Communitygithub.com

Army161/OpenMontage

Genera videos con IA a partir de descripciones de texto mediante múltiples pasarelas de proveedores. Útil para: (1) Generar videos desde texto, (2) Crear clips de video generados por IA para producción de contenido, (3) Generación de imagen a video con una imagen de referencia, (4) Elegir entre proveedores de generación de video (VEO, Kling, Sora, Runway, Seedance, MiniMax). Soporta dos pasarelas: HeyGen API y fal.ai API.

¿Qué es OpenMontage?

Este skill permite generar videos mediante inteligencia artificial a partir de descripciones textuales, soportando múltiples proveedores a través de dos pasarelas API: fal.ai y HeyGen. Los usuarios pueden elegir entre modelos como Seedance 2.0 (el predeterminado premium para trabajo cinematográfico), VEO 3.1, Kling Pro, Sora V2, Runway Gen-4, y muchos otros. Proporciona funcionalidades completas: autenticación, generación de video (texto a video e imagen a video), verificación del estado de ejecución mediante polling, y ejemplos prácticos en curl, TypeScript y Python. Además, incluye un selector inteligente (`video_selector`) que evalúa disponibilidad, coste y calidad, sesgando hacia Seedance 2.0 para intenciones cinematográficas. Es ideal para creadores de contenido y desarrolladores que necesitan integrar generación de video de alta calidad en sus flujos de trabajo.

Compatible con~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/Army161/OpenMontage/tree/HEAD/.agents/skills/ai-video-gen

Preguntar en tu IA favorita

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

Documentación

Generación de Video (Multi-Pasarela)

Genera videos con IA a partir de descripciones de texto. Soporta múltiples proveedores a través de dos pasarelas API:

PasarelaVariable de EntornoProveedoresHerramienta
fal.aiFAL_KEYSeedance 2.0 (estándar + rápido), Kling v3/v2.1, MiniMax, VEOseedance_video, kling_video, minimax_video, veo_video
HeyGenHEYGEN_API_KEYVEO 3.1, Kling Pro, Sora v2, Runway Gen-4, Seedance Pro / Lite (1.x)heygen_video

Predeterminado premium preferido — Seedance 2.0. Cuando cualquier pasarela premium esté configurada (FAL_KEY → seedance_video, o la ruta de Video Agent / Avatar Shots de HeyGen), Seedance 2.0 es el predeterminado preferido para trabajo cinematográfico, tráileres y clips de alta fidelidad. Es el único modelo en la flota con audio sincronizado nativo en una sola pasada, generación de múltiples tomas, control de cámara a nivel de director y sincronización de labios a partir de diálogo citado, y ocupa el puesto #1 en Artificial Analysis Elo a principios de 2026. Cambie de él solo cuando el usuario tenga una razón específica (presupuesto, preferencia de proveedor, ajuste estilístico como VEO para paisajes fotorrealistas o Kling para un aspecto anime concreto). Consulte la Capa 3 seedance-2-0 para la guía autorizada de parámetros y prompts.

IMPORTANTE: Use siempre video_selector en lugar de llamar a las herramientas de proveedor directamente. El selector gestiona verificaciones de disponibilidad, comparación de costes y conmutación por error automática, y su motor de puntuación ya sesga hacia Seedance 2.0 para intenciones cinematográficas.

Autenticación

Use la pasarela configurada que mejor coincida con los proveedores disponibles del usuario y sus objetivos de coste/calidad.

  • HeyGen: Establezca HEYGEN_API_KEY para acceder a la pasarela multi-modelo.
  • fal.ai: Establezca FAL_KEY para acceder a Kling, MiniMax y Veo a través de fal.ai.

No describa ninguna pasarela como predeterminada o mejor opción sin verificar primero el registro y la idoneidad de la tarea actual.

curl -X POST "https://api.heygen.com/v1/workflows/executions" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"workflow_type": "GenerateVideoNode", "input": {"prompt": "A drone shot flying over a coastal city at sunset"}}'

Flujo de Trabajo Predeterminado

  1. Llame a POST /v1/workflows/executions con workflow_type: "GenerateVideoNode" y su prompt
  2. Reciba un execution_id en la respuesta
  3. Consulte GET /v1/workflows/executions/{id} cada 10 segundos hasta que el estado sea completed
  4. Use el video_url devuelto en el resultado

Ejecutar Generación de Video

Endpoint

POST https://api.heygen.com/v1/workflows/executions

Campos de Solicitud

CampoTipoOblig.Descripción
workflow_typecadenaSíDebe ser "GenerateVideoNode"
input.promptcadenaSíDescripción de texto del video a generar
input.providercadenaProveedor de generación de video (predeterminado: "veo_3_1"). Ver Proveedores a continuación.
input.aspect_ratiocadenaRelación de aspecto (predeterminado: "16:9"). Valores comunes: "16:9", "9:16", "1:1"
input.reference_image_urlcadenaURL de imagen de referencia para generación de imagen a video
input.tail_image_urlcadenaURL de imagen final para guía de último fotograma
input.configobjetoSobrescrituras de configuración específicas del proveedor

Proveedores

ProveedorValorDescripción
VEO 3.1"veo_3_1"Google VEO 3.1 (predeterminado, mayor calidad)
VEO 3.1 Rápido"veo_3_1_fast"Variante más rápida de VEO 3.1
VEO 3"veo3"Google VEO 3
VEO 3 Rápido"veo3_fast"Variante más rápida de VEO 3
VEO 2"veo2"Google VEO 2
Kling Pro"kling_pro"Modelo Kling Pro
Kling V2"kling_v2"Modelo Kling V2
Sora V2"sora_v2"OpenAI Sora V2
Sora V2 Pro"sora_v2_pro"OpenAI Sora V2 Pro
Runway Gen-4"runway_gen4"Runway Gen-4
Seedance Lite"seedance_lite"Seedance Lite
Seedance Pro"seedance_pro"Seedance Pro
LTX Destilado"ltx_distilled"LTX Destilado (más rápido)

curl

curl -X POST "https://api.heygen.com/v1/workflows/executions" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "workflow_type": "GenerateVideoNode",
    "input": {
      "prompt": "A drone shot flying over a coastal city at golden hour, cinematic lighting",
      "provider": "veo_3_1",
      "aspect_ratio": "16:9"
    }
  }'

TypeScript

interface GenerateVideoInput {
  prompt: string;
  provider?: string;
  aspect_ratio?: string;
  reference_image_url?: string;
  tail_image_url?: string;
  config?: Record<string, any>;
}

interface ExecuteResponse {
  data: {
    execution_id: string;
    status: "submitted";
  };
}

async function generateVideo(input: GenerateVideoInput): Promise<string> {
  const response = await fetch("https://api.heygen.com/v1/workflows/executions", {
    method: "POST",
    headers: {
      "X-Api-Key": process.env.HEYGEN_API_KEY!,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      workflow_type: "GenerateVideoNode",
      input,
    }),
  });

  const json: ExecuteResponse = await response.json();
  return json.data.execution_id;
}

Python

import requests
import os

def generate_video(
    prompt: str,
    provider: str = "veo_3_1",
    aspect_ratio: str = "16:9",
    reference_image_url: str | None = None,
    tail_image_url: str | None = None,
) -> str:
    payload = {
        "workflow_type": "GenerateVideoNode",
        "input": {
            "prompt": prompt,
            "provider": provider,
            "aspect_ratio": aspect_ratio,
        },
    }

    if reference_image_url:
        payload["input"]["reference_image_url"] = reference_image_url
    if tail_image_url:
        payload["input"]["tail_image_url"] = tail_image_url

    response = requests.post(
        "https://api.heygen.com/v1/workflows/executions",
        headers={
            "X-Api-Key": os.environ["HEYGEN_API_KEY"],
            "Content-Type": "application/json",
        },
        json=payload,
    )

    data = response.json()
    return data["data"]["execution_id"]

Formato de Respuesta

{
  "data": {
    "execution_id": "node-gw-v1d2e3o4",
    "status": "submitted"
  }
}

Verificar Estado

Endpoint

GET https://api.heygen.com/v1/workflows/executions/{execution_id}

curl

curl -X GET "https://api.heygen.com/v1/workflows/executions/node-gw-v1d2e3o4" \
  -H "X-Api-Key: $HEYGEN_API_KEY"

Formato de Respuesta (Completado)

{
  "data": {
    "execution_id": "node-gw-v1d2e3o4",
    "status": "completed",
    "output": {
      "video": {
        "video_url": "https://resource.heygen.ai/generated/video.mp4",
        "video_id": "abc123"
      },
      "asset_id": "asset-xyz789"
    }
  }
}

Sondeo para Finalización

async function generateVideoAndWait(
  input: GenerateVideoInput,
  maxWaitMs = 600000,
  pollIntervalMs = 10000
): Promise<{ video_url: string; video_id: string; asset_id: string }> {
  const executionId = await generateVideo(input);
  console.log(`Submitted video generation: ${executionId}`);

  const startTime = Date.now();
  while (Date.now() - startTime < maxWaitMs) {
    const response = await fetch(
      `https://api.heygen.com/v1/workflows/executions/${executionId}`,
      { headers: { "X-Api-Key": process.env.HEYGEN_API_KEY! } }
    );
    const { data } = await response.json();

    switch (data.status) {
      case "completed":
        return {
          video_url: data.output.video.video_url,
          video_id: data.output.video.video_id,
          asset_id: data.output.asset_id,
        };
      case "failed":
        throw new Error(data.error?.message || "Video generation failed");
      case "not_found":
        throw new Error("Workflow not found");
      default:
        await new Promise((r) => setTimeout(r, pollIntervalMs));
    }
  }

  throw new Error("Video generation timed out");
}

Ejemplos de Uso

Texto a Video Simple

curl -X POST "https://api.heygen.com/v1/workflows/executions" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "workflow_type": "GenerateVideoNode",
    "input": {
      "prompt": "A person walking through a sunlit park, shallow depth of field"
    }
  }'

Imagen a Video

{
  "workflow_type": "GenerateVideoNode",
  "input": {
    "prompt": "Animate this product photo with a slow zoom and soft particle effects",
    "reference_image_url": "https://example.com/product-photo.png",
    "provider": "kling_pro"
  }
}

Formato Vertical para Redes Sociales

{
  "workflow_type": "GenerateVideoNode",
  "input": {
    "prompt": "A trendy coffee shop interior, camera slowly panning across the counter",
    "aspect_ratio": "9:16",
    "provider": "veo_3_1"
  }
}

Generación Rápida con LTX

{
  "workflow_type": "GenerateVideoNode",
  "input": {
    "prompt": "Abstract colorful shapes morphing and flowing",
    "provider": "ltx_distilled"
  }
}

Buenas Prácticas

  1. Sea descriptivo en los prompts — incluya detalles de movimiento de cámara, iluminación, estilo y atmósfera
  2. Predetermine Seedance 2.0 (a través de seedance_video) para trabajo cinematográfico y guiado por movimiento cuando FAL_KEY esté configurado — audio sincronizado en una sola pasada, múltiples tomas, sincronización de labios, cámara a nivel de director. Use VEO 3.1 / Sora V2 Pro cuando el usuario quiera específicamente el carácter de movimiento de Google u OpenAI; use ltx_distilled o veo3_fast solo cuando la velocidad sea la restricción absoluta
  3. Use imágenes de referencia para generación de imagen a video — ideal para animar fotos de productos o imágenes fijas
  4. La generación de video es el flujo de trabajo más lento — permita hasta 5 minutos, sondee cada 10 segundos
  5. La relación de aspecto importa — use 9:16 para historias/reels de redes sociales, 16:9 para paisaje, 1:1 para cuadrado
  6. El resultado incluye asset_id — úselo para referenciar el video generado en otros flujos de trabajo de HeyGen
  7. Las URLs de resultado son temporales — descargue o guarde los videos generados rápidamente

Individual skills in this repo

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

Army161/OpenMontage

Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API. Use when: (1) Choosing a specific avatar and voice for a video, (2) Writing exact scripts for an avatar to speak, (3) Building multi-scene videos with different backgrounds per scene, (4) Creating transparent WebM videos for compositing, (5) Using talking photos as video presenters, (6) Integrating HeyGen avatars with Remotion, (7) Batch video generation with exact specs, (8) Brand-consistent production videos with precise control.

Army161/OpenMontage

Use p5.js/canvas for local procedural character effects: particles, weather, squash/stretch, walk cycles, and environmental motion.

Army161/OpenMontage

Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.

Army161/OpenMontage

Create videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) One-shot prompt-to-video generation, (6) User says "make me a video" or "create a video about X".

Army161/OpenMontage

Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Use when creating Chinese voiceovers, when the user prefers Doubao/Volcengine/火山引擎/豆包 TTS, or when narration needs character-level timestamp metadata for subtitles.

Army161/OpenMontage

Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.

Army161/OpenMontage

Use when implementing Disney's 12 animation principles with Framer Motion in React applications

Army161/OpenMontage

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.

Army161/OpenMontage

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

Army161/OpenMontage

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

Army161/OpenMontage

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

Army161/OpenMontage

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

Army161/OpenMontage

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

Army161/OpenMontage

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (website-to-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.

Army161/OpenMontage

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

Army161/OpenMontage

Best practices for Remotion - Video creation in React

Army161/OpenMontage

Toolkit-specific Remotion patterns — custom transitions, shared components, and project conventions. For core Remotion framework knowledge (hooks, animations, rendering, etc.), see the `remotion-official` skill.

Army161/OpenMontage

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

Army161/OpenMontage

Animate SVG character rigs with GSAP, CSS transforms, Remotion frame control, and HyperFrames-compatible browser previews.

Army161/OpenMontage

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

Skills relacionados