Communitygithub.com

NeverSight/learn-skills.dev

Genera videos de IA con Seedance (ByteDance) a través de la API de AceDataCloud. Úsalo para crear videos a partir de prompts de texto, animar imágenes en videos con movimiento, o impulsar la generación multimodal de Seedance 2.0 con referencias de personas reales/personajes, audio de referencia y video de referencia. Soporta múltiples modelos con resolución configurable (hasta 4k), relación de aspecto, duración y generación de audio opcional.

¿Qué es learn-skills.dev?

Esta habilidad te permite generar videos de baile y movimiento con IA utilizando los modelos Seedance de ByteDance a través de la API de AceDataCloud. Es ideal para desarrolladores y creadores de contenido que desean producir videos de alta calidad a partir de descripciones de texto, animar imágenes fijas o aprovechar las capacidades multimodales avanzadas de Seedance 2.0, como referencias de personas reales, audio y video. La habilidad soporta una amplia gama de modelos, desde la serie Seedance 2.0 (con resolución de hasta 4k) hasta las versiones 1.x, cada una optimizada para diferentes casos de uso como velocidad, costo o calidad. Los flujos de trabajo incluyen texto a video, imagen a video, y combinaciones complejas con múltiples referencias de imagen, audio y video. Además, se integra con plataformas como Cursor y Claude Code a través de MCP (Model Context Protocol), facilitando su uso en entornos de desarrollo. La documentación detallada guía al usuario en la configuración de autenticación, polling de tareas asíncronas, y parámetros avanzados como resolución, duración, relación de aspecto y semilla para resultados reproducibles.

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

Preguntar en tu IA favorita

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

Documentación

Generación de Videos con Seedance

Genera videos de baile y movimiento con IA a través de la API Seedance (ByteDance) de AceDataCloud.

Configuración: Consulta autenticación para la configuración del token.

Inicio Rápido

curl -X POST https://api.acedata.cloud/seedance/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model": "doubao-seedance-2-0-260128", "content": [{"type": "text", "text": "a dancer performing contemporary ballet in a misty forest"}], "callback_url": "https://api.acedata.cloud/health"}'

Asíncrono: Consulta polling de tareas asíncronas. Realiza polling mediante POST /seedance/tasks con {"id": "..."}. Esto devuelve un ID de tarea inmediatamente. Realiza polling para obtener el resultado:

curl -X POST https://api.acedata.cloud/seedance/tasks \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"id": "<task_id from above>"}'

Modelos

Seedance 2.0 (generación actual — referencia multimodal)

La serie 2.0 añade entradas de referencia multimodal: referencias de imagen de persona real/personaje, audio de referencia y video de referencia (consulta los flujos de trabajo a continuación).

ModeloMejor paraResolución máxima
doubao-seedance-2-0-260128Máxima calidad, referencia de persona real/personaje, salida 4k4k
doubao-seedance-2-0-fast-260128Generación 2.0 más rápida720p
doubao-seedance-2-0-mini-260615Ligero / 2.0 más rentable720p

Seedance 1.x

ModeloTipoMejor para
doubao-seedance-1-5-pro-251215Texto+Imagen a Video1.5 emblemático, soporte de audio
doubao-seedance-1-0-pro-250528Texto+Imagen a VideoUso general, calidad confiable
doubao-seedance-1-0-pro-fast-251015Texto+Imagen a VideoGeneración Pro más rápida
doubao-seedance-1-0-lite-t2v-250428Solo texto a videoTexto a video ligero
doubao-seedance-1-0-lite-i2v-250428Solo imagen a videoImagen a video ligero

Flujos de Trabajo

1. Texto a Video

Pasa un elemento de contenido de texto en el arreglo content.

POST /seedance/videos
{
  "model": "doubao-seedance-1-0-pro-250528",
  "content": [
    {"type": "text", "text": "a street dancer doing breakdancing moves in an urban setting"}
  ],
  "resolution": "1080p",
  "ratio": "16:9",
  "duration": 5
}

2. Imagen a Video

Incluye un elemento de contenido de imagen (con un role opcional) junto al texto.

POST /seedance/videos
{
  "model": "doubao-seedance-1-5-pro-251215",
  "content": [
    {"type": "text", "text": "the person starts dancing gracefully"},
    {
      "type": "image_url",
      "role": "first_frame",
      "image_url": {"url": "https://example.com/dancer.jpg"}
    }
  ],
  "resolution": "720p",
  "duration": 5
}

Roles de imagen:

  • first_frame — la imagen se usa como el fotograma inicial
  • last_frame — la imagen se usa como el fotograma final
  • reference_image — la imagen se usa como referencia de estilo / sujeto / persona real (Seedance 2.0 mantiene consistente a la persona o personaje referenciado)

Medios de referencia (solo Seedance 2.0):

  • audio_url — audio de referencia para timbre de voz / música de fondo (sin role)
  • video_url — video de referencia para sujeto, movimiento de cámara, movimiento o estilo general (sin role)

3. Primer fotograma + Último fotograma

Proporciona tanto una imagen de inicio como de fin:

POST /seedance/videos
{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {"type": "text", "text": "smooth transition between two scenes"},
    {"type": "image_url", "role": "first_frame", "image_url": {"url": "https://example.com/start.jpg"}},
    {"type": "image_url", "role": "last_frame", "image_url": {"url": "https://example.com/end.jpg"}}
  ]
}

4. Referencia de persona real / personaje (Seedance 2.0)

Los modelos Seedance 2.0 (doubao-seedance-2-0-260128, doubao-seedance-2-0-fast-260128, doubao-seedance-2-0-mini-260615) pueden mantener a una persona o personaje específico consistente en una escena completamente nueva. Pasa una o más fotos como elementos image_url con role: "reference_image" — el modelo preserva la apariencia de ese sujeto. Se aceptan hasta 9 imágenes de referencia.

POST /seedance/videos
{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {"type": "text", "text": "the same person walking through a neon-lit night market, cinematic"},
    {"type": "image_url", "role": "reference_image", "image_url": {"url": "https://example.com/person.jpg"}}
  ],
  "resolution": "1080p",
  "duration": 8
}

5. Audio / video de referencia (Seedance 2.0)

Los modelos 2.0 también aceptan audio de referencia (timbre de voz, música de fondo) y video de referencia (contenido del sujeto, movimiento de cámara, movimiento, estilo general). Añade elementos de contenido audio_url y/o video_url. Límites: hasta 3 referencias de audio y 3 de video por solicitud.

POST /seedance/videos
{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {"type": "text", "text": "a singer performing on stage, matching the reference voice and motion"},
    {"type": "image_url", "role": "reference_image", "image_url": {"url": "https://example.com/person.jpg"}},
    {"type": "audio_url", "audio_url": {"url": "https://example.com/voice.mp3"}},
    {"type": "video_url", "video_url": {"url": "https://example.com/motion.mp4"}}
  ],
  "generate_audio": true
}

Parámetros

ParámetroValoresDescripción
modelconsulta la tabla de ModelosModelo a utilizar (obligatorio)
contentarregloElementos de entrada: text, image_url, audio_url (2.0), video_url (2.0) (obligatorio)
resolution"480p", "720p", "1080p", "4k"Resolución de salida. 4k es solo para doubao-seedance-2-0-260128 (estándar); 2-0-fast / 2-0-mini máximo 720p (predeterminado: 720p para pro/2.0, 480p para lite)
ratio"16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive"Relación de aspecto (predeterminado: 16:9)
duration2 – 15Duración en segundos (Seedance 2.0 soporta 4–15)
frames29–361 (debe satisfacer 25+4n)Número de fotogramas — mutuamente excluyente con duration
seed-1 a 4294967295Semilla para resultados reproducibles (-1 = aleatorio)
generate_audiotrue / falseGenerar audio (soportado por doubao-seedance-1-5-pro-251215 y la serie doubao-seedance-2-0; otros modelos lo ignoran)
camerafixedtrue / falseFijar la posición de la cámara durante la generación
watermarktrue / falseAñadir una marca de agua al video generado
return_last_frametrue / falseDevolver el último fotograma del video generado
service_tier"default", "flex"Nivel de procesamiento (predeterminado: default)
execution_expires_afternúmeroUmbral de tiempo de espera de la tarea en segundos

Sintaxis de Parámetros en Línea

También puedes incrustar parámetros de generación directamente en el prompt de texto usando la sintaxis --param valor:

A kitten yawning at the camera. --rs 720p --rt 16:9 --dur 5 --fps 24 --seed 42

Parámetros en línea soportados: --rs (resolución), --rt (relación de aspecto), --dur (duración), --frames, --fps (solo 24), --seed, --cf (camera_fixed), --wm (marca de agua).

Advertencias

  • Los nombres de los modelos usan la convención doubao-* (ej. doubao-seedance-1-0-pro-250528) — los nombres cortos antiguos como seedance-1.0 no son válidos
  • El arreglo content reemplaza los antiguos campos prompt + image_url; usa siempre content
  • Los escenarios de imagen y texto son mutuamente excluyentes por elemento de contenido — cada elemento tiene text o image_url, no ambos
  • first_frame y last_frame pueden combinarse en una sola solicitud, pero reference_image es mutuamente excluyente con first_frame / last_frame — no mezcles una imagen de referencia con fotogramas de inicio/fin
  • generate_audio: true es soportado por doubao-seedance-1-5-pro-251215 y la serie doubao-seedance-2-0; otros modelos ignoran este campo
  • Los modelos Lite se dividen: *-lite-t2v-* solo acepta texto, *-lite-i2v-* solo acepta imagen a video
  • Los elementos de referencia audio_url y video_url son usados solo por la serie Seedance 2.0
  • Las opciones de resolución son 480p, 720p, 1080p y 4k (4k es solo para doubao-seedance-2-0-260128; 2-0-fast / 2-0-mini máximo 720p) — no hay 360p ni 540p
  • Los valores de service_tier son "default" y "flex" (no "standard"/"premium")
  • El rango de duración es 2–15 segundos (Seedance 2.0 soporta 4–15) — los valores fuera de este rango fallarán
  • Los estados de tarea usan "succeeded" (no "completed") — verifica este valor al hacer polling

MCP: pip install mcp-seedance | Alojado: https://seedance.mcp.acedata.cloud/mcp | Consulta todos los servidores MCP

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 talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

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

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