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 store
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 *)
5---
6
7> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
8
9# Image to Video
10
11Convert still images to animated videos via [inference.sh](https://inference.sh) CLI.
12
13## Quick Start
14
15> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)
16
17```bash
18belt login
19
20# Generate a still image
21belt app run falai/flux-dev-lora --input '{
22 "prompt": "serene mountain lake at sunset, snow-capped peaks reflected in still water, golden hour light, landscape photography",
23 "width": 1248,
24 "height": 832
25}'
26
27# Animate it
28belt app run falai/wan-2-5-i2v --input '{
29 "prompt": "gentle ripples on the lake surface, clouds slowly drifting, warm light shifting, birds flying in the distance",
30 "image": "path/to/lake-image.png"
31}'
32```
33
34
35## Model Selection
36
37| Model | App ID | Best For | Motion Style |
38|-------|--------|----------|-------------|
39| **Wan 2.5 i2v** | `falai/wan-2-5-i2v` | Realistic motion, natural movement | Photorealistic, subtle |
40| **WAN-I2V (Pruna)** | `pruna/wan-i2v` | Economical, fast, 480p/720p | Natural, efficient |
41| **Seedance 2.0** | `bytedance/seedance-2-0` | Up to 1080p, sync audio, all input types | Versatile, high quality |
42| **Seedance 2.0 Fast** | `bytedance/seedance-2-0-fast` | Fast variant, same capabilities | Versatile, fast |
43| **Fabric 1.0** | `falai/fabric-1-0` | Cloth, fabric, liquid, flowing materials | Physics-based flow |
44| **Grok Imagine Video** | `xai/grok-imagine-video` | General animation, text-guided | Versatile |
45
46### When to Use Each
47
48| Scenario | Best Model | Why |
49|----------|-----------|-----|
50| Landscape with water/clouds | **Wan 2.5 i2v** | Best at natural, realistic motion |
51| Portrait with subtle expression | **Wan 2.5 i2v** | Maintains face fidelity |
52| Product with fabric/cloth | **Fabric 1.0** | Specialized in material physics |
53| Flag waving, curtain flowing | **Fabric 1.0** | Cloth simulation |
54| Illustrated/artistic image | **Seedance 2.0** | Matches stylized content |
55| General "bring to life" | **Seedance 2.0** | Good all-rounder, up to 1080p |
56| Quick test/iteration | **Seedance 2.0 Fast** | Faster generation |
57
58## Motion Types
59
60### Camera Movement
61
62| Movement | Prompt Keyword | Effect |
63|----------|---------------|--------|
64| Push in / Dolly forward | "slow dolly forward", "camera pushes in" | Increasing intimacy/focus |
65| Pull out / Dolly back | "camera pulls back", "slow zoom out" | Reveal, context |
66| Pan left/right | "camera pans slowly to the right" | Scanning, following |
67| Tilt up/down | "camera tilts upward" | Revealing height |
68| Orbit | "camera orbits around the subject" | 3D exploration |
69| Crane up | "camera rises upward" | Grand reveal |
70| Static | (no camera movement prompt) | Subject motion only |
71
72### Subject Motion
73
74| Type | Prompt Examples |
75|------|----------------|
76| Natural elements | "water rippling", "clouds drifting", "leaves rustling in breeze" |
77| Hair/clothing | "hair blowing gently in wind", "dress fabric flowing" |
78| Atmospheric | "fog slowly rolling", "dust particles floating in light beams" |
79| Character | "person slowly turns to camera", "subtle breathing motion" |
80| Mechanical | "gears turning", "clock hands moving" |
81| Liquid | "coffee steam rising", "paint dripping", "water pouring" |
82
83## Prompting Best Practices
84
85### The Golden Rule: Subtle > Dramatic
86
87AI video models produce better results with **gentle, subtle motion** than dramatic action. Requesting too much movement causes distortion and artifacts.
88
89```
90❌ "person running and jumping over obstacles while the camera spins"
91✅ "person slowly walking forward, gentle breeze, camera follows alongside"
92
93❌ "explosion with debris flying everywhere"
94✅ "candle flame flickering gently, warm ambient light shifting"
95
96❌ "fast zoom into the eyes with dramatic camera shake"
97✅ "slow dolly forward toward the subject, subtle focus shift"
98```
99
100### Prompt Structure
101
102```
103[Camera movement] + [Subject motion] + [Atmospheric effects] + [Mood/pace]
104```
105
106### Examples by Scenario
107
108```bash
109# Landscape animation
110belt app run falai/wan-2-5-i2v --input '{
111 "prompt": "gentle camera pan right, water reflecting moving clouds, trees swaying slightly in breeze, warm golden light, peaceful and slow",
112 "image": "landscape.png"
113}'
114
115# Portrait animation
116belt app run falai/wan-2-5-i2v --input '{
117 "prompt": "subtle breathing motion, slight head turn, natural eye blink, hair moving gently, soft ambient lighting shifts",
118 "image": "portrait.png"
119}'
120
121# Product shot animation
122belt app run bytedance/seedance-2-0 --input '{
123 "prompt": "slow 360 degree orbit around the product, gentle spotlight movement, subtle reflections shifting, premium product showcase, smooth motion",
124 "image": "product.png",
125 "generate_audio": true
126}'
127
128# Fabric/cloth animation
129belt app run falai/fabric-1-0 --input '{
130 "prompt": "fabric flowing and rippling in gentle wind, natural cloth physics, soft movement",
131 "image": "fabric-scene.png"
132}'
133
134# Architectural visualization
135belt app run falai/wan-2-5-i2v --input '{
136 "prompt": "slow dolly forward through the entrance, slight camera tilt upward, ambient light filtering through windows, dust particles in light beams",
137 "image": "building-interior.png"
138}'
139```
140
141## Duration Guidelines
142
143| Duration | Quality | Use For |
144|----------|---------|---------|
145| 2-3 seconds | Highest quality | GIFs, looping backgrounds, cinemagraphs |
146| 4-5 seconds | High quality | Social media posts, product reveals |
147| 6-8 seconds | Good quality | Short clips, transitions |
148| 10+ seconds | Quality degrades | Avoid unless stitching shorter clips |
149
150### Extending Duration
151
152For longer videos, generate multiple short clips and stitch:
153
154```bash
155# Generate 3 clips from the same image with progressive motion
156belt app run falai/wan-2-5-i2v --input '{
157 "prompt": "slow pan left, gentle water motion",
158 "image": "scene.png"
159}' --no-wait
160
161belt app run falai/wan-2-5-i2v --input '{
162 "prompt": "continuing pan, clouds shifting, light changing",
163 "image": "scene.png"
164}' --no-wait
165
166# Stitch together
167belt app run infsh/media-merger --input '{
168 "media": ["clip1.mp4", "clip2.mp4"]
169}'
170```
171
172## The Full Workflow
173
174### Still-to-Final-Video Pipeline
175
176```bash
177# 1. Generate source image (best quality)
178belt app run bytedance/seedream-4-5 --input '{
179 "prompt": "cinematic landscape, misty mountains at dawn, lake in foreground, dramatic clouds, golden hour, 4K quality, professional photography",
180 "size": "2K"
181}'
182
183# 2. Animate the image
184belt app run falai/wan-2-5-i2v --input '{
185 "prompt": "gentle mist rolling through the valley, lake surface rippling, clouds slowly moving, birds in distance, warm light shifting",
186 "image": "landscape.png"
187}'
188
189# 3. Upscale video if needed
190belt app run falai/topaz-video-upscaler --input '{
191 "video": "animated-landscape.mp4"
192}'
193
194# 4. Add ambient audio
195belt app run infsh/hunyuanvideo-foley --input '{
196 "video": "animated-landscape.mp4",
197 "prompt": "gentle nature ambience, distant birds, soft wind, water lapping"
198}'
199
200# 5. Merge video with audio
201belt app run infsh/video-audio-merger --input '{
202 "video": "upscaled-landscape.mp4",
203 "audio": "ambient-audio.mp3"
204}'
205```
206
207## Cinemagraph Effect
208
209A cinemagraph is a still photo where only one element moves (e.g., waterfall moving in an otherwise frozen scene). To achieve this:
210
2111. Generate the still image with the motion element clearly defined
2122. Prompt for motion only in that specific element
2133. Keep to 2-4 seconds for seamless looping
214
215```bash
216belt app run falai/wan-2-5-i2v --input '{
217 "prompt": "only the waterfall is moving, everything else remains perfectly still, water cascading smoothly, rest of scene frozen",
218 "image": "waterfall-scene.png"
219}'
220```
221
222## Common Mistakes
223
224| Mistake | Problem | Fix |
225|---------|---------|-----|
226| Too much motion requested | Distortion, artifacts, warping | Subtle > dramatic, always |
227| Wrong model for content type | Poor results | Use selection guide above |
228| Clips too long (10s+) | Quality degrades significantly | Keep to 3-5 seconds, stitch if needed |
229| No camera movement specified | Random/unpredictable motion | Always specify camera behavior |
230| Conflicting motion directions | Chaotic, unnatural | One primary motion direction |
231| Low-res source image | Low-res video output | Start with highest quality source |
232| Complex action scenes | Models can't handle | Keep motion simple and natural |
233
234## Related Skills
235
236```bash
237npx skills add inference-sh/skills@ai-video-generation
238npx skills add inference-sh/skills@ai-image-generation
239npx skills add inference-sh/skills@p-video
240npx skills add inference-sh/skills@video-prompting-guide
241npx skills add inference-sh/skills@prompt-engineering
242```
243
244Browse all apps: `belt app store`
245