Communitygithub.com

NeverSight/learn-skills.dev

Genera videos de avatar con cabeza parlante usando Pruna P-Video-Avatar a través de la CLI de inference.sh. Convierte una imagen de retrato en un video realista con TTS integrado. 18 veces más rápido y 6 veces más barato que la competencia.

¿Qué es learn-skills.dev?

Este skill permite a desarrolladores y agentes de IA generar videos de avatar realistas a partir de una sola imagen de retrato, utilizando el modelo Pruna P-Video-Avatar a través de la CLI `belt` de inference.sh. Es ideal para crear presentadores virtuales, demostraciones de productos, contenido educativo y marketing multilingüe. Ofrece ventajas significativas de velocidad y costo frente a alternativas como HeyGen o Fabric: es 18 veces más rápido y 6 veces más barato, con calidad comparable a Veo 3.0. El skill soporta generación de avatares a partir de texto o audio, 30 voces, 10 idiomas, resoluciones 720p y 1080p, fondos dinámicos y control corporal completo. También se integra con el modelo Pruna P-Image para generar retratos y con otros modelos de video e imagen de Pruna. Los usuarios pueden invocar el skill mediante comandos `belt` con parámetros JSON, incluyendo opciones para seleccionar voz, idioma, semilla y prompts de video/voz para controlar el tono y la emoción. Además, incluye una tabla de precios transparente y un fin de semana de lanzamiento gratuito.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/101-skills/skills/p-video-avatar

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

Instala el skill de la CLI belt: npx skills add belt-sh/cli

Pruna P-Video-Avatar

Genera videos de avatar con cabeza parlante a partir de una sola imagen de retrato a través de la CLI de inference.sh.

P-Video-Avatar es el modelo de video avatar más rápido y rentable disponible. Calidad comparable a Veo 3.0, 18 veces más rápido y 6 veces más barato que alternativas como Fabric, OmniHuman y HeyGen.

Inicio Rápido

Requiere la CLI de inference.sh (belt). Instrucciones de instalación

belt login

# Genera avatar a partir de retrato + guión de texto
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "¡Hola, bienvenido a nuestra demostración de producto!",
  "voice": "Zephyr (Female)"
}'

Flujo de Trabajo Completo: Generar Retrato + Video Avatar

Usa Pruna P-Image para generar el retrato y luego P-Video-Avatar para animarlo:

# 1. Genera una imagen de retrato con P-Image
belt app run pruna/p-image --input '{
  "prompt": "retrato profesional de una mujer joven, fondo neutro, mirando a cámara, iluminación de estudio, fotorrealista",
  "aspect_ratio": "9:16"
}'

# 2. Usa la URL de la imagen generada para crear el video avatar
belt app run pruna/p-video-avatar --input '{
  "image": "<image-url-from-step-1>",
  "voice_script": "¡Hola! Déjame guiarte a través de nuestras últimas funciones.",
  "voice": "Zephyr (Female)",
  "resolution": "720p"
}'

Ejemplos

Guión de Texto con Selección de Voz

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Bienvenido a nuestro recorrido por el producto. Hoy te mostraré tres funciones clave.",
  "voice": "Puck (Male)",
  "voice_language": "English (US)",
  "resolution": "720p"
}'

Avatar Controlado por Audio

Proporciona tu propio archivo de audio en lugar de usar el TTS integrado:

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "audio": "https://speech.mp3"
}'

Cuando se proporcionan tanto audio como voice_script, el audio tiene prioridad.

1080p con Estilo Personalizado

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "¡Esta es una noticia emocionante para nuestra comunidad!",
  "voice": "Aoede (Female)",
  "voice_prompt": "Tono entusiasta y enérgico, ritmo ligeramente más rápido",
  "video_prompt": "La persona está presentando en un escenario con iluminación dramática",
  "resolution": "1080p"
}'

Contenido Multilingüe

# Español
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Bienvenidos a nuestra demostración de producto.",
  "voice": "Kore (Female)",
  "voice_language": "Spanish"
}'

# Japonés
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "こんにちは、製品デモへようこそ。",
  "voice": "Leda (Female)",
  "voice_language": "Japanese"
}'

Generación Reproducible

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Resultados consistentes cada vez.",
  "seed": 42
}'

Voces Disponibles

Femeninas: Zephyr, Kore, Leda, Aoede, Callirrhoe, Autonoe, Despina, Erinome, Laomedeia, Achernar, Gacrux, Pulcherrima, Vindemiatrix, Sulafat

Masculinas: Puck, Charon, Fenrir, Orus, Enceladus, Iapetus, Umbriel, Algenib, Algieba, Schedar, Achird, Zubenelgenubi, Sadachbia, Sadaltager, Alnilam, Rasalgethi

Idiomas Soportados

Inglés (EE. UU.), Inglés (Reino Unido), Español, Francés, Alemán, Italiano, Portugués (Brasil), Japonés, Coreano, Hindi

Parámetros

ParámetroTipoValor por defectoDescripción
imagearchivorequeridoImagen de retrato (jpg, jpeg, png, webp)
voice_scriptcadena-Texto que la persona debe decir
audioarchivo-Archivo de audio (anula voice_script)
voicecadena"Zephyr (Female)"Selección de voz
voice_languagecadena"English (US)"Idioma de salida
resolutioncadena"720p"720p o 1080p
video_promptcadena"The person is talking."Controla el comportamiento del avatar y el fondo
voice_promptcadena"Say the following."Controla tono, ritmo, emoción
seedenteroaleatorioGeneración reproducible
disable_safety_filterbooleanotrueDeshabilitar filtro de contenido
disable_prompt_upsamplingbooleanofalseOmitir mejora del prompt

Precios

ResoluciónPrecio
720p$0.025 por segundo de video de salida
1080p$0.045 por segundo de video de salida

Ejemplo: Video de 30 segundos a 720p = $0.75

Fin de Semana de Lanzamiento Gratuito

P-Video-Avatar es completamente gratuito desde el jueves 1 de mayo de 2026 a las 4:00 p. m. CET hasta el domingo 4 de mayo de 2026 a las 11:59 p. m. CET. Todos los costos corren por nuestra cuenta durante este período; sin facturación, sin límites de resolución.

Ventaja Competitiva

CaracterísticaP-Video-AvatarFabric 1.0OmniHuman 1.5HeyGen Avatar 4
Velocidad (por segundo de video)~1.83s/s~34s/s (18x más lento)~28s/s (15x más lento)~26s/s (14x más lento)
Costo por segundo$0.025$0.14 (5.6x más)$0.16 (6.4x más)$0.075 (3x más)
TTS integradoSíSíNoSí
Fondo dinámicoSíSíNoSí
Soporte 1080pSíNoNoSí

Casos de Uso

  • Marketing: Demostraciones de productos, anuncios estilo UGC con presentadores IA
  • Educación: Videos de cursos, explicaciones, contenido de tutoría
  • Localización: Doblaje de contenido en 10 idiomas a partir de una imagen
  • Redes Sociales: Contenido consistente de influencers virtuales
  • Corporativo: Capacitación, incorporación, anuncios
  • Juegos: Avatares de personajes, videos de diálogo de NPC
  • Soporte al Cliente: Respuestas de video personalizadas

Consejos

  • Usa fotos de retrato de alta calidad (de frente, buena iluminación)
  • La relación de aspecto del video de salida coincide con la imagen de entrada
  • Usa video_prompt para controlar fondos dinámicos y lenguaje corporal
  • Usa voice_prompt para controlar el estilo de habla, emoción y ritmo
  • Mantén los videos por debajo de 3 minutos para una mejor consistencia visual
  • Genera retratos con pruna/p-image usando la relación de aspecto 9:16 para videos avatar verticales

Modelos Pruna Relacionados

# Generar imágenes de retrato
belt app run pruna/p-image --input '{"prompt": "retrato profesional"}'

# Generación general de video
belt app run pruna/p-video --input '{"prompt": "escena cinematográfica"}'

# Edición de imágenes
belt app run pruna/p-image-edit --input '{"prompt": "cambiar fondo", "image": "https://photo.jpg"}'

Skills Relacionados

# Skill completo de la plataforma (más de 250 apps)
npx skills add inference-sh/skills@infsh-cli

# Generación de video Pruna
npx skills add inference-sh/skills@p-video

# Generación de imágenes Pruna
npx skills add inference-sh/skills@p-image

# Todos los modelos de generación de video
npx skills add inference-sh/skills@ai-video-generation

# Generación de imágenes (para crear retratos)
npx skills add inference-sh/skills@ai-image-generation

Explora todas las apps de Pruna: belt app store --search "pruna"

Documentación

Individual skills in this repo

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

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), 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, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

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 awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

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

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Download YouTube videos, extract/proofread/translate subtitles, and render them onto video. Use whenever the user asks to download a YouTube video with subtitles, translate video subtitles to Chinese, add subtitles/burn subtitles to a video, or do ASR transcription on video audio. Covers the full pipeline: video download → subtitle extraction → proofreading → translation → SRT generation → subtitle rendering. Also use for "下载视频加字幕", "视频翻译字幕", "把字幕烧录到视频中". For pure subtitle file creation without rendering (just SRT output), this skill handles that too — stop before Phase 5.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

Skills relacionados