Medien Skills

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...

Erstellen Sie Videos mit ByteDance Seedance 2.0 über die inference.sh CLI. Einheitliches Modell für Text-zu-Video, Bild-zu-Video und Referenz-zu-Video mit synchronisiertem Audio, bis zu 1080p, 4-15s Dauer. Pro- und Fast-Varianten. Studio-Varianten mit privater Asset-Bibliothek für Porträtkonsistenz. Verwendung für: Social-Media-Videos, Musikvideos, Produktdemos, animierte Inhalte, KI-Video mit Ton. Auslöser: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio,...

Erstellen Sie Videos mit ByteDance Seedance 2.0 über die inference.sh CLI. Einheitliches Modell für Text-zu-Video, Bild-zu-Video und Referenz-zu-Video mit synchronisiertem Audio, bis zu 1080p, 4-15s Dauer. Pro- und Fast-Varianten. Studio-Varianten mit privater Asset-Bibliothek für Porträtkonsistenz. Verwendung für: Social-Media-Videos, Musikvideos, Produktdemos, animierte Inhalte, KI-Video mit Ton. Auslöser: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio,...

We need to translate the given text from English to German. 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. Preserve: "seedance-v2" (name to preserve), but note instruction: "Do not include the name unless it appears in the source text." The name "seedance-v2" appears in the source text as part of the CLI command "bytedance/seedance-v2/pro". So we should preserve that exact string. Also preserve "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "runcomfy run bytedance/seedance-v2/pro", "seedance", "seedance 2", "seedance v2", "seedance..." (the last is truncated). Also preserve numbers, URLs (none), technical terms.

We need to translate the given text from English to German. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions strengths, duration schema, routing alternatives, and CLI command. The name "seedance-v2" is to be preserved, but it appears in the text as "seedance-v2" in the CLI command. Also "Seedance 2.0 Pro" and "RunComfy" are product names to preserve. The text inside <text> is to be translated, but we must not include the name unless it appears in source. The name "seedance-v2" appears in the source as part of the CLI command, so we should keep it as is. Also "HappyHorse 1.0", "Wan 2.7", "Kling" are product names to preserve. The translation should be natural German, preserving technical terms and URLs (none here). The text ends with "seedance..." which is incomplete; we should translate that as is.

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...

We need to translate the given text from English to German. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions strengths, duration schema, routing alternatives, and CLI command. The name "seedance-v2" is to be preserved, but it appears in the text as "seedance-v2" in the CLI command. Also "Seedance 2.0 Pro" and "RunComfy" are product names to preserve. The text inside <text> is to be translated, but we must not include the name unless it appears in source. The name "seedance-v2" appears in the source as part of the CLI command, so we should keep it as is. Also "HappyHorse 1.0", "Wan 2.7", "Kling" are product names to preserve. "ByteDance" is a company name. "CLI" is an acronym. "lip-sync" is a technical term. "multi-modal references" might be

Film- und Videostoryboarding mit Aufnahmevokabular, Kontinuitätsregeln und Panel-Layout. Behandelt Aufnahmearten, Kamerawinkel, Bewegung, 180-Grad-Regel und Annotationsformat. Verwendung für: Videoplanung, Filmvorproduktion, Werbestoryboards, Musikvideoplanung, Animation. Auslöser: storyboard, storyboarding, shot list, film planning, video planning, pre production, shot composition, camera angles, scene planning, visual script, animatic, storyboard panels, video storyboard

Film- und Video-Storyboarding mit Aufnahmevokabular, Kontinuitätsregeln und Panel-Layout. Umfasst Aufnahmetypen, Kamerawinkel, Bewegung, 180-Grad-Regel und Annotationsformat. Verwendung für: Videoplanung, Filmvorproduktion, Werbe-Storyboards, Musikvideoplanung

Film- und Videostoryboarding mit Aufnahmevokabular, Kontinuitätsregeln und Panel-Layout. Behandelt Aufnahmearten, Kamerawinkel, Bewegung, 180-Grad-Regel und Annotationsformat. Verwendung für: Videoplanung, Filmvorproduktion, Werbestoryboards, Musikvideoplanung, Animation. Auslöser: storyboard, storyboarding, shot list, film planning, video planning, pre production, shot composition, camera angles, scene planning, visual script, animatic, storyboard panels, video storyboard

Erstellen Sie eine Lottie (Bodymovin) JSON-Animation, die in einem lokalen Skia-Player gerendert wird. Verwenden Sie dies immer dann, wenn der Benutzer darum bittet, eine Lottie-Animation zu erstellen, generieren, bearbeiten oder reparieren, oder nach "einer Animation" zum Laden fragt.

Wenn der Benutzer Videoinhalte mit KI-Tools oder programmatischen Frameworks erstellen, generieren oder produzieren möchte. Auch verwenden, wenn der Benutzer 'Videoproduktion', 'KI-Video', 'Remotion', 'Hyperframes', 'HeyGen', 'Synthesia', 'Veo', 'Sora', 'Runway', 'Kling', 'Seedance', 'Hailuo', 'MiniMax', 'Pika', 'Hunyuan', 'Wan', 'Videogenerierung', 'KI-Avatar', 'Sprecherkopf-Video', 'programmatisches Video', 'Video-Vorlage', 'Erklärvideo', 'Produktdemo-Video', 'Video-Pipeline' oder 'mach mir ein Video' erwähnt. Verwenden...

Vorhandenes Video auf RunComfy bearbeiten – diese Fähigkeit ist ein intelligenter Router, der die Absicht des Benutzers mit dem richtigen Bearbeitungsmodell im RunComfy-Katalog abgleicht. Wählt Wan 2.7 Edit-Video (allgemeines Restyling / Hintergrundtausch / Verpackungstausch, Identitäts- und Bewegungserhaltung), Kling 2.6 Pro Motion Control (präzise Bewegungsübertragung von einem Referenzvideo auf eine Zielperson) oder Lucy Edit Restyle (leichtgewichtiges, identitätsstabiles Restyling / Outfitwechsel). Bündelt die dokumentierten Eingabeaufforderungsmuster jedes Modells, sodass die Fähigkeit...

Vorhandenes Video auf RunComfy bearbeiten – diese Fähigkeit ist ein intelligenter Router, der die Absicht des Benutzers mit dem richtigen Bearbeitungsmodell im RunComfy-Katalog abgleicht. Wählt Wan 2.7 Edit-Video (allgemeines Restyling / Hintergrundtausch / Verpackungstausch, Identitäts- und Bewegungserhaltung), Kling 2.6 Pro Motion Control (präzise Bewegungsübertragung von einem Referenzvideo auf eine Zielperson) oder Lucy Edit Restyle (leichtgewichtiges, identitätsstabiles Restyling / Outfitwechsel). Bündelt die dokumentierten Prompt-Muster jedes Modells, sodass die Fähigkeit...

Vorhandenes Video auf RunComfy bearbeiten – diese Fähigkeit ist ein intelligenter Router, der die Absicht des Benutzers mit dem richtigen Bearbeitungsmodell im RunComfy-Katalog abgleicht. Wählt Wan 2.7 Edit-Video (allgemeines Restyling / Hintergrundtausch / Verpackungstausch, Identitäts- und Bewegungserhaltung), Kling 2.6 Pro Motion Control (präzise Bewegungsübertragung von einem Referenzvideo auf eine Zielperson) oder Lucy Edit Restyle (leichtgewichtiges, identitätsstabiles Restyling / Outfitwechsel). Bündelt die dokumentierten Prompting-Muster jedes Modells, sodass die Fähigkeit...

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 German. 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" does not appear in the source text; only "video outpainting" (without hyphen) appears. So we should not add the hyphenated version. We translate the text inside <text> only. We need to preserve product names, protocol names, URLs, numbers, technical terms. "RunComfy", "runcomfy CLI", "Wan 2-7 edit-video", "ComfyUI" are proper names/technical terms. "9:16", "16:9" are numbers/aspect ratios. "hero delivery" might be a term? Possibly keep as is or translate? "hero delivery" likely refers to main subject delivery

We need to translate the given text from English to German. 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" does not appear in the source text; only "video outpainting" (without hyphen) appears. So we should not add the hyphenated version. We translate the text inside <text> only. We need to preserve product names, protocol names, URLs, numbers, technical terms. "RunComfy", "runcomfy", "Wan 2-7 edit-video", "ComfyUI" are proper names/technical terms. "9:16", "16:9" are numbers/aspect ratios. "CLI" is a technical term. We translate the rest naturally. The text: "Video outpainting on RunComfy

We need to translate the given text from English to German. The text describes a video outpainting skill. We must preserve the name "video-outpainting" but it's not in the text; the text has "video outpainting" (lowercase, no hyphen). The instruction says "Do not include the name unless it appears in the source text." The source text has "video outpainting" (two words) and "video outpainting" again. So we keep that as is? Actually the name to preserve is "video-outpainting" with hyphen, but the source uses "video outpainting" without hyphen. We should translate the text, but keep technical terms like "RunComfy", "runcomfy CLI", "Wan 2-7 edit-video", "ComfyUI", "hero delivery" etc. Also preserve URLs? None. Numbers: 9:16, 16:9. Also "outpaint" is a term, likely keep as is or translate? "Outpainting" is often used in

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...

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...

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...

Ein Video ansehen (URL oder lokaler Pfad). Lädt mit yt-dlp herunter, extrahiert automatisch skalierte Frames mit ffmpeg, zieht das Transkript aus Untertiteln (oder Whisper-API-Fallback) und übergibt das Ergebnis an Claude, damit es Fragen zum Videoinhalt beantworten kann.