Skills Video

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...

Buat video AI avatar dan talking head melalui CLI inference.sh. Rekomendasi: P-Video-Avatar (tercepat, termurah, TTS bawaan). Juga: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ bahasa, pengaturan emosi untuk karakter), ElevenLabs, Kokoro. Kemampuan: avatar berbasis audio, teks-ke-avatar, video lipsync, pembuatan talking head, presenter virtual, konten UGC. Gunakan untuk: presenter AI, video penjelasan, influencer virtual, dubbing, video pemasaran, iklan UGC, avatar game,...

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...

Buat video AI avatar, talking-head, dan lip-sync di RunCom

We need to translate the given text from English to Bahasa Indonesia. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. So names like "P-Video-Avatar", "OmniHuman", "Fabric", "PixVerse", "Inworld TTS-2", "ElevenLabs", "Kokoro", "CLI", "TTS", "UGC" should remain unchanged. Also "inference.sh" is a URL-like name, preserve. The text inside <text> is a description. We translate the rest naturally. The text: "Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC

Buat video AI avatar dan talking head melalui CLI inference.sh. Rekomendasi: P-Video-Avatar (tercepat, termurah, TTS bawaan). Juga: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ bahasa, pengaturan emosi untuk karakter), ElevenLabs, Kokoro. Kemampuan: avatar berbasis audio, teks-ke-avatar, video lipsync, generasi talking head, presenter virtual, konten UGC. Gunakan untuk: presenter AI, video penjelasan, influencer virtual, dubbing, video pemasaran, iklan UGC, avatar game,...

Hasilkan video AI dengan Google Veo, Seedance 2.0, HappyHorse, Wan, Grok dan 40+ model melalui CLI inference.sh. Model: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Kemampuan: teks-ke-video, gambar-ke-video, referensi-ke-video, pengeditan video, lipsync, animasi avatar, peningkatan resolusi video, suara foley. Gunakan untuk: video media sosial, konten pemasaran, video penjelasan, demo produk, avatar AI. Pemicu: pembuatan video, video AI,...

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...

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...

Hasilkan video AI dengan Google Veo, Seedance 2.0, HappyHorse, Wan, Grok dan 40+ model melalui CLI inference.sh. Model: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Kemampuan: teks-ke-video, gambar-ke-video, referensi-ke-video, pengeditan video, lipsync, animasi avatar, peningkatan resolusi video, suara foley. Gunakan untuk: video media sosial, konten pemasaran, video penjelasan, demo produk, avatar AI. Pemicu: pembuatan video, video AI,...

Hasilkan video AI dengan Google Veo, Seedance 2.0, HappyHorse, Wan, Grok dan 40+ model melalui CLI inference.sh. Model: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Kemampuan: teks-ke-video, gambar-ke-video, referensi-ke-video, pengeditan video, lipsync, animasi avatar, peningkatan resolusi video, suara foley. Gunakan untuk: video media sosial, konten pemasaran, video penjelasan, demo produk, avatar AI. Pemicu: pembuatan video, video AI,...

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...

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...

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...

dontbesilent 短视频开头优化。诊断开头问题 + 生成优化方案。 触发方式：/dbs-hook、/hook、「帮我优化开头」「开头怎么写」 Optimasi pembukaan video pendek dengan diagnosis dan solusi. Pemicu: /dbs-hook, "optimalkan pembukaan saya", "bagaimana cara menulis pembukaan

短视频逐字稿逻辑延续检查。找出「观众会在哪一秒划走」的风险点：段落间逻辑衔接、段落内信息密度、句子口播流畅度。诊断完默认主动问是否标记式改稿。 触发方式：/dbs-script-flow、/逻辑延续、「检查逻辑延续」「看看逻辑有没有断」「帮我看看这个稿子顺不顺」「哪里会划走」

Tambahkan teks ke video wajah yang berbicara. SATU katalog (CATALOG.md) dari 32 identitas visual di balik dua mesin: column-flow (teks dikomposit ke DALAM adegan — oklusi matte + campuran campuran; cream/ink/editorial/keynote/documentary/loud/neon/glitch/chrome/velocity) dan konstitusi bertema (anchor/ordnance/terminal/neonsign/stardust/stomp/scoreboard/transit/vhs/arcade/dossier/laser/thunder/hologram/biolume/aurora/spectrum/papercut/popup/chalkboard/graffiti/brush/inkwater/ransom/lastpage/nightcity...

Dukungan kamera web.

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...

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...

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...

alur kerja video faceless-explainer - teks arbitrer (artikel / catatan / topik / ringkasan) -> narrator_scripts.json + audio (suara + BGM) + section_plan.md -> video tipografi / grafik abstrak / diagram / visualisasi data. Durasi tipikal hingga ~3 menit (titik optimal ~30-90 detik); konten yang benar-benar lebih panjang adalah video umum, bukan alur kerja ini. Menghasilkan narasi (TTS) sendiri — tidak menyinkronkan dengan sulih suara yang disediakan/direkam pengguna (itu adalah video umum). Tidak ada tangkapan layar situs web, tidak ada tangkapan layar produk asli....

Gunakan sebagai cadangan untuk pembuatan komposisi video HTML HyperFrames kustom ketika tidak ada alur kerja khusus yang cocok. Mencakup potongan panjang atau multi-adegan, reel merek/sizzle, montase, kartu judul, poster gerak dengan durasi panjang, loop statis, dan komposisi bebas dalam format atau panjang apa pun. Bukan untuk promosi produk yang dipasarkan (product-launch-video), tangkapan video dari situs web umum (website-to-video), penjelas topik (faceless-explainer), video PR GitHub (pr-to-video), pemberian teks pada rekaman yang sudah ada...

Kemas video wawancara / podcast / talking-head yang sudah ada dengan melapisi kartu GRAPHIC OVERLAY yang diatur waktunya dan dirancang ke dalam video yang sedang diputar — judul, lower-thirds, data callout, kutipan, panel samping, picture-in-picture — yang disinkronkan dengan transkrip. Video sumber diputar sepenuhnya; agen merancang dan menulis HTML setiap kartu dalam percakapan, lalu merender ke MP4 melalui hyperframes. Gunakan saat pengguna meminta graphic overlay, grafik di layar / lower-thirds / data callout / judul kinetik pada video,...

Hasilkan dan edit video menggunakan model Alibaba HappyHorse 1.0 melalui CLI inference.sh. Model: HappyHorse T2V, I2V, R2V, Video Edit. Kemampuan: teks-ke-video, gambar-ke-video, referensi-ke-video, pengeditan video dengan bahasa alami, pelestarian karakter, 720P/1080P, hingga 15 detik. Gunakan untuk: video realistis secara fisik, pengeditan video, konten konsisten karakter, demo produk, media sosial. Pemicu: happyhorse, happy horse, alibaba video, happyhorse 1.0, dashscope video, alibaba...

Hasilkan dan edit video dengan model Alibaba HappyHorse 1.0 melalui CLI inference.sh. Model: HappyHorse T2V, I2V, R2V, Video Edit. Kemampuan: teks-ke-video, gambar-ke-video, referensi-ke-video, pengeditan video dengan bahasa alami, pelestarian karakter, 720P/1080P, hingga 15 detik. Gunakan untuk: video realistis secara fisik, pengeditan video, konten konsisten karakter, demo produk, media sosial. Pemicu: happyhorse, happy horse, alibaba video, happyhorse 1.0, dashscope video, alibaba...

We need to translate the given text from English to Bahasa Indonesia. The text describes a skill for generating text-to-video with HappyHorse 1.0 on RunComfy. It mentions strengths, schema, routing alternatives, and CLI command. The instruction says to preserve product names, protocol names, URLs, numbers, technical terms. So "HappyHorse 1.0", "RunComfy", "Artificial Analysis Video Arena", "1080p", "Wan 2.7", "Seedance 2", "LTX 2", "runcomfy run happyhorse/happyhorse-1-0/text-to-video", "CLI", "happyhorse", "happy horse" should remain as is. Also preserve the name "happyhorse-1-0" if it appears, but it's not in the text except in the command. The text inside <text> is provided. We translate the rest. Let's break down the text: "Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents Happy

We need to translate the given text from English to Bahasa Indonesia. The text is a description of an agent skill for "happyhorse-1-0". We must preserve the name "happyhorse-1-0" and other proper names like "HappyHorse 1.0", "RunComfy", "Artificial Analysis Video Arena", "Wan 2.7", "Seedance 2", "LTX 2", "RunComfy CLI", and the command string. Also preserve numbers, URLs, technical terms. Do not add any extra commentary or labels. The translation should be natural in Indonesian. Let's break down the text: "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

We need to translate the given text from English to Bahasa Indonesia. The text is a description of an agent skill for "happyhorse-1-0". We must preserve the name "happyhorse-1-0" and other proper names like "HappyHorse 1.0", "RunComfy", "Artificial Analysis Video Arena", "Wan 2.7", "Seedance 2", "LTX 2", "RunComfy CLI", and the command string. Also preserve numbers, URLs, technical terms. Do not add any extra commentary or labels. The translation should be natural in Indonesian. Let's break down the text: "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

Hasilkan gambar/video melalui Higgsfield AI. Default: GPT Image 2 untuk gambar/desain/teks, Seedance 2.0 untuk video, Nano Banana 2/Pro untuk pekerjaan karakter/gambar referensi, Marketing Studio untuk iklan dengan avatar/produk/hook, pengaturan, plus Soul V2/Cinema/Cast/Location dan Kling 3.0. Gunakan saat: "buat gambar", "buat video", "animasikan foto ini", "gambar-ke-video", "edit/stylize/remix gambar ini", "hasilkan klip", "buat iklan", "buat video UGC", "demo produk", "unboxing", "video merek",...

We need to translate the given English text into Bahasa Indonesia. The text describes a skill for training a Soul Character. We must preserve the name 'higgsfield-soul-id' if it appears, but it does not appear in the text. The text includes technical terms like 'Soul Character', 'Higgsfield', 'reference_id', 'higgsfield-generate', '--soul-id', 'text2image_soul_v2'. These should be preserved as is. Also preserve numbers, URLs (none), and technical terms. Do not add any extra commentary or labels. Just translate the descriptive text. The text: "Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation. Use when: "create my Soul", "train my face", "make my digital twin", "build me an avatar", "learn my appearance", "create a character of me", "set up identity for video", "I want my face in generated images". Chain: train Soul (one-time, returns reference_id

BACA INI TERLEBIH DAHULU untuk setiap permintaan membuat, mengedit, menganimasikan, atau merender video, animasi, atau grafik gerak — baik itu promo, video penjelas, klip dengan teks, kartu judul, overlay, atau komposisi apa pun. HyperFrames merender video dari HTML; ini adalah skill utama dan cara default agen menulis atau mengedit video. Skill ini mengarahkan permintaan ke alur kerja khusus yang tepat dan menunjuk ke skill domain HyperFrames, jadi bacalah ini sebelum skill video atau animasi lainnya, jangan menebak-nebak alur kerja....

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

Use when a HyperFrames composition needs seek-safe 2D/3D keyframes, GSAP timelines, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.

Prapemrosesan aset untuk komposisi HyperFrames — TTS multi-penyedia (HeyGen / ElevenLabs / Kokoro lokal), BGM multi-penyedia (Google Lyria / MusicGen lokal), transkripsi Whisper, penghapusan latar belakang, dan pembuatan takarir. Gunakan untuk npx hyperframes tts, bgm, transcribe, remove-background, pemilihan suara/penyedia, pengaturan suasana musik, takarir / subtitle / lirik / karaoke / gaya per kata.

Mulailah di sini untuk setiap permintaan membuat, menciptakan, menghasilkan, mengedit, menganimasikan, atau merender video, animasi, grafik gerak, video penjelas, kartu judul, hamparan, video dengan teks, promosi produk, video situs web, video PR atau changelog, montase data, poster gerak, atau komposisi HTML HyperFrames. Gunakan sebelum keterampilan video atau animasi lainnya ketika pengguna ingin HyperFrames menulis atau merender video MP4/web yang sudah jadi, memilih alur kerja, atau merutekan antara video peluncuran produk, video penjelas tanpa wajah, situs web-ke-video,...

We need to translate the given text from English to Bahasa Indonesia. 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 is not explicitly written as "image-to-video" in the source text. The directory item type is "agent skill" and the name to preserve is "image-to-video". But the instruction says: "Do not include the name unless it appears in the source text." The name "image-to-video" does not appear in the source text. So we should not add it. We just translate the text inside <text>. We need to preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "HappyHorse 1.0 I2V", "Arena #1", "Wan 2.7",

We need to translate the given text from English to Bahasa Indonesia. 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 text? 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 text; it's given as the directory item type. The instruction says "Do not include the name unless it appears in the source text." The name does not appear in the source text, so we should not add it. We just translate the text inside <text>. We need to preserve product names: RunComfy, HappyHorse 1.0 I2V, Wan 2.7, Seedance 2.0 Pro, Arena #1, etc. Also preserve technical terms like i2v, audio_url, lip-sync, multi-modal, prompting patterns. URLs? None. Numbers: 1

Panduan konversi gambar-ke-video: pemilihan model, prompt gerakan, dan pergerakan kamera. Mencakup Wan 2.5 i2v, Seedance, Fabric, Grok Video beserta kapan menggunakannya. Gunakan untuk: menganimasikan gambar, membuat video dari gambar diam, menambahkan gerakan, animasi produk. Pemicu: gambar ke video, i2v, animasi gambar, gambar diam ke video, tambahkan gerakan ke gambar, animasi gambar, foto ke video, animasi gambar diam, wan i2v, image2video, hidupkan gambar, animasi foto, gerakan dari gambar

Panduan konversi gambar-ke-video: pemilihan model, prompt gerakan, dan pergerakan kamera. Mencakup Wan 2.5 i2v, Seedance, Fabric, Grok Video dengan kapan menggunakan masing-masing. Gunakan untuk: menganimasikan gambar, membuat video dari gambar diam, menambahkan gerakan, animasi produk. Pemicu: gambar ke video, i2v, animasi gambar, gambar diam ke video, tambahkan gerakan ke gambar, animasi gambar, foto ke video, animasi gambar diam, wan i2v, image2video, hidupkan gambar, animasi foto, gerakan dari gambar

We need to translate the given text from English to Bahasa Indonesia. 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 is not explicitly written as "image-to-video" in the source text. The directory item type is "agent skill" and the name to preserve is "image-to-video". But the instruction says: "Do not include the name unless it appears in the source text." The name "image-to-video" does not appear in the source text. So we should not add it. We just translate the text inside <text>. We need to preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "HappyHorse 1.0 I2V", "Arena #1", "Wan 2.7",

Pembuatan video Kling 3.0 di RunComfy. Kling 3.0 (juga disebut Kling V3.0) adalah model video multi-shot generasi ketiga dari Kuaishou Technology dengan audio sinkron asli dan identitas karakter yang konsisten antar shot. Skill ini mencakup keenam endpoint Kling 3.0, meliputi tiga tingkatan rendering (Standard, Pro, 4K) dan dua mode (teks-ke-video, gambar-ke-video). Panggilan runcomfy run kling/kling-3.0/ / melalui CLI RunComfy lokal. Dipicu oleh "kling", "kling 3.0", "kling v3", "kling pro",...

Pembuatan video Kling 3.0 di RunComfy. Kling 3.0 (juga disebut Kling V3.0) adalah model video multi-shot generasi ketiga dari Kuaishou Technology dengan audio sinkron asli dan identitas karakter yang konsisten antar shot. Skill ini mencakup keenam endpoint Kling 3.0, meliputi tiga tingkatan rendering (Standard, Pro, 4K) dan dua mode (teks-ke-video, gambar-ke-video). Panggilan runcomfy run kling/kling-3.0/ / melalui CLI RunComfy lokal. Dipicu oleh "kling", "kling 3.0", "kling v3", "kling pro",...

Pembuatan video Kling 3.0 di RunComfy. Kling 3.0 (juga disebut Kling V3.0) adalah model video multi-shot generasi ketiga dari Kuaishou Technology dengan audio sinkron asli dan identitas karakter yang konsisten antar shot. Skill ini mencakup keenam endpoint Kling 3.0, mencakup tiga tingkatan rendering (Standard, Pro, 4K) dan dua mode (teks-ke-video, gambar-ke-video). Panggilan runcomfy run kling/kling-3.0/ / melalui CLI RunComfy lokal. Dipicu oleh "kling", "kling 3.0", "kling v3", "kling pro",...

Lip-sync a face to a specific audio track on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar from a portrait + audio), Sync Labs sync v2 / Pro (state-of-the-art mouth sync onto a video), Kling lipsync (audio-to- video and text-to-video with synced speech), and Creatify lipsync. The skill picks the right endpoint for the user's actual intent — portrait still + audio (avatar-style), source video + audio (mouth- swap on existing footage), or...

We need to translate the given English text into Indonesian. The text describes a skill for lip-syncing. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "lipsync" is not in the text? Actually it appears as "Lip-sync" at the beginning. The instruction says "Do not include the name unless it appears in the source text." The name "lipsync" appears as "Lip-sync" in the source text. So we should translate that as well? But the instruction says "Preserve product names" and "Name to preserve: lipsync". So we should keep "lipsync" as is? But the source has "Lip-sync" with hyphen and capital L. Probably we should keep it as "Lip-sync" or "lipsync"? The instruction says "Name to preserve: lipsync" (lowercase). But in the text it's "Lip-sync". I think we should preserve the exact form as in the source: "Lip-sync". However, the instruction says

We need to translate the given English text into Bahasa Indonesia. The text describes a lip-sync agent skill that uses various tools. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "lipsync" is preserved but not added unless in source. The source includes "lipsync" as part of the text? Actually the first word is "Lip-sync" which is a term, not the name. The name to preserve is "lipsync" but it appears as "Lip-sync" in the text. We should keep it as "Lip-sync" or "lipsync"? The instruction says "Name to preserve: lipsync" but the text has "Lip-sync". Probably we should keep the original casing from the text. Also "RunComfy", "runcomfy", "ByteDance OmniHuman", "Sync Labs sync v2 / Pro", "Kling lipsync", "Creatify lipsync" are product names. We preserve them. The text ends with "or..." so we keep that

Penanganan multimedia dengan pustaka Mediabunny

Gunakan saat pengguna menginginkan grafik gerak pendek berbasis desain di mana gerakan adalah pesannya: tipografi kinetik, hitungan angka atau statistik, pukulan grafik data, logo sting, penguncian merek, sepertiga bawah, callout, overlay sosial, judul/cuitan/berita animasi, poster gerak, atau sorotan halaman yang ditangkap cepat. Biasanya di bawah 10 detik dan hingga ~30 detik, tanpa alur narasi, sulih suara, atau subjek aksi langsung. Dapat dirender ke MP4 atau overlay transparan. Bukan untuk karya yang lebih panjang, multi-adegan, bernarasi, atau potongan reel merek...

Gunakan saat pengguna memiliki trek musik (file audio, atau video untuk mengambil audio) dan menginginkan video HyperFrames yang tersinkronisasi beat, dari yang tenang hingga keras. Musik mengendalikan segalanya: satu penganalisis membacanya sekali, pengatur tata letak menyusun bingkai dan mengisi rencana per bingkai, dan satu sub-agen membangun setiap bingkai. Tipografi dan templat adalah dasar — video lengkap tidak memerlukan aset apa pun — tetapi gambar atau video apa pun yang disediakan pengguna dipotong ke dalam bingkai pada grid beat yang sama (potongan beat /...

Hasilkan video dengan Pruna P-Video dan model WAN melalui CLI inference.sh. Model: P-Video, WAN-T2V, WAN-I2V. Kemampuan: teks-ke-video, gambar-ke-video, dukungan audio, 720p/1080p, inferensi cepat. Pruna mengoptimalkan model untuk kecepatan tanpa kehilangan kualitas. Pemicu: 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

Hasilkan video dengan Pruna P-Video dan model WAN melalui CLI inference.sh. Model: P-Video, WAN-T2V, WAN-I2V. Kemampuan: teks-ke-video, gambar-ke-video, dukungan audio, 720p/1080p, inferensi cepat. Pruna mengoptimalkan model untuk kecepatan tanpa kehilangan kualitas. Pemicu: 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

Hasilkan video avatar berbicara dengan Pruna P-Video-Avatar melalui CLI inference.sh. Ubah gambar potret menjadi video berbicara realistis dengan TTS bawaan. 18x lebih cepat dan 6x lebih murah dibanding pesaing. Model: P-Video-Avatar, P-Image (untuk pembuatan potret). Kemampuan: teks-ke-avatar, avatar berbasis audio, 30 suara, 10 bahasa, 720p/1080p, TTS bawaan, latar dinamis, kontrol seluruh tubuh. Gunakan untuk: presenter AI, demo produk, video penjelasan, influencer virtual, pemasaran,...

Hasilkan video avatar berbicara dengan Pruna P-Video-Avatar melalui CLI inference.sh. Ubah gambar potret menjadi video berbicara realistis dengan TTS bawaan. 18x lebih cepat dan 6x lebih murah dibanding pesaing. Model: P-Video-Avatar, P-Image (untuk pembuatan potret). Kemampuan: teks-ke-avatar, avatar berbasis audio, 30 suara, 10 bahasa, 720p/1080p, TTS bawaan, latar dinamis, kontrol seluruh tubuh. Gunakan untuk: presenter AI, demo produk, video penjelasan, influencer virtual, pemasaran,...

Keterampilan pembuatan video AI dengan pemilihan model otomatis di Seedance 2, Kling 3.0, HappyHorse, dan 10+ model. Menghasilkan video multi-shot jadi (5–120 detik) dari teks, gambar, URL, naskah, atau audio — termasuk musik AI, sinkronisasi bibir, dan urutan multi-shot. Tidak perlu menulis perintah, tidak perlu memilih model. GUNAKAN UNTUK: produksi video, video AI, buat video, video produk, video merek, klip promosi, video penjelas, video pendek, video TikTok, Instagram Reel, YouTube Short, iklan produk,...

pr-to-video workflow - sebuah pull request GitHub (URL seperti github.com/ / /pull/ , atau / # , atau "PR ini" di repositori yang sudah di-checkout) -> fakta PR yang diolah (judul, body, diff, commit, file, statistik +/-) -> narrator_scripts.json + audio (suara + BGM) + section_plan.md -> video penjelas code-diff / before-after / dampak. Input adalah PERUBAHAN KODE. URL tersebut adalah tautan PR, BUKAN situs pemasaran untuk di-scrape; bukan ringkasan teks dan bukan situs produk. Untuk input non-PR (situs produk, situs umum, teks topik),...

Gunakan saat pengguna menginginkan video peluncuran produk, promosi SaaS, pengungkapan fitur, video pemasaran aplikasi/perusahaan/situs, atau naskah/brief yang diubah menjadi video berfokus produk. Pemicu termasuk video peluncuran untuk X, promosi untuk situs kami, jelaskan SaaS saya dalam satu menit, pengungkapan fitur untuk X.com, dan ubah naskah ini menjadi promosi 60 detik. Dapat menggunakan URL produk/pemasaran untuk pengambilan merek atau mode tanpa pengambilan dari brief/naskah. Bukan untuk penjelas topik tanpa produk atau URL (faceless-explainer), PR GitHub/perubahan kode...

Menangani teks di Remotion

Praktik terbaik untuk menulis Remotion React Markup

Render video dari kode komponen React/Remotion melalui inference.sh. Kirim kode TSX, dapatkan MP4. Mendukung semua API Remotion: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Resolusi, FPS, durasi, codec dapat dikonfigurasi. Gunakan untuk: pembuatan video secara programatis, grafik animasi, desain gerak, video berbasis data, animasi React ke video. Pemicu: remotion, render video dari kode, tsx ke video, react video, video programatis, render remotion, kode ke video, animasi...

Render video dari kode komponen React/Remotion melalui inference.sh. Kirim kode TSX, dapatkan MP4. Mendukung semua API Remotion: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Resolusi, FPS, durasi, codec dapat dikonfigurasi. Gunakan untuk: pembuatan video secara programatis, grafik animasi, desain gerak, video berbasis data, animasi React ke video. Pemicu: remotion, render video dari kode, tsx ke video, react video, video programatis, render remotion, kode ke video, animasi...

Render video dari kode komponen React/Remotion melalui inference.sh. Masukkan kode TSX, dapatkan MP4. Mendukung semua API Remotion: useCurrentFrame,

Membangun aplikasi video dengan Remotion - saran framework, rendering, dan Player

Terjemahkan komposisi video Remotion (berbasis React) yang sudah ada menjadi komposisi HTML HyperFrames. HANYA gunakan saat pengguna secara eksplisit meminta untuk mem-port, mengonversi, memigrasikan, menerjemahkan, atau menulis ulang komposisi Remotion sebagai HyperFrames (misalnya "port proyek Remotion saya ke HyperFrames"). JANGAN gunakan saat (a) membuat komposisi HyperFrames BARU (meskipun melakukan A/B-testing video Remotion); (b) Remotion disebutkan secara sepintas; (c) kode Remotion dibagikan sebagai referensi, bukan untuk diterjemahkan; (d) pengguna menginginkan...

Hasilkan video dengan ByteDance Seedance 2.0 melalui CLI inference.sh. Model terpadu untuk teks-ke-video, gambar-ke-video, dan referensi-ke-video dengan audio tersinkronisasi, hingga 1080p, durasi 4-15 detik. Varian Pro dan Fast. Varian Studio dengan pustaka aset pribadi untuk konsistensi potret. Gunakan untuk: video media sosial, video musik, demo produk, konten animasi, video AI dengan suara. Pemicu: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video dengan audio,...

Hasilkan video dengan ByteDance Seedance 2.0 melalui CLI inference.sh. Model terpadu untuk teks-ke-video, gambar-ke-video, dan referensi-ke-video dengan audio tersinkronisasi, hingga 1080p, durasi 4-15 detik. Varian Pro dan Fast. Varian Studio dengan pustaka aset pribadi untuk konsistensi potret. Gunakan untuk: video media sosial, video musik, demo produk, konten animasi, video AI dengan suara. Pemicu: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video dengan audio,...

We need to translate the given text from English to Bahasa Indonesia. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions strengths, duration schema, alternatives, and CLI command. The instruction says to preserve product names, protocol names, URLs, numbers, technical terms. Also preserve the name "seedance-v2" if it appears, but it does not appear in the text except as part of the CLI command? Actually the text includes "bytedance/seedance-v2/pro" - that's a technical term, so preserve as is. Also "Seedance 2.0 Pro" is a product name, preserve. "RunComfy" preserve. "HappyHorse 1.0", "Wan 2.7", "Kling" preserve. "CLI" preserve. The text ends with "seedance..." incomplete, but we translate as is. Translate the text inside <text> only. Do not include the name "seedance-v2" unless it appears

We need to translate the given text from English to Bahasa Indonesia. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions features, duration schema, and routing to other models. Also mentions CLI command and trigger phrases. 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", "seedance", "seedance 2", "seedance v2" should remain as is. Also "CLI" and "runcomfy run bytedance/seedance-v2/pro" should be preserved. Translate the rest naturally. The text inside <text> is the entire paragraph. We output only the translation, no extra labels. Let's translate: "Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy.

Hasilkan video pendek sinematik dengan ByteDance Seedance 2.0 Pro di RunComfy. Mendokumentasikan keunggulan Seedance 2.0 Pro (referensi multimodal — hingga 9 gambar, 3 video, 3 audio — audio tersinkronisasi dalam video dengan lip-sync alami, penyempurnaan

Pembuatan papan cerita film dan video dengan kosakata bidikan, aturan kontinuitas, dan tata letak panel. Mencakup jenis bidikan, sudut kamera, pergerakan, aturan 180 derajat, dan format anotasi. Gunakan untuk: perencanaan video, praproduksi film, papan cerita iklan, perencanaan video musik, animasi. Pemicu: storyboard, storyboarding, shot list, film planning, video planning, pre production, shot composition, camera angles, scene planning, visual script, animatic, storyboard panels, video storyboard

Pembuatan papan cerita film dan video dengan kosakata bidikan, aturan kontinuitas, dan tata letak panel. Mencakup jenis bidikan, sudut kamera, pergerakan, aturan 180 derajat, dan format anotasi. Gunakan untuk: perencanaan video, pra-produksi film, papan cerita iklan, perencanaan video musik, animasi. Pemicu: papan cerita, pembuatan papan cerita, daftar bidikan, perencanaan film, perencanaan video, pra-produksi, komposisi bidikan, sudut kamera, perencanaan adegan, naskah visual, animatik, panel papan cerita, papan cerita video

Pembuatan papan cerita film dan video dengan kosakata bidikan, aturan kontinuitas, dan tata letak panel. Mencakup jenis bidikan, sudut kamera, pergerakan, aturan 180 derajat, dan format anotasi. Gunakan untuk: perencanaan video, praproduksi film, papan cerita iklan, perencanaan video musik, animasi. Pemicu: storyboard, storyboarding, shot list, film planning, video planning, pre production, shot composition, camera angles, scene planning, visual script, animatic, storyboard panels, video storyboard

Kemas video talking-head / wawancara / podcast yang sudah ada dengan melapisi kartu OVERLAY GRAFIS yang dirancang dan diberi waktu pada video yang diputar — judul, lower-thirds, data callouts, kutipan, panel samping, picture-in-picture — yang disinkronkan dengan transkrip. Video sumber diputar sepenuhnya; agen merancang dan menulis HTML setiap kartu dalam percakapan, lalu merender ke MP4 melalui hyperframes. Gunakan saat pengguna meminta overlay grafis, grafik di layar / lower-thirds / data callouts / judul kinetik pada video,...

Ketika pengguna ingin membuat, menghasilkan, atau memproduksi konten video menggunakan alat AI atau kerangka kerja terprogram. Juga gunakan ketika pengguna menyebut 'produksi video,' 'video AI,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Sora,' 'Runway,' 'Kling,' 'Seedance,' 'Hailuo,' 'MiniMax,' 'Pika,' 'Hunyuan,' 'Wan,' 'generasi video,' 'avatar AI,' 'video kepala bicara,' 'video terprogram,' 'template video,' 'video penjelasan,' 'video demo produk,' 'pipeline video,' atau 'buatkan saya video.' Gunakan...

Pembuatan iklan video dengan spesifikasi tepat sesuai platform untuk TikTok, Instagram, YouTube, Facebook, LinkedIn. Mencakup dimensi, batas durasi, kerangka AIDA, dan persyaratan teks. Gunakan untuk: iklan video, iklan media sosial, materi iklan media berbayar, pemasaran video, produksi iklan. Pemicu: iklan video, iklan media sosial, iklan tiktok, iklan instagram, iklan youtube, iklan facebook, iklan linkedin, materi iklan video, spesifikasi iklan, media berbayar, pemasaran video, produksi iklan, iklan reels, iklan stories, pre roll, bumper ad

Pembuatan iklan video dengan spesifikasi tepat sesuai platform untuk TikTok, Instagram, YouTube, Facebook, LinkedIn. Mencakup dimensi, batas durasi, kerangka AIDA, dan persyaratan teks. Gunakan untuk: iklan video, iklan media sosial, kreatif media berbayar, pemasaran video, produksi iklan. Pemicu: iklan video, iklan media sosial, iklan tiktok, iklan instagram, iklan youtube, iklan facebook, iklan linkedin, kreatif video, spesifikasi iklan, media berbayar, pemasaran video, produksi iklan, iklan reels, iklan stories, pre roll, bumper ad

Edit video yang sudah ada di RunComfy — skill ini adalah router pintar yang mencocokkan maksud pengguna dengan model edit yang tepat di katalog RunComfy. Memilih Wan 2.7 Edit-Video (restyle umum / tukar latar belakang / tukar kemasan, preservasi identitas + gerakan), Kling 2.6 Pro Motion Control (mentransfer gerakan presisi dari video referensi ke karakter target), atau Lucy Edit Restyle (restyle ringan dengan identitas stabil / tukar pakaian). Menggabungkan pola prompting terdokumentasi setiap model sehingga skill...

Edit video yang sudah ada di RunComfy — skill ini adalah router pintar yang mencocokkan maksud pengguna dengan model edit yang tepat di katalog RunComfy. Memilih Wan 2.7 Edit-Video (restyle umum / tukar latar belakang / tukar kemasan, preservasi identitas + gerakan), Kling 2.6 Pro Motion Control (transfer gerakan presisi dari video referensi ke karakter target), atau Lucy Edit Restyle (restyle ringan dengan preservasi identitas / tukar pakaian). Menggabungkan pola prompt terdokumentasi setiap model sehingga skill...

Edit video yang sudah ada di RunComfy — skill ini adalah router pintar yang mencocokkan niat pengguna dengan model edit yang tepat di katalog RunComfy. Memilih Wan 2.7 Edit-Video (restyle umum / tukar latar belakang / tukar kemasan, pelestarian identitas + gerakan), Kling 2.6 Pro Motion Control (mentransfer gerakan presisi dari video referensi ke karakter target), atau Lucy Edit Restyle (restyle ringan dengan identitas stabil / tukar pakaian). Menggabungkan pola prompt yang terdokumentasi dari setiap model sehingga skill...

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 Bahasa Indonesia. The text describes a video outpainting skill. We must preserve the name "video-outpainting" and technical terms like "RunComfy", "runcomfy CLI", "Wan 2-7 edit-video", "ComfyUI". Also preserve URLs if any (none here). Numbers like "9:16", "16:9" should be kept. The translation should be natural Indonesian. The instruction says to translate only the text inside <text>, and not include the name unless it appears. The name "video-outpainting" appears in the first line? Actually the first line says "Video outpainting on RunComfy..." so "Video outpainting" is part of the text. We should translate that as "Outpainting video" or similar? But the name to preserve is "video-outpainting" (with hyphen). In the text it's written as "Video outpainting" (without hyphen). We should preserve the term as is? The instruction says "Name

We need to translate the given text from English to Bahasa Indonesia. The text describes a video outpainting skill. We must preserve the name "video-outpainting" and technical terms like "RunComfy", "runcomfy CLI", "Wan 2-7 edit-video", "ComfyUI". Also preserve URLs if any (none here). Numbers like "9:16", "16:9" should be kept. The translation should be natural Indonesian. The instruction says to translate only the text inside <text>, and not include the name unless it appears in source. The name "video-outpainting" appears in the source as part of the text? Actually the first word is "Video outpainting" - that's the skill name? But the instruction says "Name to preserve: video-outpainting" and "Do not include the name unless it appears in the source text." The source text starts with "Video outpainting on RunComfy..." so "Video outpainting" appears. So we should translate that as "Video outpainting

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...

Menulis dan mengkritisi kait viral untuk video pendek: 1 hingga 3 detik pembuka yang menentukan apakah konten lainnya akan dilihat. Gunakan ini ketika Anda membutuhkan sekumpulan ide kait untuk sebuah video, ingin memperkuat kalimat pembuka yang lemah, memilih arketipe kait yang cocok dengan ide, atau ingin kritik terhadap draf kait berdasarkan pola yang sudah terbukti. Mencakup kait tiga lapis (visual, verbal, teks di layar), kerangka kerja kreator ternama (Kallaway, MrBeast, Hormozi, Brunson, Koe, Welsh, Bush, Galloway),...

Buatlah konten video pendek dan korsel dengan retensi tinggi untuk TikTok, Reels, dan YouTube Shorts. Gunakan saat seseorang menginginkan ide hook viral, naskah atau kerangka video, konsep konten untuk produk atau topik, atau ingin meng

Tulis skrip TikTok, hook TikTok, atau ide video TikTok segar yang dirancang sesuai cara FYP benar-benar memberi peringkat konten. Gunakan saat seseorang meminta hook TikTok untuk X, ingin skrip berbentuk TikTok, menanyakan apakah klip itu TikTok atau Reel, ingin memperbaiki video TikTok yang sudah dibuat, atau ingin tahu tren TikTok apa yang layak diikuti minggu ini. Mencakup sinyal algoritma TikTok (interaksi pengguna, informasi video, perangkat dan akun), matematika tingkat penyelesaian berdasarkan durasi, suara yang sedang tren...

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 Bahasa Indonesia. The text describes an agent skill for generating text-to-video using Wan 2.7. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "wan-2-7" is to be preserved if it appears in the source text. The instruction says: "Do not include the name unless it appears in the source text." The name appears multiple times: "Wan 2.7", "wan-2-7", "wan". So we keep those as is. Also "RunComfy", "HappyHorse 1.0", "Seedance 2.0", "Kling", "LTX 2", "CLI", "audio_url", "runcomfy run wan-ai/wan-2-7/text-to-video" are technical terms/names to preserve. We translate the rest naturally. Let's break down the text: "Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model

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...

Tonton video (URL atau jalur lokal). Unduh dengan yt-dlp, ekstrak bingkai berskala otomatis dengan ffmpeg, ambil transkrip dari takarir (atau cadangan Whisper API), lalu berikan hasilnya ke Claude agar dapat menjawab pertanyaan tentang isi video.

Ambil tangkapan layar dari sebuah situs web/URL umum dan ubah menjadi video HyperFrames (tur situs, showcase, atau klip sosial dari visual situs itu sendiri). Menggunakan tangkapan layar Chrome tanpa kepala + aset merek. Gunakan ketika tujuannya bersifat umum — showcase portofolio/blog/halaman arahan atau klip sosial dari situs. BUKAN untuk: peluncuran atau promosi produk/SaaS (→ /product-launch-video, bahkan dari URL); penjelasan topik tanpa situs (→ /faceless-explainer); PR GitHub (→ /pr-to-video); menambahkan teks ke video yang sudah ada (→...

Desain thumbnail YouTube dengan dimensi spesifik, aturan kontras, dan optimasi pratinjau seluler. Mencakup zona aman, penempatan teks, psikologi ekspresi wajah, dan pengujian A/B. Gunakan untuk: thumbnail YouTube, gambar sampul video, optimasi klik-tayang. Pemicu: thumbnail youtube, desain thumbnail, thumbnail video, rasio klik-tayang, optimasi ctr, sampul youtube, gambar sampul video, pembuat thumbnail, tips thumbnail, desain youtube, gambar pratinjau video