Skills de Medios

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the...

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the...

Outpainting de imágenes en RunCom

Image outpainting on RunComfy via the `runcomfy` CLI — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspect ratio (square → 16:9, portrait → landscape) while preserving the original content. Routes across Nano Banana 2 Edit (default, spatial-language driven), GPT Image 2 Edit (multi-ref with reference-style matching), FLUX Kontext Pro (single-shot maximum-preservation), and the brand edit endpoints (Seedream / Dreamina / Qwen / FLUX 2). Picks the...

Image outpainting on RunComfy via the `runcomfy` CLI — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspect ratio (square → 16:9, portrait → landscape) while preserving the original content. Routes across Nano Banana 2 Edit (default, spatial-language driven), GPT Image 2 Edit (multi-ref with reference-style matching), FLUX Kontext Pro (single-shot maximum-preservation), and the brand edit endpoints (Seedream / Dreamina / Qwen / FLUX 2). Picks the...

Guía de conversión de imagen fija a video: selección de modelos, indicaciones de movimiento y movimiento de cámara. Cubre Wan 2.5 i2v, Seedance, Fabric, Grok Video con cuándo usar cada uno. Útil para: animar imágenes, crear video a partir de imágenes fijas, agregar movimiento, animaciones de productos. Disparadores: imagen a video, i2v, animar imagen, imagen fija a video, agregar movimiento a imagen, animación de imagen, foto a video, animar imagen fija, wan i2v, image2video, dar vida a imagen, animar foto, movimiento desde imagen

We need to translate the given text from English to Spanish. The text describes an agent skill called "image-to-video" but the instruction says to preserve the name only if it appears in the source text. The name "image-to-video" does not appear in the provided text, so we don't include it. We must preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "HappyHorse 1.0 I2V", "Arena #1", "Wan 2.7", "audio_url", "Seedance 2.0 Pro", "i2v" should remain as is. Also "native audio", "identity preservation", "custom-voiceover lip-sync", "multi-modal animation", "image + reference video + reference audio", "prompting patterns" are technical terms that might need careful translation. The text ends with "without burning..." which is incomplete but we translate as is. We need to output only the translation, no extra commentary. The target language is Spanish. Let's

We need to translate the given text from English to Spanish. The text describes an agent skill called "image-to-video" but the instruction says to preserve the name only if it appears in the source text. The name "image-to-video" does not appear in the provided text, so we don't include it. We must preserve product names, protocol names, URLs, numbers, and technical terms. So "RunComfy", "HappyHorse 1.0 I2V", "Arena #1", "Wan 2.7", "audio_url", "Seedance 2.0 Pro", "i2v" etc. should remain as is. Also "native audio", "identity preservation", "custom-voiceover lip-sync", "multi-modal animation", "image + reference video + reference audio", "prompting patterns" are technical terms that might need careful translation but should be kept as close as possible. The text ends with "without burning..." which might be incomplete but we translate as is. We need to output only the translation,

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning...

Guía de conversión de imagen fija a video: selección de modelos, indicaciones de movimiento y movimiento de cámara. Cubre Wan 2.5 i2v, Seedance, Fabric, Grok Video con cuándo usar cada uno. Útil para: animar imágenes, crear video a partir de imágenes fijas, agregar movimiento, animaciones de productos. Disparadores: imagen a video, i2v, animar imagen, imagen fija a video, agregar movimiento a imagen, animación de imagen, foto a video, animar imagen fija, wan i2v, image2video, dar vida a imagen, animar foto, movimiento desde imagen

We need to translate the given text from English to Spanish. The text describes an agent skill called "image-to-video" but the instruction says to preserve the name only if it appears in the source text. The name "image-to-video" does not appear in the provided text, so we don't include it. We must preserve product names, protocol names, URLs, numbers, and technical terms. So "RunComfy", "HappyHorse 1.0 I2V", "Arena #1", "Wan 2.7", "audio_url", "Seedance 2.0 Pro" should remain as is. Also "i2v" is a technical term. Translate the rest naturally. The text: "Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.

Generación de video Kling 3.0 en RunComfy. Kling 3.0 (también llamado Kling V3.0) es el modelo de video multishot de tercera generación de Kuaishou Technology, con audio sincronizado nativo e identidad de personaje consistente entre tomas. Esta habilidad cubre los seis endpoints de Kling 3.0, abarcando tres niveles de renderizado (Standard, Pro, 4K) y dos modos (texto a video, imagen a video). Ejecuta runcomfy run kling/kling-3.0/ / a través de la CLI local de RunComfy. Se activa con "kling", "kling 3.0", "kling v3", "kling pro",...

Generación de video Kling 3.0 en RunComfy. Kling 3.0 (también llamado Kling V3.0) es el modelo de video multishot de tercera generación de Kuaishou Technology, con audio sincronizado nativo e identidad de personaje consistente entre tomas. Esta habilidad cubre los seis endpoints de Kling 3.0, abarcando tres niveles de renderizado (Standard, Pro, 4K) y dos modos (texto a video, imagen a video). Ejecuta runcomfy run kling/kling-3.0/ / a través de la CLI local de RunComfy. Se activa con "kling", "kling 3.0", "kling v3", "kling pro",...

Generación de video Kling 3.0 en RunComfy. Kling 3.0 (también llamado Kling V3.0) es el modelo de video multiescena de tercera generación de Kuaishou Technology, con audio sincronizado nativo e identidad de personaje consistente entre escenas. Esta habilidad cubre los seis endpoints de Kling 3.0, abarcando tres niveles de renderizado (Standard, Pro, 4K) y dos modos (texto a video, imagen a video). Las llamadas ejecutan runcomfy run kling/kling-3.0/ / a través de la CLI local de RunComfy. Se activa con "kling", "kling 3.0", "kling v3", "kling pro",...

Generación de video Kling 3.0 en RunComfy. Kling 3.0 (también llamado Kling V3.0) es el modelo de video multishot de tercera generación de Kuaishou Technology, con audio sincronizado nativo e identidad de personaje consistente entre tomas. Esta habilidad cubre los seis endpoints de Kling 3.0, abarcando tres niveles de renderizado (Standard, Pro, 4K) y dos modos (texto a video, imagen a video). Ejecuta runcomfy run kling/kling-3.0/ / a través de la CLI local de RunComfy. Se activa con "kling", "kling 3.0", "kling v3", "kling pro",...

We need to translate the given text from English to Spanish, preserving the name "lipsync" and other technical terms like "RunComfy", "runcomfy CLI", "ByteDance OmniHuman", "Sync Labs sync v2 / Pro", "Kling lipsync", "Creatify lipsync". Also preserve URLs, numbers, etc. The instruction says to translate only the text inside <text>, and not include the name unless it appears in the source text. The name "lipsync" appears in the source text as part of "Kling lipsync" and "Creatify lipsync", so those should be kept as is. Also "Lip-sync" at the beginning should be translated? The instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "Lip-sync" might be considered a technical term? But it's also a verb. The source says "Lip-sync a face to a specific audio track" - that's a verb phrase. In Spanish, we might say "Sincronizar los

We need to translate the given text from English to Spanish, preserving the name "lipsync" and other technical terms like "RunComfy", "runcomfy CLI", "ByteDance OmniHuman", "Sync Labs sync v2 / Pro", "Kling lipsync", "Creatify lipsync". Also preserve URLs, numbers, etc. The instruction says to translate only the text inside <text>, and not include the name unless it appears in the source text. The name "lipsync" appears in the source text as "Lip-sync" at the beginning, so we should translate that as "Sincronización de labios" or similar? But careful: the instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "lipsync" is a technical term? It's a skill name. The instruction says "Name to preserve: lipsync". So we should preserve the word "lipsync" as is when it appears. In the source, it's "Lip-sync" (capitalized,

Agent Media OS — resolve any media need (BGM, SFX, image, icon) into a frozen local file + ledger record. One verb (`resolve`) handles the full cascade — project cache, global cache, HeyGen catalog search, freeze, register. Keeps search noise on disk, hands the agent a path. Use when a composition needs background music, sound effects, images, or icons.

Manejo multimedia con la librería Mediabunny

Genera imágenes con Google Nano Banana 2 (texto a imagen de nivel flash de la familia Gemini) en RunComfy, incluyendo los patrones de indicaciones documentados del modelo para que la habilidad obtenga resultados más precisos que con indicaciones simples sobre el mismo modelo. Documenta las fortalezas de Nano Banana 2 (iteración rápida, renderizado de tipografía en imagen, encuadre predecible, contexto web opcional), los precios por nivel de resolución, el dial de tolerancia de seguridad y cuándo dirigirse a Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream...

Genera imágenes con los modelos Pruna P-Image a través de la CLI de inference.sh. Modelos: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Capacidades: texto a imagen, edición de imágenes, estilos LoRA, composición de múltiples imágenes, inferencia rápida. Pruna optimiza los modelos para velocidad sin pérdida de calidad. Disparadores: pruna, p-image, pruna image, fast image generation, optimized flux, pruna ai, p image, fast ai image, economic image generation, cheap image generation

Genera videos con Pruna P-Video y modelos WAN a través de la CLI de inference.sh. Modelos: P-Video, WAN-T2V, WAN-I2V. Capacidades: texto a video, imagen a video, soporte de audio, 720p/1080p, inferencia rápida. Pruna optimiza los modelos para velocidad sin pérdida de calidad. Disparadores: 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

Genera videos con Pruna P-Video y modelos WAN a través de la CLI de inference.sh. Modelos: P-Video, WAN-T2V, WAN-I2V. Capacidades: texto a video, imagen a video, soporte de audio, 720p/1080p, inferencia rápida. Pruna optimiza los modelos para velocidad sin pérdida de calidad. Disparadores: 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

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 voz mediante TTS integrado. 18 veces más rápido y 6 veces más barato que la competencia. Modelos: P-Video-Avatar, P-Image (para generación de retratos). Capacidades: texto a avatar, avatares controlados por audio, 30 voces, 10 idiomas, 720p/1080p, TTS integrado, fondos dinámicos, control de cuerpo completo. Uso para: presentadores IA, demostraciones de productos, videos explicativos, influencers virtuales, marketing,...

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 voz mediante TTS integrado. 18 veces más rápido y 6 veces más barato que la competencia. Modelos: P-Video-Avatar, P-Image (para generación de retratos). Capacidades: texto a avatar, avatares controlados por audio, 30 voces, 10 idiomas, 720p/1080p, TTS integrado, fondos dinámicos, control de cuerpo completo. Usos: presentadores IA, demostraciones de productos, videos explicativos, influencers virtuales, marketing,...

Habilidad de generación de video con IA con selección automática de modelos entre Seedance 2, Kling 3.0, HappyHorse y más de 10 modelos. Produce videos terminados de múltiples tomas (5–120 s) a partir de texto, imágenes, URLs, guiones o audio, incluyendo música generada por IA, sincronización de labios y secuenciación de múltiples tomas. Sin necesidad de escribir indicaciones ni elegir modelos. ÚSALO PARA: producción de video, video con IA, hacer un video, video de producto, video de marca, clip promocional, video explicativo, video corto, video de TikTok, Reel de Instagram, YouTube Short, anuncio de producto,...

Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's dedicated `relight` LoRA endpoint for purpose-built relighting, with fallback to identity-preserving edit endpoints (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when prose lighting language is enough. Use for product relighting (studio softbox → window light), portrait mood shift (overcast → golden hour), or color-grade change....

Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's dedicated `relight` LoRA endpoint for purpose-built relighting, with fallback to identity-preserving edit endpoints (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when prose lighting language is enough. Use for product relighting (studio softbox → window light), portrait mood shift (overcast → golden hour), or color-grade change....

Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's dedicated `relight` LoRA endpoint for purpose-built relighting, with fallback to identity-preserving edit endpoints (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when prose lighting language is enough. Use for product relighting (studio softbox → window light), portrait mood shift (overcast → golden hour), or color-grade change....

Manejo de subtítulos en Remotion