shift"
100```
101
102### Prompt Structure
103
104```
105[Camera movement] + [Subject motion] + [Atmospheric effects] + [Mood/pace]
106```
107
108### Examples by Scenario
109
110```bash
111# Landscape animation
112belt app run falai/wan-2-5-i2v --input '{
113 "prompt": "gentle camera pan right, water reflecting moving clouds, trees swaying slightly in breeze, warm golden light, peaceful and slow",
114 "image": "landscape.png"
115}'
116
117# Portrait animation
118belt app run falai/wan-2-5-i2v --input '{
119 "prompt": "subtle breathing motion, slight head turn, natural eye blink, hair moving gently, soft ambient lighting shifts",
120 "image": "portrait.png"
121}'
122
123# Product shot animation
124belt app run bytedance/seedance-2-0 --input '{
125 "prompt": "slow 360 degree orbit around the product, gentle spotlight movement, subtle reflections shifting, premium product showcase, smooth motion",
126 "image": "product.png",
127 "generate_audio": true
128}'
129
130# Fabric/cloth animation
131belt app run falai/fabric-1-0 --input '{
132 "prompt": "fabric flowing and rippling in gentle wind, natural cloth physics, soft movement",
133 "image": "fabric-scene.png"
134}'
135
136# Architectural visualization
137belt app run falai/wan-2-5-i2v --input '{
138 "prompt": "slow dolly forward through the entrance, slight camera tilt upward, ambient light filtering through windows, dust particles in light beams",
139 "image": "building-interior.png"
140}'
141```
142
143## Duration Guidelines
144
145| Duration | Quality | Use For |
146|----------|---------|---------|
147| 2-3 seconds | Highest quality | GIFs, looping backgrounds, cinemagraphs |
148| 4-5 seconds | High quality | Social media posts, product reveals |
149| 6-8 seconds | Good quality | Short clips, transitions |
150| 10+ seconds | Quality degrades | Avoid unless stitching shorter clips |
151
152### Extending Duration
153
154For longer videos, generate multiple short clips and stitch:
155
156```bash
157# Generate 3 clips from the same image with progressive motion
158belt app run falai/wan-2-5-i2v --input '{
159 "prompt": "slow pan left, gentle water motion",
160 "image": "scene.png"
161}' --no-wait
162
163belt app run falai/wan-2-5-i2v --input '{
164 "prompt": "continuing pan, clouds shifting, light changing",
165 "image": "scene.png"
166}' --no-wait
167
168# Stitch together
169belt app run infsh/media-merger --input '{
170 "media": ["clip1.mp4", "clip2.mp4"]
171}'
172```
173
174## The Full Workflow
175
176### Still-to-Final-Video Pipeline
177
178```bash
179# 1. Generate source image (best quality)
180belt app run bytedance/seedream-4-5 --input '{
181 "prompt": "cinematic landscape, misty mountains at dawn, lake in foreground, dramatic clouds, golden hour, 4K quality, professional photography",
182 "size": "2K"
183}'
184
185# 2. Animate the image
186belt app run falai/wan-2-5-i2v --input '{
187 "prompt": "gentle mist rolling through the valley, lake surface rippling, clouds slowly moving, birds in distance, warm light shifting",
188 "image": "landscape.png"
189}'
190
191# 3. Upscale video if needed
192belt app run falai/topaz-video-upscaler --input '{
193 "video": "animated-landscape.mp4"
194}'
195
196# 4. Add ambient audio
197belt app run infsh/hunyuanvideo-foley --input '{
198 "video": "animated-landscape.mp4",
199 "prompt": "gentle nature ambience, distant birds, soft wind, water lapping"
200}'
201
202# 5. Merge video with audio
203belt app run infsh/video-audio-merger --input '{
204 "video": "upscaled-landscape.mp4",
205 "audio": "ambient-audio.mp3"
206}'
207```
208
209## Cinemagraph Effect
210
211A cinemagraph is a still photo where only one element moves (e.g., waterfall moving in an otherwise frozen scene). To achieve this:
212
2131. Generate the still image with the motion element clearly defined
2142. Prompt for motion only in that specific element
2153. Keep to 2-4 seconds for seamless looping
216
217```bash
218belt app run falai/wan-2-5-i2v --input '{
219 "prompt": "only the waterfall is moving, everything else remains perfectly still, water cascading smoothly, rest of scene frozen",
220 "image": "waterfall-scene.png"
221}'
222```
223
224## Common Mistakes
225
226| Mistake | Problem | Fix |
227|---------|---------|-----|
228| Too much motion requested | Distortion, artifacts, warping | Subtle > dramatic, always |
229| Wrong model for content type | Poor results | Use selection guide above |
230| Clips too long (10s+) | Quality degrades significantly | Keep to 3-5 seconds, stitch if needed |
231| No camera movement specified | Random/unpredictable motion | Always specify camera behavior |
232| Conflicting motion directions | Chaotic, unnatural | One primary motion direction |
233| Low-res source image | Low-res video output | Start with highest quality source |
234| Complex action scenes | Models can't handle | Keep motion simple and natural |
235
236## Related Skills
237
238```bash
239npx skills add inference-sh/skills@ai-video-generation
240npx skills add inference-sh/skills@ai-image-generation
241npx skills add inference-sh/skills@p-video
242npx skills add inference-sh/skills@video-prompting-guide
243npx skills add inference-sh/skills@prompt-engineering
244```
245
246Browse all apps: `belt app list`
247