Skills Médias

Run any model on RunComfy from the command line. The `runcomfy` CLI is one binary, one auth, hundreds of model endpoints — image generation, image edit, video generation, image-to-video, lip-sync, face swap, video edit, inpainting, outpainting, extend, ControlNet, relight, upscale, LoRA training and more. Submit a request, poll for status, download the output. This skill teaches the agent how to install, authenticate, discover model schemas, invoke models, stream / poll / no-wait, script in...

Run any model on RunComfy from the command line. The `runcomfy` CLI is one binary, one auth, hundreds of model endpoints — image generation, image edit, video generation, image-to-video, lip-sync, face swap, video edit, inpainting, outpainting, extend, ControlNet, relight, upscale, LoRA training and more. Submit a request, poll for status, download the output. This skill teaches the agent how to install, authenticate, discover model schemas, invoke models, stream / poll / no-wait, script in...

Run any model on RunComfy from the command line. The `runcomfy` CLI is one binary, one auth, hundreds of model endpoints — image generation, image edit, video generation, image-to-video, lip-sync, face swap, video edit, inpainting, outpainting, extend, ControlNet, relight, upscale, LoRA training and more. Submit a request, poll for status, download the output. This skill teaches the agent how to install, authenticate, discover model schemas, invoke models, stream / poll / no-wait, script in...

Générer des vidéos avec ByteDance Seedance 2.0 via l'interface CLI inference.sh. Modèle unifié pour texte-vers-vidéo, image-vers-vidéo et référence-vers-vidéo avec audio synchronisé, jusqu'à 1080p, durée de 4 à 15 secondes. Variantes Pro et Fast. Variantes Studio avec bibliothèque d'actifs privée pour la cohérence des portraits. Utilisation pour : vidéos sur les réseaux sociaux, clips musicaux, démos produits, contenu animé, vidéo IA avec son. Déclencheurs : seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio,...

Générer des vidéos avec ByteDance Seedance 2.0 via l'interface CLI inference.sh. Modèle unifié pour texte-vers-vidéo, image-vers-vidéo et référence-vers-vidéo avec audio synchronisé, jusqu'à 1080p, durée de 4 à 15 secondes. Variantes Pro et Fast. Variantes Studio avec bibliothèque d'actifs privée pour la cohérence des portraits. Utilisation : vidéos pour réseaux sociaux, clips musicaux, démos produits, contenu animé, vidéo IA avec son. Déclencheurs : seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio,...

We need to translate the given text from English to French. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions strengths, duration schema, and routing alternatives. Also mentions CLI command and trigger keywords. We must preserve product names, protocol names, URLs, numbers, technical terms. So "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "seedance-v2", "runcomfy run bytedance/seedance-v2/pro" should remain as is. Also "4–15s" is a number range, keep as is. "multi-modal references", "in-pass audio", "lip-sync", "cinematic motion refinement" are technical terms; translate if possible but keep meaning. "CLI" is an acronym, keep. Trigger keywords: "seedance", "seedance 2", "seedance v2", "seedance...

We need to translate the given text from English to French. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions strengths, duration schema, and routing alternatives. Also mentions CLI command and trigger keywords. Important: Preserve product names, protocol names, URLs, numbers, technical terms. Do not add any extra commentary or labels. The name "seedance-v2" is to be preserved but it's not in the text? Actually the instruction says "Name to preserve: seedance-v2" but the text does not contain that exact string. The text contains "seedance", "seedance 2", "seedance v2", "seedance..." so we should preserve those as is. Also "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "runcomfy run bytedance/seedance-v2/pro" should remain unchanged. Numbers like

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance...

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance...

Storyboard pour film et vidéo avec vocabulaire des plans, règles de continuité et mise en page des cases. Couvre les types de plans, angles de caméra, mouvements, règle des 180 degrés et format d'annotation. Utilisation : planification vidéo, préproduction de film, storyboards publicitaires, planification de clips musicaux, animation. Déclencheurs : storyboard, storyboarding, liste de plans, planification de film, planification vidéo, préproduction, composition de plans, angles de caméra, planification de scène, script visuel, animatique, cases de storyboard, storyboard vidéo

We need to translate the given text from English to French. The text describes a skill for storyboard creation. We must preserve the name "storyboard-creation" but it's not in the text, so we don't include it. We translate the entire text inside <text>. No extra labels. Keep technical terms like "180-degree rule" as is? Probably translate "180-degree rule" as "règle des 180 degrés". Shot types, camera angles, etc. should be translated appropriately. Also preserve URLs? None. Numbers: "180-degree" is a number. Also "shot vocabulary" -> "vocabulaire des plans". "continuity rules" -> "règles de continuité". "panel layout" -> "disposition des panneaux". "annotation format" -> "format d'annotation". The triggers list: storyboard, storyboarding, shot list, etc. Translate each trigger word/phrase. For "storyboard" and "storyboarding" in French, "storyboard" is often used as is, but "story

Storyboard pour film et vidéo avec vocabulaire des plans, règles de continuité et mise en page des cases. Couvre les types de plans, angles de caméra, mouvements, règle des 180 degrés et format d'annotation. Utilisation : planification vidéo, préproduction de film, storyboards publicitaires, planification de clips musicaux, animation. Déclencheurs : storyboard, storyboarding, liste de plans, planification de film, planification vidéo, préproduction, composition de plans, angles de caméra, planification de scène, script visuel, animatique, cases de storyboard, storyboard vidéo

Créez une animation Lottie (Bodymovin) au format JSON qui s'affiche dans un lecteur skia local. Utilisez-la lorsque l'utilisateur demande de créer, générer, modifier ou corriger une animation Lottie, ou demande "une animation" à charger.

Lorsque l'utilisateur souhaite créer, générer ou produire du contenu vidéo à l'aide d'outils d'IA ou de frameworks programmatiques. Utilisez également lorsque l'utilisateur mentionne 'production vidéo', 'IA vidéo', 'Remotion', 'Hyperframes', 'HeyGen', 'Synthesia', 'Veo', 'Sora', 'Runway', 'Kling', 'Seedance', 'Hailuo', 'MiniMax', 'Pika', 'Hunyuan', 'Wan', 'génération vidéo', 'avatar IA', 'vidéo de tête parlante', 'vidéo programmatique', 'modèle vidéo', 'vidéo explicative', 'vidéo de démonstration produit', 'pipeline vidéo' ou 'fais-moi une vidéo'. Utilisez...

Modifier une vidéo existante sur RunComfy — cette compétence est un routeur intelligent qui associe l'intention de l'utilisateur au bon modèle d'édition dans le catalogue RunComfy. Sélectionne Wan 2.7 Edit-Video (restylage général / échange d'arrière-plan / échange d'emballage, préservation de l'identité et du mouvement), Kling 2.6 Pro Motion Control (transférer un mouvement précis d'une vidéo de référence à un personnage cible), ou Lucy Edit Restyle (restylage léger avec préservation de l'identité / échange de tenue). Regroupe les schémas de sollicitation documentés de chaque modèle afin que la compétence...

Modifier une vidéo existante sur RunComfy — cette compétence est un routeur intelligent qui associe l'intention de l'utilisateur au bon modèle d'édition dans le catalogue RunComfy. Sélectionne Wan 2.7 Edit-Video (restylage général / échange d'arrière-plan / échange d'emballage, préservation de l'identité et du mouvement), Kling 2.6 Pro Motion Control (transférer un mouvement précis d'une vidéo de référence à un personnage cible), ou Lucy Edit Restyle (restylage léger avec préservation de l'identité / échange de tenue). Regroupe les schémas de sollicitation documentés de chaque modèle afin que la compétence...

Modifier une vidéo existante sur RunComfy — cette compétence est un routeur intelligent qui associe l'intention de l'utilisateur au bon modèle d'édition dans le catalogue RunComfy. Sélectionne Wan 2.7 Edit-Video (restylage général / échange d'arrière-plan / échange d'emballage, préservation de l'identité et du mouvement), Kling 2.6 Pro Motion Control (transférer un mouvement précis d'une vidéo de référence à un personnage cible), ou Lucy Edit Restyle (restylage léger avec préservation de l'identité / échange de tenue). Regroupe les schémas de sollicitation documentés de chaque modèle afin que la compétence...

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend...

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend...

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend...

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven,...

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven,...

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven,...

We need to translate the given text from English to French. The text describes a video outpainting skill. We must preserve the name "video-outpainting" but it's not in the text; the text mentions "video outpainting" and "video outpainting" as terms. The instruction says: "Do not include the name unless it appears in the source text." The name "video-outpainting" is not in the source text, so we don't include it. The source text has "Video outpainting" at the beginning. We translate that. We need to translate the entire text inside <text> tags. Keep technical terms like "RunComfy", "runcomfy CLI", "Wan 2-7 edit-video", "ComfyUI", "hero delivery" etc. Preserve URLs? None. Numbers: 9:16, 16:9. Also "outpainting" is a technical term, likely kept as is or translated? In French, "outpainting" is often used as is, but sometimes

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), add environment beyond the original frame while preserving the central action. Routes prompt-shaped spatial extension through Wan 2-7 edit-video and points the agent at dedicated ComfyUI outpaint workflows when seam quality matters for hero delivery. Triggers on "video outpaint", "video outpainting", "extend video canvas", "expand...

We need to translate the given text from English to French. The text describes a video outpainting skill. We must preserve the name "video-outpainting" but it's not in the text; the text mentions "Video outpainting" at the start. We should translate that as "Video outpainting" is a term, but we can translate it as "Extension vidéo" or keep "Video outpainting"? The instruction says preserve product names, protocol names, URLs, numbers, technical terms. "Video outpainting" is a technical term, so likely keep as is or translate? The name to preserve is "video-outpainting" (lowercase with hyphen). In the text it's "Video outpainting" (capitalized). I think we should keep it as "Video outpainting" because it's a technical term. But the instruction says "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "video-outpainting" does not appear in the source text; the source

Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven lip-sync via `audio_url`, smoother transitions, prompt expansion), the duration / resolution / aspect-ratio schema, and when to route to HappyHorse 1.0 / Seedance 2.0 / Kling / LTX 2 instead. Calls `runcomfy run wan-ai/wan-2-7/text-to-video` through the local RunComfy CLI. Triggers on "wan", "wan 2.7", "wan-2-7", "wan video", or any...

We need to translate the given text from English to French, preserving the name "wan-2-7" and other technical terms. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "wan-2-7" appears in the source text, so we keep it as is. Also preserve "RunComfy", "Wan-AI", "HappyHorse 1.0", "Seedance 2.0", "Kling", "LTX 2", "runcomfy run wan-ai/wan-2-7/text-to-video", "CLI", and URLs or technical terms. The text is a description of an agent skill. We need to output only the translation, no extra commentary. Let's translate paragraph by paragraph. Original: "Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven lip-sync

Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven lip-sync via `audio_url`, smoother transitions, prompt expansion), the duration / resolution / aspect-ratio schema, and when to route to HappyHorse 1.0 / Seedance 2.0 / Kling / LTX 2 instead. Calls `runcomfy run wan-ai/wan-2-7/text-to-video` through the local RunComfy CLI. Triggers on "wan", "wan 2.7", "wan-2-7", "wan video", or any...

Regarder une vidéo (URL ou chemin local). Télécharge avec yt-dlp, extrait les images automatiquement redimensionnées avec ffmpeg, récupère la transcription des sous-titres (ou via l'API Whisper en solution de repli), et transmet le résultat à Claude pour qu'il puisse répondre à des questions sur le contenu de la vidéo.