Communitygithub.com

JantonioFC/skillsbank

透過 inference.sh CLI 使用 Google Veo、Seedance、Wan、Grok 等 40+ 模型生成 AI 影片。支援的模型包括 Veo 3.1、Veo 3、Seedance 1.5 Pro、Wan 2.5、Grok Imagine Video、OmniHuman、Fabric、HunyuanVideo。功能涵蓋文字轉影片、圖片轉影片、唇形同步、虛擬人偶動畫、影片畫質提升等。

skillsbank 是什麼?

JantonioFC/skillsbank 是一個強大的 AI 影片生成技能,專為開發者和 AI 代理設計。它整合了 40 多種先進的 AI 模型,包括 Google Veo 3.1/3、ByteDance Seedance 1.5 Pro/1.0 Pro、Fal AI Wan 2.5、xAI Grok Imagine Video 以及 OmniHuman、Fabric、PixVerse 等,並透過統一的 inference.sh CLI 提供便捷的操作介面。此技能支援多種影片生成模式:文字轉影片(Text-to-Video)、圖片轉影片(Image-to-Video)、虛擬人偶動畫(Avatars/Lipsync)、影片畫質提升(Upscaling)、以及添加音效(Foley)等。使用者可以輕鬆地透過命令列執行生成任務,取得即時結果,並進一步串接整合到更複雜的媒體製作工作流程中。這個技能特別適合需要快速產出高品質 AI 影片、進行大量批次生成或建構自動化內容管線的開發者、創作者及企業。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/JantonioFC/skillsbank/tree/HEAD/skills/ai-video-generation

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

預覽

來自技能 README

AI 影片生成

說明文件

AI 影片生成

使用時機

當需要執行指定的自動化任務時,可運用此技能。

透過 inference.sh CLI,使用 40 多種 AI 模型生成影片。

AI 影片生成

快速開始

# 安裝 CLI
curl -fsSL https://cli.inference.sh | sh && infsh login

# 使用 Veo 生成影片
infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}'

可用模型

文字轉影片

模型App ID最佳用途
Veo 3.1 Fastgoogle/veo-3-1-fast快速生成,可選配音訊
Veo 3.1google/veo-3-1最佳品質,幀插值
Veo 3google/veo-3高品質附帶音訊
Veo 3 Fastgoogle/veo-3-fast快速生成附帶音訊
Veo 2google/veo-2逼真影片
Grok Videoxai/grok-imagine-videoxAI,可設定時長
Seedance 1.5 Probytedance/seedance-1-5-pro附帶首幀控制
Seedance 1.0 Probytedance/seedance-1-0-pro最高 1080p

圖片轉影片

模型App ID最佳用途
Wan 2.5falai/wan-2-5讓任意圖片動起來
Wan 2.5 I2Vfalai/wan-2-5-i2v高品質圖片轉影片
Seedance Litebytedance/seedance-1-0-lite輕量級 720p

虛擬人偶 / 唇形同步

模型App ID最佳用途
OmniHuman 1.5bytedance/omnihuman-1-5多角色
OmniHuman 1.0bytedance/omnihuman-1-0單一角色
Fabric 1.0falai/fabric-1-0圖片說話並唇形同步
PixVerse Lipsyncfalai/pixverse-lipsync逼真唇形同步

工具

工具App ID描述
HunyuanVideo Foleyinfsh/hunyuanvideo-foley為影片添加音效
Topaz Upscalerfalai/topaz-video-upscaler提升影片畫質
Media Mergerinfsh/media-merger合併影片並添加轉場

瀏覽所有影片應用

infsh app list --category video

範例

使用 Veo 文字轉影片

infsh app run google/veo-3-1-fast --input '{
  "prompt": "A timelapse of a flower blooming in a garden"
}'

Grok 影片

infsh app run xai/grok-imagine-video --input '{
  "prompt": "Waves crashing on a beach at sunset",
  "duration": 5
}'

使用 Wan 2.5 圖片轉影片

infsh app run falai/wan-2-5 --input '{
  "image_url": "https://your-image.jpg"
}'

AI 虛擬人偶 / 說話頭像

infsh app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

Fabric 唇形同步

infsh app run falai/fabric-1-0 --input '{
  "image_url": "https://face.jpg",
  "audio_url": "https://audio.mp3"
}'

PixVerse 唇形同步

infsh app run falai/pixverse-lipsync --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

影片畫質提升

infsh app run falai/topaz-video-upscaler --input '{"video_url": "https://..."}'

添加音效 (Foley)

infsh app run infsh/hunyuanvideo-foley --input '{
  "video_url": "https://silent-video.mp4",
  "prompt": "footsteps on gravel, birds chirping"
}'

合併影片

infsh app run infsh/media-merger --input '{
  "videos": ["https://clip1.mp4", "https://clip2.mp4"],
  "transition": "fade"
}'

相關技能

# 完整平台技能 (150+ 應用)
npx skills add inference-sh/skills@inference-sh

# Google Veo 專用
npx skills add inference-sh/skills@google-veo

# AI 虛擬人偶 & 唇形同步
npx skills add inference-sh/skills@ai-avatar-video

# 文字轉語音 (用於影片旁白)
npx skills add inference-sh/skills@text-to-speech

# 圖片生成 (用於圖片轉影片)
npx skills add inference-sh/skills@ai-image-generation

# Twitter (發佈影片)
npx skills add inference-sh/skills@twitter-automation

瀏覽所有應用:infsh app list

文件

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

JantonioFC/skillsbank

AI-powered image editing with style transfer and object removal

JantonioFC/skillsbank

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

JantonioFC/skillsbank

Analise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debitos, ocupante e classificacao da oportunidade.

JantonioFC/skillsbank

Embed Photopea in web apps using photopea.js. Covers embedding, file I/O, scripting, exporting, layers, text, filters, and the full Photoshop-compatible API.

JantonioFC/skillsbank

Best practices for Remotion - Video creation in React

JantonioFC/skillsbank

Generate walkthrough videos from Stitch projects using Remotion with smooth transitions, zooming, and text overlays

JantonioFC/skillsbank

Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence

JantonioFC/skillsbank

Writes complete, structured landing pages optimized for SEO ranking, AEO citation, and visitor conversion. Activate when the user wants to write or generate a landing page for a product, service, or offer.

JantonioFC/skillsbank

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

JantonioFC/skillsbank

Upload, stream, search, edit, transcribe, and generate AI video and audio using the VideoDB SDK.

JantonioFC/skillsbank

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

JantonioFC/skillsbank

Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities.

JantonioFC/skillsbank

Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending

JantonioFC/skillsbank

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

JantonioFC/skillsbank

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,'...

JantonioFC/skillsbank

Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, expla...

JantonioFC/skillsbank

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awarene...

JantonioFC/skillsbank

Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.

JantonioFC/skillsbank

Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.

JantonioFC/skillsbank

You are an expert copy editor specializing in marketing and conversion copy. Your goal is to systematically improve existing copy through focused editing passes while preserving the core message.

相關技能