Skills Media

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...

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...

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 Bahasa Indonesia, preserving the specified terms: "image-outpainting", "RunComfy", "runcomfy", "Nano Banana 2 Edit", "GPT Image 2 Edit", "FLUX Kontext Pro", "Seedream", "Dreamina", "Qwen", "FLUX 2". Also preserve URLs, numbers, technical terms. Do not add any extra commentary or labels. The text is a description of an agent skill. Translate only the content inside <text>. The name "image-outpainting" is not in the source text? Actually it is in the first line: "Image outpainting on RunComfy..." So we need to translate "Image outpainting" but preserve the name? The instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "Image outpainting" might be a technical term, but it's also the name of the skill. The instruction says "Do not include the name unless it appears in the source text." It does

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",

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

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 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning...

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

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",...

Kling 3.0 generasi video di RunComfy. Kling 3.0 (juga disebut Kling V3.0) adalah model video multi-shot generasi ketiga dari Kuaishou Technology dengan audio tersinkronisasi native dan identitas karakter yang konsisten di seluruh shot. Skill ini mencakup keenam endpoint Kling 3.0, mencakup tiga tingkat rendering (Standard, Pro, 4K) dan dua mode (text-to-video, image-to-video). Panggilan runcomfy run kling/kling-3.0/ / melalui CLI RunComfy lokal. Memicu pada "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",...

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

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

Agent Media OS — resolve any media need (BGM, SFX, image, icon) into a frozen local file + ledger record. One verb (`resolve`) handles the full cascade — project cache, global cache, HeyGen catalog search, freeze, register. Keeps search noise on disk, hands the agent a path. Use when a composition needs background music, sound effects, images, or icons.

Penanganan multimedia dengan pustaka Mediabunny

Hasilkan gambar dengan Google Nano Banana 2 (text-to-image tingkat flash keluarga Gemini) di RunComfy — dibundel dengan pola prompt terdokumentasi model tersebut sehingga skill menghasilkan output yang lebih tajam dibandingkan prompt naif terhadap model yang sama. Mendokumentasikan keunggulan Nano Banana 2 (iterasi cepat, rendering tipografi dalam gambar, pembingkaian yang dapat diprediksi, konteks berbasis web opsional), harga berdasarkan tingkat resolusi, dial toleransi keamanan, serta kapan harus beralih ke Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream...

Hasilkan gambar dengan model Pruna P-Image melalui CLI inference.sh. Model: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Kemampuan: teks-ke-gambar, pengeditan gambar, gaya LoRA, komposisi multi-gambar, inferensi cepat. Pruna mengoptimalkan model untuk kecepatan tanpa kehilangan kualitas. Pemicu: pruna, p-image, pruna image, fast image generation, optimized flux, pruna ai, p image, fast ai image, economic image generation, cheap image generation

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,...

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....

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....

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....

Menangani teks di Remotion