image-to-video

작성자: halt-catch-fire

정지 영상을 비디오로 변환하는 가이드: 모델 선택, 모션 프롬프팅, 카메라 움직임. Wan 2.5 i2v, Seedance, Fabric, Grok Video를 각각 사용해야 할 시점과 함께 다룹니다. 용도: 이미지 애니메이션, 정지 영상으로 비디오 제작, 모션 추가, 제품 애니메이션. 트리거: 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

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

halt-catch-fire의 다른 스킬

ai-image-generation
halt-catch-fire
We need to translate the given text from English to Korean. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. So names like GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve, inference.sh CLI, etc. should remain as is. Also numbers like 50+, 4.5. The text inside <text> is a description of an agent skill for AI image generation. We need to translate the rest naturally into Korean. Let's break it down: "Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI." -> "inference.sh CLI를 통해 GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve 및 50개 이상의 모델로 AI 이미지를 생성합니다." "Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4
creativemediaimage
ai-video-generation
halt-catch-fire
inference.sh CLI를 통해 Google Veo, Seedance 2.0, HappyHorse, Wan, Grok 및 40개 이상의 모델로 AI 비디오를 생성합니다. 모델: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. 기능: 텍스트-비디오, 이미지-비디오, 참조-비디오, 비디오 편집, 립싱크, 아바타 애니메이션, 비디오 업스케일링, 폴리 사운드. 사용처: 소셜 미디어 비디오, 마케팅 콘텐츠, 설명 비디오, 제품 데모, AI 아바타. 트리거: 비디오 생성, AI 비디오,...
creativevideomedia
twitter-automation
halt-catch-fire
We need to translate the given text from English to Korean. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "twitter-automation" is not in the text, so we don't include it. We only translate the text inside <text>. No extra labels or commentary. The text describes an agent skill for automating Twitter/X. It mentions CLI, apps like x/post-tweet, etc., capabilities, use cases, and triggers. We need to translate naturally while keeping technical terms like "inference.sh CLI", "x/post-tweet", etc. as is. Also "Twitter/X" should be preserved as is or translated? The instruction says preserve product names, so "Twitter" and "X" are product names. But "Twitter/X" might be a combined reference. I'll keep "Twitter/X" as is. Similarly "X API" should be preserved. "inference.sh CLI" is a technical term, keep as is. The list of apps: x/post-tweet, x/post-create (with media),
marketingapicommunication
ai-avatar-video
halt-catch-fire
inference.sh CLI를 통해 AI 아바타 및 토킹 헤드 영상을 생성합니다. 권장: P-Video-Avatar (가장 빠르고 저렴하며 TTS 내장). 추가: OmniHuman, Fabric, PixVerse. 오디오: Inworld TTS-2 (100개 이상 언어, 캐릭터 감정 조절), ElevenLabs, Kokoro. 기능: 오디오 기반 아바타, 텍스트-투-아바타, 립싱크 영상, 토킹 헤드 생성, 가상 프레젠터, UGC 콘텐츠. 용도: AI 프레젠터, 설명 영상, 가상 인플루언서, 더빙, 마케팅 영상, UGC 광고, 게이밍 아바타,...
videocreativemedia
agent-browser
halt-catch-fire
inference.sh를 통한 AI 에이전트용 브라우저 자동화. @e 참조를 사용하여 웹 페이지 탐색, 요소와 상호작용, 스크린샷 촬영, 비디오 녹화. 기능: 웹 스크래핑, 양식 작성, 클릭, 타이핑, 드래그 앤 드롭, 파일 업로드, JavaScript 실행. 용도: 웹 자동화, 데이터 추출, 테스트, 에이전트 브라우징, 연구. 트리거: 브라우저, 웹 자동화, 스크래핑, 탐색, 클릭, 양식 작성, 스크린샷, 웹 브라우징, Playwright, 헤드리스 브라우저, 웹 에이전트, 인터넷 서핑, 비디오 녹화
browser-automationweb-scrapingtesting
web-search
halt-catch-fire
Tavily와 Exa를 통해 inference.sh CLI로 웹 검색 및 콘텐츠 추출. 앱: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. 기능: AI 기반 검색, 콘텐츠 추출, 직접 답변, 리서치. 용도: 리서치, RAG 파이프라인, 사실 확인, 콘텐츠 수집, 에이전트. 트리거: 웹 검색, tavily, exa, search api, 콘텐츠 추출, 리서치, 인터넷 검색, ai 검색, 검색 어시스턴트, 웹 스크래핑, rag, perplexity 대안
researchweb-scrapingapi
infsh-cli
halt-catch-fire
inference.sh CLI를 통해 250개 이상의 AI 앱 실행 - 이미지 생성, 비디오 제작, LLM, 검색, 3D, Twitter 자동화. 모델: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter 등 다수. AI 앱 실행, 이미지/비디오 생성, LLM 호출, 웹 검색 또는 Twitter 자동화 시 사용. 트리거: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
developmentapicreative
landing-page-design
halt-catch-fire
랜딩 페이지 전환 최적화: 레이아웃 규칙, 히어로 섹션 디자인, CTA 심리학 포함. 어바우드 더 폴드 공식, 소셜 프루프 배치, 모바일 디자인, F-패턴 리딩을 다룹니다. 사용처: 스타트업 랜딩 페이지, 제품 페이지, SaaS 마케팅, 전환 최적화. 트리거: 랜딩 페이지, 히어로 섹션, 어바우드 더 폴드, 전환 최적화, 랜딩 페이지 디자인, CTA 버튼, 히어로 이미지, 랜딩 페이지 레이아웃, SaaS 랜딩 페이지, 제품 페이지 디자인, 전환율, 랜딩 페이지...