Runcomfy Com Skills

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step...

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced...

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits,...

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right...

Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1...

We need to translate the given text from English to German. The text describes a Codex Pet generator skill. We must preserve the name "codex-pet" but it's not in the text, so ignore. Preserve product names: Codex, RunComfy, OpenAI GPT Image 2. Preserve technical terms: spritesheet.webp, pet.json, ${CODEX_HOME:-$HOME/.codex}/pets/ /, 1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states, idle, running-right, running-left, waving, jumping, failed, waiting, running, review. Also preserve URLs? None. Numbers and technical terms. Translate the rest naturally. The text is a description of what the skill does. Output only the translation, no extra commentary. Let me translate: "Codex Pet Generator auf RunComfy. Erstelle ein Codex-kompatibles Codex Pet Spritesheet.webp + pet.json aus einem einzelnen Referenzbild,

We need to translate the given English text into German. The text describes a pose-conditioned generation system on RunComfy via CLI. It mentions routes across Kling 2-6 Motion Control Pro/Standard, community Wan 2-2 Animate, and Z-Image Turbo ControlNet LoRA. It picks the right route based on video vs still and stylized vs photoreal. Ends with "Triggers on..." which is incomplete. We must preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "runcomfy CLI", "Kling 2-6 Motion Control Pro / Standard", "Wan 2-2 Animate", "Z-Image Turbo ControlNet LoRA", "OpenPose", "DWPose", "canny", "depth control image" should remain as is. Also "pose-conditioned generation" is a technical term, but we can translate "generation" to "Generierung" but keep "pose-conditioned" as "posengesteuert" or "pose-kond

Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy via the `runcomfy` CLI. ElevenLabs Music turns a style description plus structured lyrics into studio-quality 44.1 kHz stereo audio — 5 seconds to 5 minutes — with section-level control (Intro / Verse / Chorus / Bridge), multilingual vocals, and commercial-friendly output. Generate a backing track, a full vocal song, a jingle, a podcast intro, a game loop, or an instrumental bed. Calls `runcomfy run...

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for...

Generiere Bilder mit Flux 2 Klein (Black Forest Labs' destillierte schnelle Variante von Flux 2) auf RunComfy – gebündelt mit den dokumentierten Prompting-Mustern des Modells, sodass der Skill schärfere Ergebnisse liefert als naives Prompting mit demselben Modell. Dokumentiert die Stärken von Flux 2 Klein (Latenz unter einer Sekunde, Multi-Referenz-Markenstyling, deklarative Subjekt-zuerst-Prompts), die Schrittanzahl-Strategie (4–8 für schnelle Iteration, ~25 für Verfeinerung), den Trade-off zwischen der 9B- und 4B-Variante sowie die Entscheidung, wann zu Flux 2 Pro /... weitergeleitet werden sollte.

Bilder mit Flux 1 Kontext Pro (Black Forest Labs' präzises lokales Bildbearbeitungsmodell) auf RunComfy bearbeiten – gebündelt mit den dokumentierten Prompting-Mustern des Modells, sodass die Fertigkeit schärfere Ergebnisse liefert als naives Prompting mit demselben Modell. Dokumentiert die Stärken von Flux Kontext (präzise lokale Bearbeitungen mit einer Referenz, starke Prompt-Kontrolle, konsistente hochtreue Ausgaben), das Schema (einzelnes Bild + Prompt) und wann stattdessen zu Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein weitergeleitet werden sollte. Ruft...

We need to translate the given text from English to German, preserving the name "gpt-image-2" 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 "gpt-image-2" appears in the source text, so it should be preserved. Also preserve "RunComfy", "Flux 2", "Nano Banana Pro", "Seedream", "CLI", "openai/gpt-image-2/text-to-image", "/edit", etc. The text is a description of an agent skill. Translate naturally to German. Let's break down the source: "Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls

Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls...

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse...

Bilder auf RunComfy bearbeiten – diese Fertigkeit ist ein intelligenter Router, der die Absicht des Nutzers mit dem passenden Bearbeitungsmodell im RunComfy-Katalog abgleicht. Wählt Nano Banana Edit (Stapelverarbeitung bis zu 20, standardmäßig identitätserhaltend), OpenAI GPT Image 2 Edit (mehrsprachige Textumschreibung im Bild, Multi-Referenz-Komposition, Layout-Präzision), Flux Kontext Pro (Einzel-Referenz, hochgetreue lokale Bearbeitung) oder Z-Image Turbo Inpaint (maskengesteuerte präzise Bereichsbearbeitung). Bündelt die dokumentierten Eingabeaufforderungsmuster jedes Modells, sodass die Fertigkeit...

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...

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...

We need to translate the given text from English to German. The text describes a skill called "image-to-video" but the instruction says not to include the name unless it appears in the source text. The name "image-to-video" does appear in the source? Actually, the source text starts with "Animate any still image on RunComfy — this skill is a smart router..." The name "image-to-video" is not explicitly in the source text; it's given as the name to preserve but not to include unless in source. So we just translate the text inside <text>. 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" should remain as is. Also "i2v" is a technical term, keep as is. "native audio", "identity preservation", "custom-voiceover lip-sync",

Kling 3.0 Videogenerierung auf RunComfy. Kling 3.0 (auch Kling V3.0 genannt) ist das Multi-Shot-Videomodell der dritten Generation von Kuaishou Technology mit nativem synchronisiertem Audio und konsistenter Charakteridentität über mehrere Aufnahmen hinweg. Diese Fähigkeit deckt alle sechs Kling 3.0-Endpunkte ab, die drei Rendering-Stufen (Standard, Pro, 4K) und zwei Modi (Text-zu-Video, Bild-zu-Video) umfassen. Aufrufe erfolgen über runcomfy run kling/kling-3.0/ / über die lokale RunComfy-CLI. Auslöser sind "kling", "kling 3.0", "kling v3", "kling pro",...

We need to translate the given English text into German, preserving the specified name "lipsync" 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 "lipsync" appears in the source text as "Lip-sync" at the beginning. So we should translate that as "Lippensynchronisation" or similar? But the instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "lipsync" is a technical term, but it's also the name of the skill. The instruction says "Name to preserve: lipsync". So we should keep "lipsync" as is? However, the source text has "Lip-sync" (capitalized, hyphenated). The instruction says "Do not include the name unless it appears in the source text." It does appear. So we should preserve the exact form? But the instruction says "Name to preserve: lipsync" (lowercase, no hyphen). Possibly

Generiere Bilder mit Google Nano Banana 2 (Gemini-Familie Flash-Stufe Text-zu-Bild) auf RunComfy – gebündelt mit den dokumentierten Prompting-Mustern des Modells, sodass der Skill schärfere Ergebnisse liefert als naives Prompting mit demselben Modell. Dokumentiert die Stärken von Nano Banana 2 (schnelle Iteration, In-Bild-Typografie-Rendering, vorhersagbarer Bildausschnitt, optionaler webgestützter Kontext), die Preisgestaltung nach Auflösungsstufen, den Sicherheitstoleranz-Regler und wann an Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream weitergeleitet werden sollte...

We need to translate the given text from English to German. The text describes an agent skill for editing images using Google Nano Banana 2 on RunComfy. We must preserve the name "nano-banana-edit" as per instruction, but the name is not inside the <text> tag? Actually the instruction says "Name to preserve: nano-banana-edit" but the text inside <text> does not contain that exact name. It contains "Nano Banana Edit" and "nano banana edit" etc. We should preserve those as they appear, but not add the name if not present. The instruction says "Do not include the name unless it appears in the source text." So we only translate the text inside <text>. We need to translate the description, keeping product names like "Google Nano Banana 2", "RunComfy", "Nano Banana Edit", "GPT Image 2 edit", "Flux Kontext", "Nano Banana 2 t2i", "runcomfy run google/nano-banana-2/edit", "RunCom

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....

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...

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

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...

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 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...