[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-FireRedTeam--FireRed-OpenStoryline":3,"tool-FireRedTeam--FireRed-OpenStoryline":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":75,"owner_avatar_url":76,"owner_bio":77,"owner_company":78,"owner_location":78,"owner_email":78,"owner_twitter":78,"owner_website":78,"owner_url":79,"languages":80,"stars":105,"forks":106,"last_commit_at":107,"license":108,"difficulty_score":10,"env_os":109,"env_gpu":110,"env_ram":110,"env_deps":111,"category_tags":118,"github_topics":119,"view_count":23,"oss_zip_url":78,"oss_zip_packed_at":78,"status":16,"created_at":129,"updated_at":130,"faqs":131,"releases":172},3190,"FireRedTeam\u002FFireRed-OpenStoryline","FireRed-OpenStoryline","FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction, LLM-powered planning, and precise tool orchestration. It facilitates transparent, human-in-the-loop creation with reusable Style Skills for consistent, professional storytelling.","FireRed-OpenStoryline 是一款智能视频编辑助手，旨在将繁琐的手动剪辑转化为自然的对话式创作。用户只需通过简单的语言描述意图，它便能自动完成从素材搜索、剧本生成到配乐配音的全流程制作，彻底解决了传统视频制作门槛高、耗时长的痛点。\n\n这款工具特别适合内容创作者、营销人员以及希望快速产出高质量视频的普通用户，同时也为开发者提供了可复用的风格技能模块，便于探索更深层的应用场景。其核心亮点在于强大的大语言模型规划能力：不仅能理解主题与情感自动生成连贯故事线，支持“少样本”风格迁移以精准复刻特定文案语调，还能根据情绪智能推荐背景音乐并实现自动卡点。更独特的是，它允许用户通过对话实时调整剪辑节奏、画面细节甚至字体样式，并将成熟的编辑策略保存为“风格技能”，确保系列作品保持专业且一致的视觉叙事风格。无论是制作产品评测还是生活 Vlog，FireRed-OpenStoryline 都能让创意表达变得简单而高效。","\u003Cdiv align=\"center\">\n  \u003Ca href=\"#gh-light-mode-only\">\n    \u003Cimg\n      src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_d3eba7972743.png\"\n      alt=\"openstoryline\"\n      width=\"70%\"\n    \u002F>\n  \u003C\u002Fa>\n\n  \u003Ca href=\"#gh-dark-mode-only\">\n    \u003Cimg\n      src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_2a634a71a487.png\"\n      alt=\"openstoryline\"\n      width=\"70%\"\n    \u002F>\n  \u003C\u002Fa>\n  \n  \u003Cp>\n    \u003Ca href=\".\u002FREADME_zh.md\">🇨🇳 简体中文\u003C\u002Fa> | \n    \u003Ca href=\".\u002FREADME.md\">🌏 English\u003C\u002Fa>\n  \u003C\u002Fp>\n  \u003Cp>\n    \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FFireRedTeam\" target=\"_blank\">\u003Cimg alt=\"Hugging Face\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Hugging%20Face-FireRedTeam-ffc107?color=ffc107&logoColor=white\" style=\"display: inline-block;\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fwww.modelscope.cn\u002Fstudios\u002FFireRedTeam\u002FFireRed-OpenStoryline\" target=\"_blank\">\n        \u003Cimg alt=\"ModelScope Demo\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FModelScope-Demo-4B6CFF?style=flat&logo=modelscope&logoColor=white\" style=\"display: inline-block;\"\u002F>\u003C\u002Fa>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-≥3.11-blue\" alt=\"Python\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202.0-blue\" alt=\"License\">\n    \u003Ca href=\"https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fdocs\u002Fmedia\u002Fothers\u002Fgroup_20260329.jpg\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FXiaohongshu-Group-E9DBFC?style=flat&logo=xiaohongshu&logoColor=white\" alt=\"xiaohongshu\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fhellogithub.com\u002Frepository\u002FFireRedTeam\u002FFireRed-OpenStoryline\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fapi.hellogithub.com\u002Fv1\u002Fwidgets\u002Frecommend.svg?rid=fb457793a87e4bdab9c4f5ca26451a7f&claim_uid=4QpcNTrHEAg3O8n&theme=small\" alt=\"Featured｜HelloGitHub\" \u002F>\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n\n[🤗 HuggingFace Demo](https:\u002F\u002Ffireredteam-firered-openstoryline.hf.space\u002F) • [🌐 Homepage](https:\u002F\u002Ffireredteam.github.io\u002Fdemos\u002Ffirered_openstoryline\u002F)\n\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F9116767e-bcd9-417a-93d8-2db4d3d5df8e\" width=\"70%\" poster=\"\"> \u003C\u002Fvideo>\n\u003C\u002Fdiv>\n\n**FireRed-OpenStoryline** turns complex video creation into natural, intuitive conversations. Designed with both accessibility and enterprise-grade reliability in mind, FireRed-OpenStoryline makes video creation easy and friendly to beginners and creative enthusiasts alike.\n> Deriving from the saying \"A single spark can start a prairie fire\", the name FireRed represents our vision: to spread our SOTA capabilities—honed in real-world scenarios—like sparks across the wilderness, igniting the imagination of developers worldwide to reshape the future of AI together.\n\n## ✨ Key Features\n- 🌐 **Smart Media Search & Organization**: Automatically searches online and downloads images and video clips that match your requirements. Performs clip segmentation and content understanding based on your thematic media.\n- ✍️ **Intelligent Script Generation**: Combines user themes, visual understanding, and emotion recognition to automatically construct storylines and context-aware narration. Features built-in Few-shot style transfer capabilities, allowing users to define specific copy styles (e.g., product reviews, casual vlogs) via reference text, achieving precise replication of tone, rhythm, and sentence structure.\n- 🎵 **Intelligent Music, Voiceover & Font Recommendations**: Supports personal playlist imports and auto-recommends BGM based on content and mood, featuring smart beat-syncing. Simply describe the desired tone—e.g., \"Restrained,\" \"Emotional,\" or \"Documentary-style\"—and the system matches suitable voiceovers and fonts to ensure a cohesive aesthetic.\n- 💬 **Conversational Refinement**: Rapidly cut, swap, or resequence clips. Edit scripts and fine-tune visual details—including color, font, stroke, and position. All edits are performed exclusively via natural language prompts with immediate results.\n- ⚡**Editing Skill Archiving**: Save your complete editing workflow as a custom Skill. Simply swap the media and apply the corresponding Skill to instantly replicate the style, enabling efficient batch creation.\n\n## NEWS\n\n* 🎬 **2026-04-02**: Added the **AI Transition Generation** feature, which automatically creates transition shots based on the ending frame of one clip, the opening frame of the next, and a natural-language description, making scene transitions smoother and the narrative more coherent.\n* 🚀 **2026-03-22**: Introduced an **ASR-based rough cut skill for speech videos**, enabling automatic removal of filler words, disfluencies, and repeated sentences, with timestamp-aligned segmentation for cleaner and more efficient speech editing workflows.\n* 🔥 **2026-03-12**: Integrated with **OpenClaw**, adding two OpenClaw Skills — `openstoryline-install` and `openstoryline-use` — covering the initial installation\u002Ffirst-run workflow and the actual usage workflow, respectively. Also added Skill usage instructions for **Claude Code**, making it easier for **Claude Code** to install and invoke the project in accordance with the repository guidelines.\n* **2026-02-10**: FireRed-OpenStoryline was officially open-sourced.\n\n> \u003Csub>\n> ⚠️ Note: AI transitions rely on third-party AIGC video generation services, and \u003Cb>the cost is relatively high\u003C\u002Fb>. Due to variations in source material quality, prompts, and model performance, the generated results are somewhat unpredictable. It is recommended to enable this feature only when needed.\n> \u003C\u002Fsub>\n\n## 🏗️ Architecture\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_efaa33560db2.jpg\" alt=\"openstoryline architecture\" width=\"800\">\n\u003C\u002Fp>\n\n## ✨ Demo\n\u003Ctable align=\"center\">\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>Zhongcao Style\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Humorous Style\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Product Picks\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Artistic Style\u003C\u002Fb>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F28043813-1fda-4077-80d4-c6f540d7c7cb\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fa1e33da2-a799-4398-a1bb-b25bb5143d7c\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F444fd0fb-8824-4c25-b449-9309b0fcfd85\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F2e69fa0d-b693-4d4f-b4d2-45146254f9e8\" width=\"220\" \u002F>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>Unboxing\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Talking Pet\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Travel Vlog\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>Year-in-Review\u003C\u002Fb>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fff1d669b-1d27-4cf8-b0be-1b141c717466\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F063608bb-7fbd-4841-a08f-032ae459499f\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fbc441dfa-e995-4575-8401-ecefa269e57b\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F533ef5c3-bb76-4416-bff7-825e88b00b7d\" width=\"220\" \u002F>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n> \u003Csub>\n> 🎨 \u003Cb>Effects Note:\u003C\u002Fb> Due to licensing restrictions on open-source assets, the elements (fonts\u002Fmusic) in the first row represent only basic effects. We \u003Cb>highly recommend\u003C\u002Fb> following the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fblob\u002Fmain\u002Fdocs\u002Fsource\u002Fzh\u002Fguide.md#2-%E9%AB%98%E7%BA%A7%E4%BD%BF%E7%94%A8%E6%95%99%E7%A8%8B\">Custom Asset Library Tutorial\u003C\u002Fa> to unlock commercial-grade fonts, music, and VFX for significantly better video quality.\u003Cbr>\n> ⚠️ \u003Cb>Quality Note:\u003C\u002Fb> To save space in the README, the demo videos are heavily compressed. The actual output retains the original resolution by default and supports custom dimensions.\u003Cbr>\n> In the Demo: The \u003Cb>first row\u003C\u002Fb> shows default open-source assets (Restricted Mode); the \u003Cb>second row\u003C\u002Fb> shows Xiaohongshu App \"AI Clip\" asset library effects. 👉 \u003Ca href=\"https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fdocs\u002Fmedia\u002Fothers\u002Fai_cut_guide.png\">Click to view tutorial\u003C\u002Fa>\u003Cbr>\n> ⚖️ \u003Cb>Disclaimer:\u003C\u002Fb> User footage and brand logos shown in the demos are for technical demonstration purposes only. Ownership belongs to the original creators. Please contact us for copyright concerns.\n> \u003C\u002Fsub>\n\n## 🤖 Use Through an Agent\n\nFireRed-OpenStoryline supports usage through Agent Skills.\nWe provide two Skills:\n\n* `openstoryline-install`: for installation, configuration, and first-run verification.\n* `openstoryline-use`: for starting the service and running the actual video editing workflow.\n\n### OpenClaw\n\nJust tell OpenClaw: “I want to try OpenStoryline. Help me install the required Skills,” and it will automatically trigger the installation.\nIf the installation runs into problems, use the following commands to install them manually:\n\n```bash\nopenclaw skills install openstoryline-install\nopenclaw skills install openstoryline-use\n```\n\nIf your current OpenClaw version does not support `openclaw skills install`, or if installation still fails, you can use ClawHub instead:\n\n```bash\nnpx clawhub install openstoryline-install\nnpx clawhub install openstoryline-use\n```\n\nOnce installed, you only need to send your media assets to OpenClaw, and it can help you complete the entire process from installing FireRed-OpenStoryline to generating the final video.\n\n### Claude Code\n\nThis repository comes with built-in Claude Code Skills.\nIf you start Claude Code from the **root directory of this repository**, you can use the project-level Skills included in the repo directly. Claude Code can then help you install and use FireRed-OpenStoryline.\n\n```bash\n\u002Fopenstoryline-install\n\u002Fopenstoryline-use\n```\n\nIf you want to install these two Skills into your own global Claude Code configuration, run:\n\n```bash\nmkdir -p ~\u002F.claude\u002Fskills\ncp -R .claude\u002Fskills\u002Fopenstoryline-install ~\u002F.claude\u002Fskills\u002F\ncp -R .claude\u002Fskills\u002Fopenstoryline-use ~\u002F.claude\u002Fskills\u002F\n```\n\n### Other Compatible Agents (Experimental)\n\nThese Skills are based on an open Agent Skills format, so in theory they can also be installed into other compatible agents.\nFor example, you can install them into Codex via the Skills CLI:\n\n```bash\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-install --agent codex\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-use --agent codex\n```\n\nOr use the commands below with the `--global` flag to install these Skills into the user-level directory so they are available across projects:\n\n```bash\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-install --global\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-use --global\n```\n\n## 📦 Install\n### 1. Clone repository\n```\n# If git is not installed, refer to the official website for installation: https:\u002F\u002Fgit-scm.com\u002Finstall\u002F\n# Or manually download the code\ngit clone https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline.git\ncd FireRed-OpenStoryline\n```\n### 2. Create a virtual environment\n\nInstall Conda according to the official guide (Miniforge is recommended, it is suggested to check the option to automatically configure environment variables during installation): https:\u002F\u002Fdocs.conda.io\u002Fprojects\u002Fconda\u002Fen\u002Flatest\u002Fuser-guide\u002Finstall\u002Findex.html\n\n\n```\n# Recommended python>=3.11\nconda create -n storyline python=3.11\nconda activate storyline\n```\n### 3. 📦 Resource Download & Installation\n#### 3.1 Automatic Installation (Linux and macOS only)\n```\nsh build_env.sh\n```\n#### 3.2 Manual Installation\n##### A. MacOS or Linux\n  - Step 1: Install wget (if not already installed)\n\n    ```\n    # MacOS: If you haven't installed Homebrew yet, please install it first: https:\u002F\u002Fbrew.sh\u002F\n    brew install wget\n    \n    # Ubuntu\u002FDebian\n    sudo apt-get install wget\n    \n    # CentOS\n    sudo yum install wget\n    ```\n  - Step 2: Download Resources\n\n    ```bash\n    chmod +x download.sh\n    .\u002Fdownload.sh\n    ```\n  \n  - Step 3: Install Dependencies\n\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n##### B. Windows\n\n  - Step 1: Prepare Directory: Create a new directory named `resource` in the project root directory.\n\n  - Step 2: Download and Extract:\n\n    *   [Download Models (models.zip)](https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fmodels.zip) -> Extract to the `.storyline` directory.\n\n    *   [Download Resources (resource.zip)](https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fresource.zip) -> Extract to the `resource` directory.\n  - Step 3:  **Install Dependencies**:\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n## 🚀 Quick Start\n\nNote: Before starting, you need to configure the API-Key in config.toml first. For details, please refer to the documentation [API-Key Configuration](docs\u002Fsource\u002Fen\u002Fapi-key.md)\n\n\n### 1. Start the MCP Server\n\n#### MacOS or Linux\n\n```bash\nPYTHONPATH=src python -m open_storyline.mcp.server\n```\n\n#### Windows\n```\n$env:PYTHONPATH=\"src\"; python -m open_storyline.mcp.server\n```\n\n### 2. Start the conversation interface\n\n- Method 1: Command Line Interface\n\n  ```bash\n  python cli.py\n  ```\n\n- Method 2: Web Interface\n\n  ```bash\n  uvicorn agent_fastapi:app --host 127.0.0.1 --port 8005\n  ```\n\n## 🐳 Docker\n\n### Pull the Image\n```bash\n# Pull image from Docker Hub official repository\n# Recommended for users outside China\ndocker pull openstoryline\u002Fopenstoryline:v1.0.1\n\n# Pull image from Alibaba Cloud Container Registry\n# Recommended for users in China (faster and more stable)\ndocker pull crpi-6knxem4w8ggpdnsn.cn-shanghai.personal.cr.aliyuncs.com\u002Fopenstoryline\u002Fopenstoryline:v1.0.1\n```\n\n### Start the Container\n```\ndocker run \\\n  -v $(pwd)\u002Fconfig.toml:\u002Fapp\u002Fconfig.toml \\\n  -v $(pwd)\u002Foutputs:\u002Fapp\u002Foutputs \\\n  -v $(pwd)\u002Frun.sh:\u002Fapp\u002Frun.sh \\\n  -p 7860:7860 \\\n  openstoryline\u002Fopenstoryline:v1.0.1\n```\nAfter starting, access the Web interface at http:\u002F\u002F0.0.0.0:7860\n\n## 📁 Project Structure\n```\nFireRed-OpenStoryline\u002F\n├── 🎯 src\u002Fopen_storyline\u002F           Core application\n│   ├── mcp\u002F                         🔌 Model Context Protocol\n│   ├── nodes\u002F                       🎬 Video processing nodes\n│   ├── skills\u002F                      🛠️ Agent skills library\n│   ├── storage\u002F                     💾 Agent Memory\n│   ├── utils\u002F                       🧰 Helper utilities\n│   ├── agent.py                     🤖 Build Agent\n│   └── config.py                    ⚙️ Configuration management\n├── 📚 docs\u002F                         Documentation\n├── 🐳 Dockerfile                    Docker Configuration\n├── 💬 prompts\u002F                      LLM prompt templates\n├── 🎨 resource\u002F                     Static resources\n│   ├── bgms\u002F                        Background music library\n│   ├── fonts\u002F                       Font files\n│   ├── script_templates\u002F            Video script templates\n│   └── unicode_emojis.json          Emoji list\n├── 🔧 scripts\u002F                      Utility scripts\n├── 🌐 web\u002F                          Web interface\n├── 🚀 agent_fastapi.py              FastAPI server\n├── 🖥️ cli.py                        Command-line interface\n├── ⚙️ config.toml                   Main configuration file\n├── 🚀 build_env.sh                  Environment Build Script\n├── 📥 download.sh                   Resource downloader\n├── 📦 requirements.txt              Runtime dependencies\n└── ▶️ run.sh                        Launch script\n\n```\n\n## 📚 Documentation\n\n### 📖 Tutorial Index\n\n- [API Key Configuration](docs\u002Fsource\u002Fen\u002Fapi-key.md) - How to configure and manage API keys\n- [Usage Tutorial](docs\u002Fsource\u002Fen\u002Fguide.md) - Common use cases and basic operations\n- [FAQ](docs\u002Fsource\u002Fen\u002Ffaq.md) - Frequently asked questions\n\n## TODO\n\n- [ ] Add the function of **voiceover type video editing**.\n- [ ] Add support for **voice cloning**\n- [ ] Add more **transition\u002Ffilter\u002Feffects** effects functions.\n- [ ] Add **image\u002Fvideo generation and editing** capabilities.\n- [ ] **GPU-accelerated** rendering and highlight selection.\n\n## Acknowledgements\n\nThis project is built upon the following excellent open-source projects:\n\n### Core Dependencies\n- [MoviePy](https:\u002F\u002Fgithub.com\u002FZulko\u002Fmoviepy) - Video editing library\n- [FFmpeg](https:\u002F\u002Fffmpeg.org\u002F) - Multimedia framework\n- [LangChain](https:\u002F\u002Fwww.langchain.com\u002F) - A framework that provides pre-built Agents\n\n## 📄 License\n\nThis project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.\n\n## ⭐ Star History\n\n\u003Cdiv align=\"center\"> \u003Cp> \u003Cimg width=\"800\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_c640222d99e1.png\" alt=\"Star-history\"> \u003C\u002Fp> \u003C\u002Fdiv>\n","\u003Cdiv align=\"center\">\n  \u003Ca href=\"#gh-light-mode-only\">\n    \u003Cimg\n      src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_d3eba7972743.png\"\n      alt=\"openstoryline\"\n      width=\"70%\"\n    \u002F>\n  \u003C\u002Fa>\n\n  \u003Ca href=\"#gh-dark-mode-only\">\n    \u003Cimg\n      src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_2a634a71a487.png\"\n      alt=\"openstoryline\"\n      width=\"70%\"\n    \u002F>\n  \u003C\u002Fa>\n  \n  \u003Cp>\n    \u003Ca href=\".\u002FREADME_zh.md\">🇨🇳 简体中文\u003C\u002Fa> | \n    \u003Ca href=\".\u002FREADME.md\">🌏 English\u003C\u002Fa>\n  \u003C\u002Fp>\n  \u003Cp>\n    \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FFireRedTeam\" target=\"_blank\">\u003Cimg alt=\"Hugging Face\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Hugging%20Face-FireRedTeam-ffc107?color=ffc107&logoColor=white\" style=\"display: inline-block;\"\u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fwww.modelscope.cn\u002Fstudios\u002FFireRedTeam\u002FFireRed-OpenStoryline\" target=\"_blank\">\n        \u003Cimg alt=\"ModelScope Demo\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FModelScope-Demo-4B6CFF?style=flat&logo=modelscope&logoColor=white\" style=\"display: inline-block;\"\u002F>\u003C\u002Fa>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-≥3.11-blue\" alt=\"Python\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202.0-blue\" alt=\"License\">\n    \u003Ca href=\"https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fdocs\u002Fmedia\u002Fothers\u002Fgroup_20260329.jpg\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FXiaohongshu-Group-E9DBFC?style=flat&logo=xiaohongshu&logoColor=white\" alt=\"xiaohongshu\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fhellogithub.com\u002Frepository\u002FFireRedTeam\u002FFireRed-OpenStoryline\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fapi.hellogithub.com\u002Fv1\u002Fwidgets\u002Frecommend.svg?rid=fb457793a87e4bdab9c4f5ca26451a7f&claim_uid=4QpcNTrHEAg3O8n&theme=small\" alt=\"Featured｜HelloGitHub\" \u002F>\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n\n[🤗 HuggingFace Demo](https:\u002F\u002Ffireredteam-firered-openstoryline.hf.space\u002F) • [🌐 Homepage](https:\u002F\u002Ffireredteam.github.io\u002Fdemos\u002Ffirered_openstoryline\u002F)\n\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F9116767e-bcd9-417a-93d8-2db4d3d5df8e\" width=\"70%\" poster=\"\"> \u003C\u002Fvideo>\n\u003C\u002Fdiv>\n\n**FireRed-OpenStoryline** 将复杂的视频创作转化为自然、直观的对话式操作。它兼顾易用性与企业级可靠性，让初学者和创意爱好者都能轻松上手，享受视频制作的乐趣。\n> “星星之火，可以燎原”，FireRed 这个名字寓意着我们的愿景：将我们在真实场景中锤炼出的 SOTA 技术能力，如星火般播撒到广阔天地间，点燃全球开发者们的想象力，共同重塑人工智能的未来。\n\n## ✨ 核心功能\n- 🌐 **智能媒体搜索与整理**：自动在线搜索并下载符合需求的图片和视频片段，同时根据主题素材进行片段分割和内容理解。\n- ✍️ **智能脚本生成**：结合用户主题、视觉理解和情感识别，自动生成故事情节及上下文相关的旁白。内置少样本风格迁移能力，用户可通过参考文本定义特定文案风格（如产品评测、休闲 Vlog），精准复制语气、节奏和句式结构。\n- 🎵 **智能音乐、配音与字体推荐**：支持导入个人播放列表，并根据内容和情绪自动推荐背景音乐，具备智能节拍同步功能。只需描述所需氛围——例如“内敛”、“感性”或“纪录片风”——系统便会匹配合适的配音和字体，确保整体风格统一。\n- 💬 **对话式精细调整**：快速剪切、替换或重新排序片段；编辑脚本并微调视觉细节，包括颜色、字体、描边和位置等。所有修改均通过自然语言指令完成，即时生效。\n- ⚡**剪辑技能存档**：将完整的剪辑流程保存为自定义技能。只需更换素材，应用相应技能即可快速复现风格，实现高效批量制作。\n\n## 最新动态\n\n* 🎬 **2026年4月2日**：新增 **AI 转场生成** 功能，可根据当前片段的结束帧、下一片段的起始帧以及自然语言描述，自动生成转场镜头，使场景过渡更加流畅，叙事更连贯。\n* 🚀 **2026年3月22日**：推出基于 ASR 的语音视频粗剪技能，可自动去除填充词、语病和重复句子，并按时间戳分割，让语音编辑流程更简洁高效。\n* 🔥 **2026年3月12日**：与 OpenClaw 集成，新增 `openstoryline-install` 和 `openstoryline-use` 两个 OpenClaw 技能，分别覆盖初始安装\u002F首次运行流程和实际使用流程。同时，还添加了 Claude Code 的技能使用说明，便于 Claude Code 按照仓库规范安装并调用该项目。\n* **2026年2月10日**：FireRed-OpenStoryline 正式开源。\n\n> \u003Csub>\n> ⚠️ 注意：AI 转场依赖第三方 AIGC 视频生成服务，\u003Cb>成本相对较高\u003C\u002Fb>。由于素材质量、提示词和模型性能的差异，生成效果存在一定不确定性。建议仅在必要时启用此功能。\n> \u003C\u002Fsub>\n\n## 🏗️ 架构设计\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_efaa33560db2.jpg\" alt=\"openstoryline architecture\" width=\"800\">\n\u003C\u002Fp>\n\n## ✨ 演示\n\u003Ctable align=\"center\">\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>中草风格\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>幽默风格\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>产品推荐\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>艺术风格\u003C\u002Fb>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F28043813-1fda-4077-80d4-c6f540d7c7cb\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fa1e33da2-a799-4398-a1bb-b25bb5143d7c\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F444fd0fb-8824-4c25-b449-9309b0fcfd85\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F2e69fa0d-b693-4d4f-b4d2-45146254f9e8\" width=\"220\" \u002F>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cb>开箱\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>会说话的宠物\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>旅行Vlog\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cb>年度回顾\u003C\u002Fb>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fff1d669b-1d27-4cf8-b0be-1b141c717466\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F063608bb-7fbd-4841-a08f-032ae459499f\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fbc441dfa-e995-4575-8401-ecefa269e57b\" width=\"220\" \u002F>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F533ef5c3-bb76-4416-bff7-825e88b00b7d\" width=\"220\" \u002F>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n> \u003Csub>\n> 🎨 \u003Cb>效果说明：\u003C\u002Fb>由于开源素材的授权限制，第一行中的元素（字体、音乐）仅展示基础效果。我们\u003Cb>强烈建议\u003C\u002Fb>参考\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fblob\u002Fmain\u002Fdocs\u002Fsource\u002Fzh\u002Fguide.md#2-%E9%AB%98%E7%BA%A7%E4%BD%BF%E7%94%A8%E6%95%99%E7%A8%8B\">自定义素材库教程\u003C\u002Fa>,以解锁商业级字体、音乐和特效，从而获得更优质的视频效果。\u003Cbr>\n> ⚠️ \u003Cb>质量说明：\u003C\u002Fb>为节省 README 空间，演示视频经过了大幅压缩。实际输出默认保留原始分辨率，并支持自定义尺寸。\u003Cbr>\n> 在演示中：\u003Cb>第一行\u003C\u002Fb>展示了默认的开源素材（受限模式）；\u003Cb>第二行\u003C\u002Fb>则展示了小红书App“AI剪辑”素材库的效果。👉 \u003Ca href=\"https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fdocs\u002Fmedia\u002Fothers\u002Fai_cut_guide.png\">点击查看教程\u003C\u002Fa>\u003Cbr>\n> ⚖️ \u003Cb>免责声明：\u003C\u002Fb>演示中出现的用户素材和品牌标志仅用于技术演示目的，其所有权归原创作者所有。如有版权问题，请与我们联系。\n> \u003C\u002Fsub>\n\n## 🤖 通过智能体使用\n\nFireRed-OpenStoryline 支持通过智能体技能使用。\n我们提供了两个技能：\n\n* `openstoryline-install`：用于安装、配置及首次运行验证。\n* `openstoryline-use`：用于启动服务并执行实际的视频编辑流程。\n\n### OpenClaw\n\n只需告诉 OpenClaw：“我想试用 OpenStoryline，帮我安装所需的技能”，它就会自动触发安装过程。\n如果安装过程中遇到问题，可以使用以下命令手动安装：\n\n```bash\nopenclaw skills install openstoryline-install\nopenclaw skills install openstoryline-use\n```\n\n若当前版本的 OpenClaw 不支持 `openclaw skills install`，或安装仍失败，可改用 ClawHub：\n\n```bash\nnpx clawhub install openstoryline-install\nnpx clawhub install openstoryline-use\n```\n\n安装完成后，只需将您的媒体素材发送给 OpenClaw，它就能帮助您完成从安装 FireRed-OpenStoryline 到生成最终视频的整个流程。\n\n### Claude Code\n\n本仓库内置了 Claude Code 技能。\n如果您从**本仓库的根目录**启动 Claude Code，可以直接使用仓库内包含的项目级技能，Claude Code 将协助您安装并使用 FireRed-OpenStoryline。\n\n```bash\n\u002Fopenstoryline-install\n\u002Fopenstoryline-use\n```\n\n若希望将这两个技能安装到您自己的全局 Claude Code 配置中，请执行以下操作：\n\n```bash\nmkdir -p ~\u002F.claude\u002Fskills\ncp -R .claude\u002Fskills\u002Fopenstoryline-install ~\u002F.claude\u002Fskills\u002F\ncp -R .claude\u002Fskills\u002Fopenstoryline-use ~\u002F.claude\u002Fskills\u002F\n```\n\n### 其他兼容智能体（实验性）\n\n这些技能基于开放的智能体技能格式，理论上也可安装到其他兼容的智能体中。\n例如，您可以通过 Skills CLI 将它们安装到 Codex 中：\n\n```bash\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-install --agent codex\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-use --agent codex\n```\n\n或者使用下方命令并加上 `--global` 标志，将这些技能安装到用户级别目录，使其在不同项目间通用：\n\n```bash\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-install --global\nnpx skills add FireRedTeam\u002FFireRed-OpenStoryline --skill openstoryline-use --global\n```\n\n## 📦 安装\n### 1. 克隆仓库\n```\n# 若未安装 Git，请参考官网进行安装：https:\u002F\u002Fgit-scm.com\u002Finstall\u002F\n# 或者手动下载代码\ngit clone https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline.git\ncd FireRed-OpenStoryline\n```\n### 2. 创建虚拟环境\n\n请按照官方指南安装 Conda（推荐使用 Miniforge，建议在安装时勾选自动配置环境变量的选项）：https:\u002F\u002Fdocs.conda.io\u002Fprojects\u002Fconda\u002Fen\u002Flatest\u002Fuser-guide\u002Finstall\u002Findex.html\n\n\n```\n# 推荐 Python>=3.11\nconda create -n storyline python=3.11\nconda activate storyline\n```\n\n### 3. 📦 资源下载与安装\n#### 3.1 自动安装（仅限 Linux 和 macOS）\n```\nsh build_env.sh\n```\n#### 3.2 手动安装\n##### A. MacOS 或 Linux\n  - 第一步：安装 wget（如果尚未安装）\n\n    ```\n    # MacOS：如果您尚未安装 Homebrew，请先安装：https:\u002F\u002Fbrew.sh\u002F\n    brew install wget\n    \n    # Ubuntu\u002FDebian\n    sudo apt-get install wget\n    \n    # CentOS\n    sudo yum install wget\n    ```\n  - 第二步：下载资源\n\n    ```bash\n    chmod +x download.sh\n    .\u002Fdownload.sh\n    ```\n  \n  - 第三步：安装依赖项\n\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n##### B. Windows\n\n  - 第一步：准备目录：在项目根目录下创建一个名为 `resource` 的新目录。\n\n  - 第二步：下载并解压：\n\n    *   [下载模型（models.zip）](https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fmodels.zip) -> 解压到 `.storyline` 目录。\n\n    *   [下载资源（resource.zip）](https:\u002F\u002Fimage-url-2-feature-1251524319.cos.ap-shanghai.myqcloud.com\u002Fopenstoryline\u002Fresource.zip) -> 解压到 `resource` 目录。\n  - 第三步：**安装依赖项**：\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n## 🚀 快速入门\n\n注意：在开始之前，您需要先在 config.toml 中配置 API-Key。有关详细信息，请参阅文档 [API-Key 配置](docs\u002Fsource\u002Fen\u002Fapi-key.md)\n\n\n### 1. 启动 MCP 服务器\n\n#### MacOS 或 Linux\n\n```bash\nPYTHONPATH=src python -m open_storyline.mcp.server\n```\n\n#### Windows\n```\n$env:PYTHONPATH=\"src\"; python -m open_storyline.mcp.server\n```\n\n### 2. 启动对话界面\n\n- 方法 1：命令行界面\n\n  ```bash\n  python cli.py\n  ```\n\n- 方法 2：Web 界面\n\n  ```bash\n  uvicorn agent_fastapi:app --host 127.0.0.1 --port 8005\n  ```\n\n## 🐳 Docker\n\n### 拉取镜像\n```bash\n# 从 Docker Hub 官方仓库拉取镜像\n# 推荐给中国以外的用户\ndocker pull openstoryline\u002Fopenstoryline:v1.0.1\n\n# 从阿里云容器镜像服务拉取镜像\n# 推荐给中国用户使用（速度更快、更稳定）\ndocker pull crpi-6knxem4w8ggpdnsn.cn-shanghai.personal.cr.aliyuncs.com\u002Fopenstoryline\u002Fopenstoryline:v1.0.1\n```\n\n### 启动容器\n```\ndocker run \\\n  -v $(pwd)\u002Fconfig.toml:\u002Fapp\u002Fconfig.toml \\\n  -v $(pwd)\u002Foutputs:\u002Fapp\u002Foutputs \\\n  -v $(pwd)\u002Frun.sh:\u002Fapp\u002Frun.sh \\\n  -p 7860:7860 \\\n  openstoryline\u002Fopenstoryline:v1.0.1\n```\n启动后，可通过 http:\u002F\u002F0.0.0.0:7860 访问 Web 界面。\n\n## 📁 项目结构\n```\nFireRed-OpenStoryline\u002F\n├── 🎯 src\u002Fopen_storyline\u002F           核心应用\n│   ├── mcp\u002F                         🔌 模型上下文协议\n│   ├── nodes\u002F                       🎬 视频处理节点\n│   ├── skills\u002F                      🛠️ 代理技能库\n│   ├── storage\u002F                     💾 代理内存\n│   ├── utils\u002F                       🧰 辅助工具\n│   ├── agent.py                     🤖 构建代理\n│   └── config.py                    ⚙️ 配置管理\n├── 📚 docs\u002F                         文档\n├── 🐳 Dockerfile                    Docker 配置\n├── 💬 prompts\u002F                      LLM 提示模板\n├── 🎨 resource\u002F                     静态资源\n│   ├── bgms\u002F                        背景音乐库\n│   ├── fonts\u002F                       字体文件\n│   ├── script_templates\u002F            视频脚本模板\n│   └── unicode_emojis.json          表情符号列表\n├── 🔧 scripts\u002F                      工具脚本\n├── 🌐 web\u002F                          Web 界面\n├── 🚀 agent_fastapi.py              FastAPI 服务器\n├── 🖥️ cli.py                        命令行界面\n├── ⚙️ config.toml                   主配置文件\n├── 🚀 build_env.sh                  环境构建脚本\n├── 📥 download.sh                   资源下载器\n├── 📦 requirements.txt              运行时依赖\n└── ▶️ run.sh                        启动脚本\n\n```\n\n## 📚 文档\n\n### 📖 教程索引\n\n- [API Key 配置](docs\u002Fsource\u002Fen\u002Fapi-key.md) - 如何配置和管理 API 密钥\n- [使用教程](docs\u002Fsource\u002Fen\u002Fguide.md) - 常见用例及基本操作\n- [常见问题解答](docs\u002Fsource\u002Fen\u002Ffaq.md) - 常见问题解答\n\n## TODO\n\n- [ ] 添加 **配音式视频编辑** 功能。\n- [ ] 增加对 **语音克隆** 的支持\n- [ ] 增加更多 **转场\u002F滤镜\u002F特效** 功能。\n- [ ] 增加 **图像\u002F视频生成与编辑** 能力。\n- [ ] 实现 **GPU 加速** 渲染与高亮选择。\n\n## 致谢\n\n本项目基于以下优秀的开源项目构建：\n\n### 核心依赖\n- [MoviePy](https:\u002F\u002Fgithub.com\u002FZulko\u002Fmoviepy) - 视频编辑库\n- [FFmpeg](https:\u002F\u002Fffmpeg.org\u002F) - 多媒体框架\n- [LangChain](https:\u002F\u002Fwww.langchain.com\u002F) - 提供预构建代理的框架\n\n## 📄 许可证\n\n本项目采用 Apache License 2.0 许可证 - 详情请参阅 [LICENSE](LICENSE) 文件。\n\n## ⭐ 星标历史\n\n\u003Cdiv align=\"center\"> \u003Cp> \u003Cimg width=\"800\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_readme_c640222d99e1.png\" alt=\"Star-history\"> \u003C\u002Fp> \u003C\u002Fdiv>","# FireRed-OpenStoryline 快速上手指南\n\nFireRed-OpenStoryline 是一款将复杂视频创作转化为自然对话的 AI 开源工具。它支持智能素材搜索、剧本生成、配乐推荐及通过自然语言进行视频剪辑，适合初学者及创意开发者。\n\n## 1. 环境准备\n\n在开始之前，请确保您的系统满足以下要求：\n\n*   **操作系统**：Linux 或 macOS（Windows 用户建议使用 WSL2）。\n*   **Python 版本**：≥ 3.11。\n*   **依赖工具**：\n    *   `git`：用于克隆代码库。\n    *   `conda` (推荐 Miniforge) 或 `venv`：用于管理虚拟环境。\n    *   `wget`：用于资源下载（macOS 需通过 Homebrew 安装，Linux 通常预装）。\n\n> **提示**：本项目对显存有一定要求，建议具备 NVIDIA GPU 以获得最佳体验。\n\n## 2. 安装步骤\n\n### 第一步：克隆仓库\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline.git\ncd FireRed-OpenStoryline\n```\n\n### 第二步：创建虚拟环境\n推荐使用 Conda 创建隔离环境（确保 Python 版本为 3.11 或更高）：\n\n```bash\nconda create -n storyline python=3.11\nconda activate storyline\n```\n\n### 第三步：安装依赖与资源\n\n#### 方案 A：自动安装（推荐 Linux\u002FmacOS 用户）\n运行官方提供的脚本，自动完成依赖安装及必要资源下载：\n\n```bash\nsh build_env.sh\n```\n\n#### 方案 B：手动安装\n如果自动脚本执行失败，可按以下步骤手动操作：\n\n1.  **安装 wget** (如未安装)：\n    *   macOS: `brew install wget`\n    *   Ubuntu\u002FDebian: `sudo apt-get install wget`\n\n2.  **安装 Python 依赖**：\n    ```bash\n    pip install -r requirements.txt\n    ```\n    > **国内加速建议**：如遇下载缓慢，可使用清华或阿里镜像源：\n    > `pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple`\n\n3.  **下载模型与资源**：\n    参考项目 `docs` 目录下的详细指引，手动下载所需的字体、音乐素材及预训练模型至指定文件夹。\n\n## 3. 基本使用\n\nFireRed-OpenStoryline 支持两种主要使用方式：直接运行服务或通过 AI Agent 调用。\n\n### 方式一：直接启动服务\n激活环境后，运行启动脚本进入交互界面（具体启动命令视版本更新可能略有不同，通常为）：\n\n```bash\npython main.py\n# 或\nstreamlit run app.py\n```\n启动后，在浏览器访问本地地址，即可通过对话框输入主题（例如：“制作一个关于北京旅行的幽默短视频”），系统将自动搜索素材、生成剧本并合成视频。\n\n### 方式二：通过 AI Agent 调用 (OpenClaw \u002F Claude Code)\n项目内置了 Agent Skills，可让 AI 助手全自动完成安装到生成的流程。\n\n**使用 OpenClaw:**\n```bash\n# 安装技能\nopenclaw skills install openstoryline-install\nopenclaw skills install openstoryline-use\n\n# 使用时只需告诉 Agent：“我想试用 OpenStoryline，帮我安装并制作一个视频。”\n```\n\n**使用 Claude Code:**\n若在项目根目录下运行 Claude Code，可直接调用内置技能：\n```bash\n\u002Fopenstoryline-install\n\u002Fopenstoryline-use\n```\n\n### 💡 进阶提示\n*   **素材库优化**：默认开源素材受版权限制效果基础。建议查阅 `Custom Asset Library Tutorial` 配置商业级字体和音乐，以显著提升视频质感。\n*   **技能存档**：您可以将满意的编辑流程保存为自定义 \"Skill\"，后续只需替换媒体素材即可批量复刻相同风格的视频。","一位独立旅游博主需要在 24 小时内将周末拍摄的数百段零散素材，剪辑成一支风格统一、配乐卡点精准的目的地宣传短片。\n\n### 没有 FireRed-OpenStoryline 时\n- **素材整理耗时巨大**：需人工逐帧浏览数百个视频片段进行筛选和分类，耗费数小时甚至半天时间。\n- **文案与画面割裂**：手动撰写脚本后，需反复调整画面顺序以匹配旁白，难以保证情感节奏的连贯性。\n- **后期调整门槛高**：若想更换背景音乐或调整字幕样式，必须重新在时间轴上手动对齐节拍和修改参数，极易出错。\n- **风格难以复用**：每次制作新视频都要重新摸索调色和剪辑节奏，无法快速复制以往成功的“电影感”风格。\n\n### 使用 FireRed-OpenStoryline 后\n- **智能素材聚合**：只需输入主题，FireRed-OpenStoryline 自动搜索并下载相关素材，同时基于内容理解完成片段分割与归类。\n- **意图驱动叙事**：通过自然语言描述想要的“治愈系”氛围，工具自动生成契合画面的脚本与旁白，并利用 Few-shot 能力完美复刻指定文风。\n- **对话式精细微调**：直接指令“把第二段换成更激昂的音乐”或“字幕字体改为手写体”，FireRed-OpenStoryline 即刻完成剪辑替换与视觉调整。\n- **风格技能沉淀**：将本次满意的剪辑逻辑保存为\"Style Skill\"，下次制作同类视频时一键调用，确保品牌视觉高度一致。\n\nFireRed-OpenStoryline 将繁琐的技术操作转化为直观的创意对话，让创作者从机械劳动中解放，专注于故事本身。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FFireRedTeam_FireRed-OpenStoryline_d3eba797.png","FireRedTeam","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FFireRedTeam_5699dc7e.png","小红书Super Intelligence部门下属基础算法实验室， Xiaohongshu Super Intelligence fundamental technology lab",null,"https:\u002F\u002Fgithub.com\u002FFireRedTeam",[81,85,89,93,97,101],{"name":82,"color":83,"percentage":84},"Python","#3572A5",70.7,{"name":86,"color":87,"percentage":88},"JavaScript","#f1e05a",16.7,{"name":90,"color":91,"percentage":92},"HTML","#e34c26",6.3,{"name":94,"color":95,"percentage":96},"CSS","#663399",5.2,{"name":98,"color":99,"percentage":100},"Shell","#89e051",1,{"name":102,"color":103,"percentage":104},"Dockerfile","#384d54",0.1,1626,160,"2026-04-04T06:39:26","Apache-2.0","Linux, macOS","未说明",{"notes":112,"python":113,"dependencies":114},"自动安装脚本 (build_env.sh) 仅支持 Linux 和 macOS；Windows 用户需参考手动安装步骤。项目支持通过 OpenClaw、Claude Code 等 Agent 技能进行安装和调用。部分功能（如 AI 转场）依赖第三方 AIGC 视频生成服务且成本较高。建议按照教程配置自定义素材库以解锁商业级字体和音乐。",">=3.11",[115,116,117],"conda (推荐 Miniforge)","wget","git",[15,52,13,26],[120,121,122,123,124,125,126,127,128],"agent","video-cut","skills","chatbot","video","video-editing","video-editing-tools","langchain","mcp","2026-03-27T02:49:30.150509","2026-04-06T05:17:36.584131",[132,137,142,147,152,157,162,167],{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},14696,"生成的视频没有声音或无法加载素材怎么办？","如果是视频无法加载或没声音，通常是因为缺少 ffmpeg 或版本不兼容。解决方法：1. 打开 config.toml 文件，将开发者调试模式开关打开以查看更详细的日志；2. 如果不是使用 conda 安装的环境，需要手动安装 ffmpeg。目前功能仅支持保留背景音乐和视频原声，暂不支持口播类型剪辑（预计后续版本支持）。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F13",{"id":138,"question_zh":139,"answer_zh":140,"source_url":141},14697,"程序运行到一半卡住不动，也没有报错信息，如何处理？","这种情况通常发生在“素材内容理解”阶段，该过程比较耗时。如果长时间无进展，请检查是否停在了理解特定 clips 的阶段。建议耐心等待，因为处理多个视频切片（clips）时速度会变慢。如果确实卡死，可尝试提供最后的日志打印信息以便进一步排查。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F46",{"id":143,"question_zh":144,"answer_zh":145,"source_url":146},14698,"Windows 部署文档中提到的文件夹名称是否正确？","文档曾有错误，正确的操作应该是创建 'resource' 文件夹，而不是 '.storyline' 文件夹。README 文档已根据反馈进行了更正，请以最新文档为准。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F48",{"id":148,"question_zh":149,"answer_zh":150,"source_url":151},14699,"为什么 Docker 镜像在普通服务器（amd64 架构）上无法启动？","早期版本的 Docker 镜像仅支持 linux\u002Farm64 架构，导致在大多数 amd64 服务器上报错。维护者已更新镜像，现在支持 amd64 架构。如果遇到此问题，请拉取最新版本的镜像即可解决。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F12",{"id":153,"question_zh":154,"answer_zh":155,"source_url":156},14700,"渲染进度条卡在 99% 或显示不准确是程序出错了吗？","这不是程序错误。工具调用过程存在不确定性，难以实时准确上报时间进度。目前只有“渲染工具”的进度条是真实的，其他阶段（如素材理解）的进度条可能迅速跳到 99% 然后等待。这是因为后端已完成工作但前端状态更新机制所致，请耐心等待任务自然结束，后续版本会优化进度展示形式。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F44",{"id":158,"question_zh":159,"answer_zh":160,"source_url":161},14701,"如何保留视频的原声，而不是被配音完全覆盖？","该问题已在之前的版本中修复（PR #22）。现在的逻辑支持混音，不再是将视频原声整体替换为配音+BGM，而是可以保留视频原声。请确保您使用的是最新版本的代码。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F14",{"id":163,"question_zh":164,"answer_zh":165,"source_url":166},14702,"执行 download.sh 脚本时报语法错误怎么办？","在某些 Shell 环境（如 sh）下直接运行会报语法错误（Syntax error: \"(\" unexpected）。请使用 bash 来执行该脚本，命令为：bash download.sh。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F35",{"id":168,"question_zh":169,"answer_zh":170,"source_url":171},14703,"这个项目包含大模型的训练代码吗？","不包含。FireRed-OpenStoryline 是一套智能剪辑 Agent 框架，主要用于利用现有大模型能力进行视频自动化剪辑，不提供大模型本身的训练代码。","https:\u002F\u002Fgithub.com\u002FFireRedTeam\u002FFireRed-OpenStoryline\u002Fissues\u002F15",[]]