视频技能

通过inference.sh CLI创建AI虚拟形象和说话头像视频。推荐：P-Video-Avatar（最快、最便宜、内置TTS）。其他选项：OmniHuman、Fabric、PixVerse。音频：Inworld TTS-2（支持100+语言、角色情感控制）、ElevenLabs、Kokoro。功能：音频驱动虚拟形象、文本转虚拟形象、唇形同步视频、说话头像生成、虚拟主持人、UGC内容。用途：AI主持人、解说视频、虚拟网红、配音、营销视频、UGC广告、游戏虚拟形象等。

We need to translate the given English text into Simplified Chinese. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "ai-avatar-video" is not in the text, so we don't include it. We must not add any labels or extra commentary. Just translate the text inside <text>. The text describes creating AI avatar videos using runcomfy CLI, mentioning various models: ByteDance OmniHuman, Wan-AI Wan 2-7, HappyHorse 1.0, Seedance v2 Pro. Also mentions user intents like UGC voiceover, virtual presenter, etc. We need to translate accurately, keeping technical terms and names as is. For example, "talking-head" might be translated as "说话头像" or keep as "talking-head"? Probably keep as "talking-head" or translate? The instruction says preserve technical terms, but "talking-head" is a common term. I'll translate it as "说话头像" but maybe keep English? Better to translate common terms

We need to translate the given English text into Simplified Chinese. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "ai-avatar-video" is not in the text, so we don't include it. We must not add any labels or extra commentary. Just translate the text inside <text> tags. The text describes creating AI avatar videos using runcomfy CLI, mentioning various models: ByteDance OmniHuman, Wan-AI Wan 2-7, HappyHorse 1.0, Seedance v2 Pro. Also mentions user intents like UGC voiceover, virtual presenter, etc. We need to ensure technical terms like "t2v", "i2v", "in-pass audio", "multi-modal cinematic" are preserved or appropriately translated? The instruction says preserve technical terms, so we can keep them as is or translate if common? But "t2v" and "i2v" are likely abbreviations for text-to-video and image-to-video, which are common. However,

通过inference.sh CLI创建AI虚拟形象和说话头像视频。推荐：P-Video-Avatar（最快、最便宜、内置TTS）。其他选项：OmniHuman、Fabric、PixVerse。音频：Inworld TTS-2（支持100+语言、角色情感控制）、ElevenLabs、Kokoro。功能：音频驱动虚拟形象、文本转虚拟形象、唇形同步视频、说话头像生成、虚拟主持人、UGC内容。用途：AI主持人、解说视频、虚拟网红、配音、营销视频、UGC广告、游戏虚拟形象……

通过inference.sh CLI创建AI虚拟形象和说话头像视频。推荐：P-Video-Avatar（最快、最便宜、内置TTS）。其他选项：OmniHuman、Fabric、PixVerse。音频：Inworld TTS-2（支持100多种语言、角色情感控制）、ElevenLabs、Kokoro。功能：音频驱动虚拟形象、文本转虚拟形象、唇形同步视频、说话头像生成、虚拟主持人、UGC内容。用途：AI主持人、解说视频、虚拟网红、配音、营销视频、UGC广告、游戏虚拟形象……

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...

通过 inference.sh CLI，使用 Google Veo、Seedance 2.0、HappyHorse、Wan、Grok 及 40 多个模型生成 AI 视频。模型包括：Veo 3.1、Veo 3、Seedance 2.0、HappyHorse 1.0、Wan 2.5、Grok Imagine Video、OmniHuman、Fabric、HunyuanVideo。功能涵盖：文生视频、图生视频、参考视频生成、视频编辑、唇形同步、虚拟人动画、视频增强、拟音音效。适用于：社交媒体视频、营销内容、解说视频、产品演示、AI 虚拟人。触发词：视频生成、AI 视频……

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 Simplified Chinese. The text describes an agent skill for AI video generation using RunComfy CLI. It lists various models and capabilities. We must preserve product names, protocol names, URLs, numbers, technical terms. No extra commentary. The name "ai-video-generation" is not in the text, so we don't include it. We translate only the text inside <text>. The text includes a list of models with versions and descriptions. We need to translate the descriptions but keep model names and version numbers as is. Also keep "RunComfy", "CLI", "Arena", "open weights", "audio-driven lip-sync", "multi-modal cinematic", "text-to-video (t2v)", "image-to-video (i2v)", "video-extend endpoint". For Chinese, we can use common translations for terms like "native in-pass audio" -> "原生内嵌音频", "smart router" -> "智能路由器", "covers" -> "涵盖", etc. Ensure the translation is natural and

通过 inference.sh CLI，使用 Google Veo、Seedance 2.0、HappyHorse、Wan、Grok 及 40 多个模型生成 AI 视频。模型包括：Veo 3.1、Veo 3、Seedance 2.0、HappyHorse 1.0、Wan 2.5、Grok Imagine Video、OmniHuman、Fabric、HunyuanVideo。功能涵盖：文生视频、图生视频、参考视频生成、视频编辑、唇形同步、虚拟人动画、视频增强、拟音音效。适用于：社交媒体视频、营销内容、解说视频、产品演示、AI 虚拟人。触发词：视频生成、AI 视频……

通过 inference.sh CLI，使用 Google Veo、Seedance 2.0、HappyHorse、Wan、Grok 及 40 多个模型生成 AI 视频。模型包括：Veo 3.1、Veo 3、Seedance 2.0、HappyHorse 1.0、Wan 2.5、Grok Imagine Video、OmniHuman、Fabric、HunyuanVideo。功能涵盖：文本转视频、图像转视频、参考转视频、视频编辑、唇形同步、虚拟形象动画、视频增强、拟音音效。适用于：社交媒体视频、营销内容、解说视频、产品演示、AI 虚拟形象。触发词：视频生成、AI 视频……

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...

We need to translate the given text from English to Simplified Chinese. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "controlnet-pose" is to be preserved but not included unless it appears in the source text. The source text does not include "controlnet-pose" explicitly, so we don't add it. We translate only the text inside <text>. No extra commentary, labels, etc. The text describes a pose-conditioned generation system on RunComfy via CLI, with 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 but we translate as is. We need to preserve: "RunComfy", "runcomfy", "Kling 2-6 Motion Control Pro / Standard", "Wan 2-2 Animate", "Z-Image Turbo Control

We need to translate the given text from English to Simplified Chinese. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "controlnet-pose" is to be preserved but not included unless it appears in the source text. The source text does not include "controlnet-pose" explicitly, so we don't add it. We translate only the text inside <text>. No extra commentary, labels, etc. The text describes a pose-conditioned generation system on RunComfy via CLI, with 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 need to translate accurately, preserving terms like "RunComfy", "CLI", "Kling 2-6 Motion Control Pro / Standard", "Wan 2-2 Animate", "Z-Image Turbo ControlNet Lo

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」

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」

为说话人视频添加字幕。一个包含32种视觉风格的目录（CATALOG.md），基于两种引擎：列流（字幕合成到场景中——遮罩遮挡+混合模式；奶油/墨水/编辑/主题演讲/纪录片/响亮/霓虹/故障/铬/速度）和主题构成（锚点/军械/终端/霓虹灯/星尘/跺脚/记分牌/交通/VHS/街机/档案/激光/雷声/全息/生物光/极光/光谱/剪纸/弹出/黑板/涂鸦/画笔/水墨/勒索/最后一页/夜城...

支持网络摄像头。

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...

我们要求翻译一段文本，目标语言是简体中文。文本内容是关于一个名为"face-swap"的agent skill的描述。需要保留产品名称、协议名称、URL、数字和技术术语。不要添加任何额外内容。文本中提到了多个工具/模型名称：RunComfy, runcomfy CLI, Wan 2-2 Animate, GPT Image 2 Edit, Nano Banana Edit, Flux Kontext, Kling 2-6 Motion Control Pro。这些都需要保留原样。另外注意"face-swap"是名称，但文本中没有出现，所以不翻译。翻译时只翻译<text>内的内容，不要包含"description"等标签。 文本内容：描述通过runcomfy CLI在RunComfy上实现换脸/换角色到视频或图像中。跨越多个社区模型/工具。最后一句"Picks the right model for..."不完整，但按原样翻译。 翻译时注意技术术语的准确性，比如"audio-driven character animation"译为"音频驱动的角色动画"，"identity swap"译为

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...

faceless-explainer 视频工作流程 - 任意文本（文章/笔记/主题/简报）→ narrator_scripts.json + 音频（语音+背景音乐）+ section_plan.md → 排版/抽象图形/图表/数据可视化视频。典型时长约3分钟以内（最佳时长约30-90秒）；真正较长的内容属于通用视频，不适用此工作流程。生成自身的旁白（TTS）——不与用户提供/预先录制的画外音同步（那是通用视频）。不涉及网站抓取，无真实产品截图……

用作自定义HyperFrames HTML视频合成创作的后备方案，适用于无专门工作流程的场景。涵盖较长或多场景作品、品牌/宣传片、蒙太奇、标题卡、动态海报、静态循环以及任意长度或格式的自由创作。不适用于营销产品推广（product-launch-video）、通用网站转视频（website-to-video）、主题解说（faceless-explainer）、GitHub PR视频（pr-to-video）、为现有素材添加字幕等场景。

将现有的讲话/访谈/播客视频进行包装，在播放的视频上叠加定时设计的图形覆盖卡片——标题、下方字幕、数据标注、引文、侧边栏、画中画——并与转录文本同步。源视频完整播放；代理在对话中设计并编写每张卡片的HTML，然后通过hyperframes渲染为MP4。当用户要求为视频添加图形覆盖、屏幕图形/下方字幕/数据标注/动态标题时使用……

通过inference.sh命令行界面，使用阿里巴巴HappyHorse 1.0模型生成和编辑视频。模型包括：HappyHorse T2V、I2V、R2V、Video Edit。功能：文本转视频、图像转视频、参考转视频、自然语言视频编辑、角色保留、720P/1080P分辨率、最长15秒。用途：物理逼真视频、视频编辑、角色一致性内容、产品演示、社交媒体。触发词：happyhorse、happy horse、alibaba video、happyhorse 1.0、dashscope video、alibaba...

通过inference.sh命令行界面，使用阿里巴巴HappyHorse 1.0模型生成和编辑视频。模型包括：HappyHorse T2V、I2V、R2V、Video Edit。功能：文本转视频、图像转视频、参考转视频、自然语言视频编辑、角色保留、720P/1080P分辨率、最长15秒。用途：物理逼真视频、视频编辑、角色一致性内容、产品演示、社交媒体。触发词：happyhorse、happy horse、alibaba video、happyhorse 1.0、dashscope video、alibaba...

在RunComfy上使用HappyHorse 1.0生成文本到视频。介绍HappyHorse 1.0的优势（在Artificial Analysis Video Arena排名第一，原生1080p并同步音频，多镜头角色一致性，支持6种语言提示），时长/宽高比/分辨率方案，以及何时转向Wan

在 RunComfy 上使用 HappyHorse 1.0 生成文本到视频。介绍 HappyHorse 1.0 的优势（在 Artificial Analysis Video Arena 排名第一，原生 1080p 并带有同步音频，多镜头角色一致性，支持 6 种语言提示）、时长

在RunComfy上使用HappyHorse 1.0生成文本到视频。介绍HappyHorse 1.0的优势（在Artificial Analysis Video Arena排名第一，原生1080p并同步音频，多