image-to-video

We need to translate the given text from English to French. The text is a description of an agent skill for image-to-video conversion. The name "image-to-video" is to be preserved, but it does not appear in the source text. The source text contains "Still-to-video conversion guide" and various terms like "Wan 2.5 i2v", "Seedance", "Fabric", "Grok Video" which are product names/protocol names/technical terms and should be preserved. Also URLs, numbers, etc. We must not add any extra commentary or labels. Just translate the text inside <text> tags. The text: "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

npx skills add https://github.com/halt-catch-fire/skills --skill image-to-video

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

ModelApp IDBest ForMotion Style
Wan 2.5 i2vfalai/wan-2-5-i2vRealistic motion, natural movementPhotorealistic, subtle
WAN-I2V (Pruna)pruna/wan-i2vEconomical, fast, 480p/720pNatural, efficient
Seedance 2.0bytedance/seedance-2-0Up to 1080p, sync audio, all input typesVersatile, high quality
Seedance 2.0 Fastbytedance/seedance-2-0-fastFast variant, same capabilitiesVersatile, fast
Fabric 1.0falai/fabric-1-0Cloth, fabric, liquid, flowing materialsPhysics-based flow
Grok Imagine Videoxai/grok-imagine-videoGeneral animation, text-guidedVersatile

When to Use Each

ScenarioBest ModelWhy
Landscape with water/cloudsWan 2.5 i2vBest at natural, realistic motion
Portrait with subtle expressionWan 2.5 i2vMaintains face fidelity
Product with fabric/clothFabric 1.0Specialized in material physics
Flag waving, curtain flowingFabric 1.0Cloth simulation
Illustrated/artistic imageSeedance 2.0Matches stylized content
General "bring to life"Seedance 2.0Good all-rounder, up to 1080p
Quick test/iterationSeedance 2.0 FastFaster generation

Motion Types

Camera Movement

MovementPrompt KeywordEffect
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

TypePrompt 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

DurationQualityUse For
2-3 secondsHighest qualityGIFs, looping backgrounds, cinemagraphs
4-5 secondsHigh qualitySocial media posts, product reveals
6-8 secondsGood qualityShort clips, transitions
10+ secondsQuality degradesAvoid 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:

  1. Generate the still image with the motion element clearly defined
  2. Prompt for motion only in that specific element
  3. 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

MistakeProblemFix
Too much motion requestedDistortion, artifacts, warpingSubtle > dramatic, always
Wrong model for content typePoor resultsUse selection guide above
Clips too long (10s+)Quality degrades significantlyKeep to 3-5 seconds, stitch if needed
No camera movement specifiedRandom/unpredictable motionAlways specify camera behavior
Conflicting motion directionsChaotic, unnaturalOne primary motion direction
Low-res source imageLow-res video outputStart with highest quality source
Complex action scenesModels can't handleKeep 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

Plus de skills de halt-catch-fire

ai-image-generation
halt-catch-fire
Générez des images IA avec GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve et plus de 50 modèles via l'interface CLI inference.sh. Modèles : GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capacités : texte vers image, image vers image, inpainting, LoRA, édition d'image, upscaling, rendu de texte. Utilisation pour : art IA, maquettes de produits, concept art, graphiques pour réseaux sociaux, visuels marketing, illustrations. Déclencheurs : flux, génération d'image, image IA, texte vers...
creativemediaimage
ai-video-generation
halt-catch-fire
We need to translate the given text from English to French. The text describes an AI video generation skill. We must preserve the name "ai-video-generation" but it's not in the text, so we ignore. Preserve product names, protocol names, URLs, numbers, technical terms. So "Google Veo", "Seedance 2.0", "HappyHorse", "Wan", "Grok", "inference.sh CLI", "Veo 3.1", "Veo 3", "Seedance 2.0", "HappyHorse 1.0", "Wan 2.5", "Grok Imagine Video", "OmniHuman", "Fabric", "HunyuanVideo", "text-to-video", "image-to-video", "reference-to-video", "video editing", "lipsync", "avatar animation", "video upscaling", "foley sound", "social media videos", "marketing content", "explainer videos", "product demos", "AI avatars",
creativevideomedia
twitter-automation
halt-catch-fire
Automatisez Twitter/X avec publication, engagement et gestion des utilisateurs via l'interface CLI inference.sh. Applications : x/post-tweet, x/post-create (avec média), x/post-like, x/post-retweet, x/dm-send, x/user-follow. Capacités : publier des tweets, planifier du contenu, aimer des publications, retweeter, envoyer des messages directs, suivre des utilisateurs, obtenir des profils. Utilisation pour : automatisation des réseaux sociaux, planification de contenu, bots d'engagement, croissance d'audience, API X. Déclencheurs : twitter api, x api, tweet automation, post to twitter, twitter bot, social media automation, x...
marketingapicommunication
ai-avatar-video
halt-catch-fire
We need to translate the given text from English to French, preserving the name "ai-avatar-video" and other technical terms. The text describes creating AI avatar and talking head videos via inference.sh CLI. It recommends P-Video-Avatar, and lists other options: OmniHuman, Fabric, PixVerse. Audio options: Inworld TTS-2, ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars,... We must not include the name "ai-avatar-video" unless it appears in the source text. It does not appear in the source text, so we omit it. We translate the rest naturally. Keep product names, protocol names, URLs, numbers, technical terms as is. So "inference.sh CLI" stays, "P-Video-Avatar", "OmniHuman", "F
videocreativemedia
agent-browser
halt-catch-fire
Automatisation de navigateur pour agents IA via inference.sh. Naviguer sur des pages web, interagir avec des éléments en utilisant les références @e, prendre des captures d'écran, enregistrer des vidéos. Capacités : scraping web, remplissage de formulaires, clics, saisie, glisser-déposer, téléchargement de fichiers, exécution JavaScript. Utilisation pour : automatisation web, extraction de données, tests, navigation agent, recherche. Déclencheurs : navigateur, automatisation web, scraping, navigation, clic, remplissage de formulaire, capture d'écran, navigation web, playwright, navigateur headless, agent web, surf internet, enregistrement vidéo
browser-automationweb-scrapingtesting
web-search
halt-catch-fire
Recherche web et extraction de contenu avec Tavily et Exa via l'interface en ligne de commande inference.sh. Applications : Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capacités : recherche assistée par IA, extraction de contenu, réponses directes, recherche documentaire. Utilisation pour : recherche, pipelines RAG, vérification des faits, agrégation de contenu, agents. Déclencheurs : recherche web, tavily, exa, api de recherche, extraction de contenu, recherche, recherche internet, recherche IA, assistant de recherche, scraping web, rag, alternative à perplexity
researchweb-scrapingapi
infsh-cli
halt-catch-fire
We need to translate the given text from English to French, preserving the name "infsh-cli" and other technical terms, product names, protocol names, URLs, numbers, etc. The instruction says: "Do not include the name unless it appears in the source text." The name "infsh-cli" is not in the source text, so we don't include it. The source text has "inference.sh CLI" - that should be preserved as is? The instruction says preserve product names, so "inference.sh CLI" should stay. Also "FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter" are product names, keep them. "Twitter" is a product name. "AI" is a term, keep as is or translate? Usually "IA" in French, but the instruction says preserve technical terms? "AI" is a common acronym, often kept as is. But in French, "IA" is used. However, the instruction says "preserve product names
developmentapicreative
landing-page-design
halt-catch-fire
We need to translate the given text from English to French. The text is a description of an agent skill for landing page design. We must preserve the name "landing-page-design" but it's not in the text, so we don't include it. We translate only the text inside <text>. No extra labels. Keep technical terms like "CTA", "F-pattern", "SaaS", etc. as is or translate if appropriate? The instruction says preserve technical terms, so "CTA" stays, "F-pattern" might be kept or translated? Usually "F-pattern" is a known term, but in French it might be "motif en F" or keep as is. Since it's a technical term, I'll keep "F-pattern" as is. "above-the-fold" is a term, often kept as "above-the-fold" or "au-dessus de la ligne de flottaison". I'll keep as "above-the-fold" for consistency. "social proof" -> "preuve sociale". "mobile design" -> "conception mobile