Skills Doany Ai

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...

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on...

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...

We need to translate the given text from English to Russian, preserving the name 'face-swap' and other technical terms like 'runcomfy', 'Wan 2-2 Animate', 'GPT Image 2 Edit', etc. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. Also, do not include the name unless it appears in the source text. The name 'face-swap' appears in the first sentence? Actually the text starts with "Swap a face / character..." but the name 'face-swap' is given as the item name, but it's not in the text. The instruction says "Do not include the name unless it appears in the source text." So we should not add 'face-swap' to the translation. The text itself does not contain 'face-swap' as a word; it says "Swap a face / character". So we translate that. We need to translate the entire text inside <text>. Keep technical terms in English. Translate the rest naturally. Let's break it down:

Генерируйте изображения с помощью Flux 2 Klein (дистиллированного быстрого варианта Flux 2 от Black Forest Labs) на RunComfy — в комплекте с документированными паттернами промптов модели, благодаря чему навык выдает более качественные результаты, чем наивный промптинг той же модели. Описывает сильные стороны Flux 2 Klein (субсекундная задержка, мультиреференсный брендовый стиль, декларативные промпты с приоритетом субъекта), стратегию количества шагов (4–8 для быстрой итерации, ~25 для полировки), компромисс между вариантами 9B и 4B, а также когда перенаправлять на Flux 2 Pro /...

Редактируйте изображения с помощью Flux 1 Kontext Pro (точной модели локального редактирования изображений от Black Forest Labs) на RunComfy — в комплекте с документированными шаблонами промптов модели, благодаря чему навык выдает более точные результаты, чем наивный промптинг той же модели. Документирует сильные стороны Flux Kontext (точные локальные правки по одному референсу, сильный контроль промпта, стабильно высокая точность результатов), схему (одно изображение + промпт), а также когда переключаться на Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein. Вызывает...

We need to translate the given text from English to Russian, preserving the name "gpt-image-2" and other technical terms. The text describes an agent skill for generating and editing images with OpenAI GPT Image 2 on RunComfy. It mentions strengths, sizes, edit language, routing to siblings, CLI commands, and trigger phrases. We must not add any extra commentary, labels, or formatting. Just the translation. Let's translate carefully: "Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy." -> "Создавайте и редактируйте изображения с помощью OpenAI GPT Image 2 (ChatGPT Images 2.0) на 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." -> "Документирует сильные стороны GPT Image 2 (

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...

Генерируйте текст в видео с помощью HappyHorse 1.0 на RunComfy. Описывает сильные стороны HappyHorse 1.0 (#1 в Artificial Analysis Video Arena, нативное 1080p

Редактируйте изображения на RunComfy — этот навык является интеллектуальным маршрутизатором, который сопоставляет намерение пользователя с подходящей моделью редактирования в каталоге RunComfy. Выбирает Nano Banana Edit (пакетная обработка до 20 изображений, сохранение идентичности по умолчанию), OpenAI GPT Image 2 Edit (многоязычное переписывание текста внутри изображения, многокомпонентная композиция, точность макета), Flux Kontext Pro (локальное редактирование с высокой точностью по одному референсу) или Z-Image Turbo Inpaint (точное редактирование области по маске). Включает задокументированные шаблоны подсказок для каждой модели, чтобы навык получал...

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...

We need to translate the given text from English to Russian, preserving the specified name "image-outpainting" 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 "image-outpainting" appears in the source text? Actually, the source text starts with "Image outpainting on RunComfy..." so "image-outpainting" is not explicitly written as a name; it's "Image outpainting" as a phrase. But the instruction says "Name to preserve: image-outpainting" - that likely means the skill name is "image-outpainting" and we should preserve it if it appears. In the source, it's "Image outpainting" (capitalized). Probably we should keep it as "image-outpainting" or as it appears? The instruction says "Do not include the name unless it appears in the source text." It appears as "Image outpainting" - so we should preserve that exact form? But the name given

We need to translate the given text from English to Russian, preserving the specified name "image-to-video" (though it's not in the text, but the instruction says to preserve it if it appears; it doesn't appear, so ignore). Also preserve product names: RunComfy, HappyHorse 1.0 I2V, Wan 2.7, Seedance 2.0 Pro, Arena #1, and technical terms like i2v, audio_url, multi-modal, prompting patterns. Also preserve URLs? None. Numbers: 1.0, 2.7, 2.0, #1. Do not add any extra commentary or labels. Translate the text inside <text> only. 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

Генерация видео Kling 3.0 на RunComfy. Kling 3.0 (также известный как Kling V3.0) — это третье поколение мультикадровой видеомодели от Kuaishou Technology с нативным синхронизированным звуком и единой идентичностью персонажа между кадрами. Этот навык охватывает все шесть конечных точек Kling 3.0, охватывающих три уровня рендеринга (Standard, Pro, 4K) и два режима (текст-в-видео, изображение-в-видео). Вызовы runcomfy run kling/kling-3.0/ / через локальный CLI RunComfy. Срабатывает по запросам "kling", "kling 3.0", "kling v3", "kling pro",...

We need to translate the given text from English to Russian, preserving the specified 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 source text. The name "lipsync" appears in the source text as "Lip-sync" at the beginning, so we should translate that as "Липсинк" or keep as "lipsync"? The instruction says "Name to preserve: lipsync" meaning we should preserve the name as is. But in the source it's "Lip-sync" with hyphen and capital L. Probably we should keep it as "lipsync" (lowercase) as per the preserved name? However, the instruction says "Do not include the name unless it appears in the source text." It does appear

Генерируйте изображения с помощью Google Nano Banana 2 (текст-в-изображение уровня flash семейства Gemini) на RunComfy — навык включает документированные паттерны промптинга модели, что обеспечивает более точный результат по сравнению с наивным промптингом той же модели. Описывает сильные стороны Nano Banana 2 (быстрая итерация, рендеринг типографики внутри изображения, предсказуемое кадрирование, опциональный веб-контекст), ценообразование по уровням разрешения, регулятор толерантности к безопасности, а также случаи, когда следует переключаться на Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream...

Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to 20 inputs), the schema, and when to route to GPT Image 2 edit / Flux Kontext / Nano Banana 2 t2i instead. Calls `runcomfy run google/nano-banana-2/edit` through the local RunComfy CLI. Triggers on "nano banana edit", "edit with nano banana", "image edit nano...

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....

Запускайте любые модели на RunComfy из

Генерируйте кинематографичные короткие видео с помощью ByteDance Seedance 2.0 Pro на RunComfy. Описывает сильные стороны Seedance 2.0 Pro (мультимодальные референсы — до 9 изображений, 3 видео, 3 аудио — синхронизированное встроенное аудио с естественной синхронизацией губ, кинематографическое уточнение движения), схему длительности 4–15 секунд и когда перенаправлять на HappyHorse 1.0 / Wan 2.7 /

Редактирование существующего видео на RunComfy — этот навык является интеллектуальным маршрутизатором, который сопоставляет намерение пользователя с подходящей моделью редактирования в каталоге RunComfy. Выбирает Wan 2.7 Edit-Video (общий рестайлинг / замена фона / замена упаковки, сохранение идентичности и движения), Kling 2.6 Pro Motion Control (перенос точного движения из эталонного видео на целевого персонажа) или Lucy Edit Restyle (легкий рестайлинг с сохранением идентичности / замена одежды). Объединяет задокументированные шаблоны подсказок каждой модели, чтобы навык...

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...

We need to translate the given text from English to Russian, preserving the specified name "video-inpainting" (though it's not in the text, so ignore). Also preserve product names, protocol names, URLs, numbers, technical terms. The text describes region edits across video frames using various tools. Translate naturally. Key terms: "Region edits across video frames" -> "Редактирование областей в видеокадрах", "RunComfy" (preserve), "runcomfy CLI" (preserve), "remove an object" -> "удалить объект", "clean up wires or watermarks" -> "очистить провода или водяные знаки", "replace a region with matching motion" -> "заменить область с соответствующим движением", "Routes across" -> "Маршруты через", "Wan 2-7 edit-video" (preserve), "prompt-driven region edits with spatial language" -> "редактирование областей на основе подсказок с пространственным языком", "Lucy

We need to translate the given text from English to Russian, preserving the name "video-outpainting" and other technical terms. The text describes a video outpainting skill on RunComfy via CLI. We must not include the name unless it appears in the source text. The source text includes "video-outpainting" as part of the directory item type? Actually the instruction says "Name to preserve: video-outpainting" but the text inside <text> does not contain that exact string? Wait, the text inside <text> starts with "Video outpainting on RunComfy..." so "Video outpainting" appears. The name to preserve is "video-outpainting" (with hyphen). The source text has "Video outpainting" (space). We should preserve the exact name as given? The instruction says "Name to preserve: video-outpainting" but the source text uses "Video outpainting". Possibly we should keep the hyphenated version if it appears? But it doesn't appear. The instruction says "Do not include the name unless

Генерируйте текст-в-видео с помощью Wan 2.7 (флагманской модели движения от Wan-AI) на RunComfy. Описывает сильные стороны Wan 2.7 (много