[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-luban-agi--Awesome-AIGC-Tutorials":3,"tool-luban-agi--Awesome-AIGC-Tutorials":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},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,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},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",142651,2,"2026-04-06T23:34:12",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},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。",107888,"2026-04-06T11:32:50",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":10,"last_commit_at":59,"category_tags":60,"status":17},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[35,15,13,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":72,"owner_avatar_url":73,"owner_bio":74,"owner_company":74,"owner_location":74,"owner_email":74,"owner_twitter":74,"owner_website":74,"owner_url":75,"languages":74,"stars":76,"forks":77,"last_commit_at":78,"license":79,"difficulty_score":80,"env_os":81,"env_gpu":82,"env_ram":82,"env_deps":83,"category_tags":87,"github_topics":89,"view_count":32,"oss_zip_url":74,"oss_zip_packed_at":74,"status":17,"created_at":103,"updated_at":104,"faqs":105,"releases":106},4792,"luban-agi\u002FAwesome-AIGC-Tutorials","Awesome-AIGC-Tutorials","Curated tutorials and resources for Large Language Models, AI Painting, and more. ","Awesome-AIGC-Tutorials 是一个精心策划的 AIGC（生成式人工智能）学习资源库，旨在为想要深入探索大语言模型、AI 绘画及相关领域的用户提供一个系统化的知识入口。面对当前 AI 技术迭代迅速、优质教程分散且难以筛选的痛点，该项目通过人工甄选的方式，将零散的课程、论文、实践指南和系统架构资料整合成结构清晰的知识体系，帮助用户高效获取从理论基础到落地应用的全方位内容。\n\n无论是刚入门的初学者，还是寻求进阶的开发者、研究人员或设计师，都能在这里找到适合自己的学习路径。资源覆盖范围广泛，不仅包含吴恩达\"AI for Everyone\"等通识课程，还深入探讨了提示词工程、Stable Diffusion 原理、多模态学习以及 AI 系统架构等专业议题。其独特亮点在于持续更新的机制，及时收录全球顶尖高校（如微软、谷歌、沃顿商学院等）发布的最新课程与研讨会资料，并明确标注了学习难度和形式（视频或文档），让用户能根据自身背景精准选择。如果你希望系统化地掌握生成式 AI 的核心技能，Awesome-AIGC-Tutorials 将是你值得信赖的导航指南。","# Awesome AIGC Tutorials \n\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fluban-agi\u002Fawesome-aigc-tutorials) \n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT) \n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fluban-agi\u002FAwesome-AIGC-Tutorials?color=green)\n[![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluban-agi\u002FAwesome-AIGC-Tutorials?style=social)](https:\u002F\u002Fgithub.com\u002Fluban-agi\u002FAwesome-AIGC-Tutorials)\n\nEnglish | [中文版](README_zh.md)\n\n\nAwesome AIGC Tutorials houses a curated collection of tutorials and resources spanning across Large Language Models, AI Painting, and related fields. Discover in-depth insights and knowledge catered for both beginners and advanced AI enthusiasts.\n\n## 🔔 Recent Updates\n\n- [2024-02-18] - 🌈 Added new course: [CSCI-GA.3033-102 Special Topic - Learning with Large Language and Vision Models](https:\u002F\u002Fwww.sainingxie.com\u002Fllvm-fall23\u002F) in Multimodal.\n- [2024-02-14] - 💬 Added new course: [CS11-711 Advanced Natural Language Processing](https:\u002F\u002Fphontron.com\u002Fclass\u002Fanlp2024\u002F) in Large Language Models.\n- [2024-02-14] - 💬 Added new seminar: [AI-Systems (LLM Edition) 294-162](https:\u002F\u002Flearning-systems.notion.site\u002Flearning-systems\u002FAI-Systems-LLM-Edition-294-162-Fall-2023-661887583bd340fa851e6a8da8e29abb) in AI System.\n\n## 🌱 How to Contribute\n\nWe warmly welcome contributions from everyone, whether you've found a typo, a bug, have a suggestion, or want to share a resource related to AIGC. For detailed guidelines on how to contribute, please see our [CONTRIBUTING.md](CONTRIBUTING.md) file.\n\n## 📜 Content\n- [👋 Introduction](#-introduction)\n- [💬 Large Language Models](#-large-language-models)\n  - [💡 Prompt Engineering](#-prompt-engineering)\n  - [🔧 LLMs in Practice](#-llms-in-practice)\n  - [🔬 Theory of LLMs](#-theory-of-llms)\n- [🎨 AI Painting](#-ai-painting)\n  - [🧑‍🎨 Art Fundamentals and AI Painting Techniques](#-art-fundamentals-and-ai-painting-techniques)\n  - [🌊 Stable Diffusion Principles and Applications](#-stable-diffusion-principles-and-applications)\n- [🔊 AI Audio](#-ai-audio)\n- [🌈 Multimodal](#-multimodal)\n- [🧠 Deep Learning](#-deep-learning)\n- [💻 AI System](#-ai-system)\n- [🗂 Miscellaneous](#-miscellaneous)\n  - [✨ Star History](#-star-history)\n  - [🤝 Friendship Links](#-friendship-links)\n\n## 👋 Introduction\n- [AI for Everyone - Andrew Ng](https:\u002F\u002Fwww.deeplearning.ai\u002Fcourses\u002Fai-for-everyone\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - \"AI for Everyone\" is a beginner's guide to understanding AI's practical applications, its limitations, and its societal impact, ideal for business professionals and leaders alike.\n- [Practical AI for Teachers and Students - Wharton School](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLwRdpYzPkkn302_rL5RrXvQE8j0jLP02j)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Wharton Interactive's crash course delves into the mechanics and impacts of LLMs, spotlighting models like OpenAI's ChatGPT4, Microsoft's Bing in Creative Mode, and Google's Bard. \n- [Artificial Intelligence for Beginners - Microsoft](https:\u002F\u002Fmicrosoft.github.io\u002FAI-For-Beginners\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - This 12-week Microsoft curriculum dives deep into AI methodologies, spanning symbolic AI to neural networks, while highlighting TensorFlow and PyTorch frameworks, yet omits business applications, classic machine learning, and certain cloud-specific topics.\n- [Generative AI learning path - Google Cloud](https:\u002F\u002Fwww.cloudskillsboost.google\u002Fjourneys\u002F118)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This learning path offers a comprehensive journey from the basics of Large Language Models to deploying generative AI solutions on Google Cloud. \n\n## 💬 Large Language Models\n\n### 💡 Prompt Engineering\n- [ChatGPT Prompt Engineering for Developers - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Fchatgpt-prompt-engineering-for-developers\u002F) ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - Co-taught by OpenAI and DeepLearning.AI, this course guides learners in leveraging Large Language Models for tasks like summarizing and text transformation, with hands-on experiences in a Jupyter notebook environment.\n- [Building Systems with the ChatGPT API - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Fbuilding-systems-with-chatgpt\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - Led by experts from OpenAI and DeepLearning.AI, this course teaches automating workflows using language models, creating prompt chains, integrating Python, and designing chatbots, all through hands-on Jupyter notebook exercises with just basic Python knowledge required.\n- [LangChain for LLM Application Development - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Flangchain-for-llm-application-development\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - Guided by the creator of LangChain and Andrew Ng, this course dives into advanced LLM techniques like chaining operations and using models as reasoning agents, empowering learners to craft robust applications quickly with foundational Python knowledge.\n- [LangChain: Chat with Your Data - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Flangchain-chat-with-your-data\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - Delve into Retrieval Augmented Generation and chatbot creation based on document content with LangChain, covering data loading, splitting, embeddings, advanced retrieval techniques, and interactive chatbot building, designed for Python-savvy developers keen on harnessing Large Language Models.\n- [Prompt Engineering for ChatGPT - Vanderbilt University](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fprompt-engineering?utm_medium=sem&utm_source=gg&utm_campaign=B2C_EMEA_prompt-engineering_vanderbilt_FTCOF_learn_country-GB-country-UK&campaignid=20462816306&adgroupid=157715342052&device=c&keyword=prompt%20engineering%20coursera&matchtype=b&network=g&devicemodel=&adposition=&creativeid=670151312123&hide_mobile_promo&gclid=Cj0KCQjwuZGnBhD1ARIsACxbAVg8RCaUF0lwFyVnMuP7T7bHoH0jST0XXhQ3S1vmDxtZc8O1WlJ8FXQaAtG-EALw_wcB)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Unlock the potential of Large Language Models like ChatGPT by mastering prompt engineering, transitioning from basic to sophisticated prompts, enabling diverse applications ranging from writing to simulation, suitable for anyone with basic computer skills.\n- [Prompt Engineering Guide - DAIR.AI](https:\u002F\u002Fwww.promptingguide.ai\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green) \n  - This guide introduces Prompt Engineering, a discipline that optimizes interactions with Large Language Models, offering extensive resources, research, and tools.\n- [Learn Prompting](https:\u002F\u002Flearnprompting.org\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - Dive into a beginner-friendly guide on Generative AI and Prompt Engineering, offering insights from industry giants, and explore how these tools revolutionize content creation and the future of work.\n- [LangChain AI Handbook - James Briggs and Francisco Ingham](https:\u002F\u002Fwww.pinecone.io\u002Flearn\u002Fseries\u002Flangchain\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBook-%2391672c)\n  - Explore the transformative world of LangChain, mastering core components, crafting effective prompts, and harnessing advanced AI agents, conversational memories, and custom tools for cutting-edge applications. \n\n### 🔧 LLMs in Practice\n- [LLM Bootcamp - The Full Stack](https:\u002F\u002Ffullstackdeeplearning.com\u002Fllm-bootcamp\u002Fspring-2023\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Delve deep into prompt engineering, LLM operations, user experience design for language interfaces, augmented language model techniques, foundational LLM insights, hands-on projects, and the future of LLMs, complemented by expert talks from industry leaders on training and agent design.\n- [Finetuning Large Language Models - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Ffinetuning-large-language-models\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - Learn the techniques of finetuning large language models (LLMs) with Sharon Zhou, gaining expertise in data preparation, training, and updating neural net weights for improved results tailored to your data.\n- [CS25: Transformers United V3 - Stanford University](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002Findex.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This course delves into the transformative role of Transformers in deep learning, particularly their impact on the advancement of language models like ChatGPT and GPT-4.\n- [Learn the fundamentals of generative AI for real-world applications - AWS x DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fcourses\u002Fgenerative-ai-with-llms\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This course, in partnership with AWS, offers deep insights into generative AI and Large Language Models (LLMs). Participants will learn the mechanics, optimization, and real-world applications of LLMs from AWS AI experts. Suitable for professionals in AI and machine learning, with a Coursera certificate upon completion. Basic Python and machine learning knowledge recommended.\n\n### 🔬 Theory of LLMs\n- [CS324 - Advances in Foundation Models - Stanford University](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2023\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  - CS 324 delves into foundation models like GPT-3 and DALL-E, covering their principles, systems, ethics, and application, and culminates in a hands-on research project or application design.\n- [CS11-711 Advanced Natural Language Processing - Carnegie Mellon University](https:\u002F\u002Fphontron.com\u002Fclass\u002Fanlp2024\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - CMU's Advanced NLP course explores modern neural methods for understanding and innovating in natural language processing.\n- [CS 601.471\u002F671 NLP: Self-supervised Models - Johns Hopkins University](https:\u002F\u002Fself-supervised.cs.jhu.edu\u002Fsp2024\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - This course offers an in-depth exploration of self-supervised learning techniques for NLP, training students to design and implement neural network models using PyTorch, with a focus on various language model architectures.\n- [11-667: Large Language Models Methods and Applications - Carnegie Mellon University](https:\u002F\u002Fcmu-llms.org\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - This graduate course offers a comprehensive overview of large language models (LLMs), covering basics, emergent capabilities, applications, scaling techniques, deployment concerns, and future challenges, equipping students for research and applications in the AI era.\n- [CS224N: Natural Language Processing with Deep Learning - Stanford University](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This course provides a comprehensive insight into Deep Learning for NLP using PyTorch, emphasizing end-to-end neural models, eliminating the need for task-specific feature engineering, and equipping students with the skills to craft their own neural network solutions.\n- [TinyML and Efficient Deep Learning Computing - Massachusetts Institute of Technology](https:\u002F\u002Fhanlab.mit.edu\u002Fcourses\u002F2023-fall-65940?schedule)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This course explores efficient AI computing techniques for deep learning on constrained devices, covering model compression, pruning, quantization, architecture search, distributed training, and quantum machine learning, with hands-on deployment of large models like LLaMA 2 on laptops.\n- [Speech and Language Processing - Dan Jurafsky and James H. Martin](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBook-%2391672c)\n  - Authored by leading experts in the field, this authoritative text provides an in-depth exploration of the algorithms and mathematical models for modern natural language processing and speech recognition, and is continually updated to reflect the rapid advancements in the NLP domain.\n- [COS 597G (Fall 2022): Understanding Large Language Models - Princeton University](https:\u002F\u002Fwww.cs.princeton.edu\u002Fcourses\u002Farchive\u002Ffall22\u002Fcos597G\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - An advanced exploration into the transformative realm of LLMs, discussing state-of-the-art models, their profound capabilities, and associated challenges, with an emphasis on in-depth research, ethical considerations, and hands-on project experience, tailored for seasoned students versed in machine learning and deep NLP frameworks.\n\n## 🎨 AI Painting\n\n### 🧑‍🎨 Art Fundamentals and AI Painting Techniques\n- [Lecture Series: An interesting topic every week on the fundamentals of art - Niji Academy](https:\u002F\u002Fwww.niji.academy\u002Fwork\u002Flecture)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  - Niji Academy blends art fundamentals with AI, elevating painting skills and speeding up art learning.\n \n### 🌊 Stable Diffusion Principles and Applications\n\n- [How Diffusion Models Work - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Fhow-diffusion-models-work\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow) ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - Master generative AI in 'How Diffusion Models Work', an intermediate course by Sharon Zhou, where you'll craft diffusion models from scratch, enriched with hands-on coding and labs, ideal for those proficient in Python, Tensorflow, or Pytorch.\n- [Hugging Face Diffusion Models Course](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusion-models-class)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - The Hugging Face course offers an in-depth look into diffusion models, guiding participants through media generation, hands-on training, and customization using the Diffusers library, with a foundational understanding of Python and Deep Learning essential for the best experience.\n- [Practical Deep Learning for Coders part 2: Deep Learning Foundations to Stable Diffusion - fast.ai](https:\u002F\u002Fcourse.fast.ai\u002FLessons\u002Fpart2.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This course offers an in-depth exploration of Stable Diffusion algorithms, covering advanced deep learning techniques and hands-on projects using PyTorch, empowering students with expertise in cutting-edge diffusion models. \n\n## 🔊 AI Audio\n- [Hugging Face Audio Course](https:\u002F\u002Fhuggingface.co\u002Flearn\u002Faudio-course\u002Fchapter0\u002Fintroduction)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow) \n  - The Hugging Face Audio course teaches how to use transformers for various audio tasks, from speech recognition to generating speech from text, combining theory with hands-on exercises for learners familiar with deep learning.\n- [CS224S: Spoken Language Processing - Stanford University](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224s\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - An immersive course on spoken language technology, covering dialog systems, deep learning in speech recognition and synthesis, with hands-on projects using modern tools like PyTorch, Alexa Skills Kit, and SpeechBrain, culminating in student-driven research or system design projects. \n \n## 🌈 Multimodal\n- [CSCI-GA.3033-102 Special Topic - Learning with Large Language and Vision Models](https:\u002F\u002Fwww.sainingxie.com\u002Fllvm-fall23\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - Graduate course on the impact of large language and vision models, covering multimodal and generative AI, and preparing students for AI research.\n- [Tutorial on MultiModal Machine Learning (ICML 2023) - Carnegie Mellon University](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fmmml-tutorial\u002Ficml2023\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This course offers an in-depth look at Multimodal Machine Learning, drawing insights from the latest edition of a survey paper and CMU's academic teachings, addressing its unique challenges and future directions. \n- [11-777: MultiModal Machine Learning (Fall 2022) - Carnegie Mellon University](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fmmml-course\u002Ffall2022\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - This course delves into Multimodal Machine Learning (MMML), covering its mathematical foundations, state-of-the-art probabilistic models, and key challenges, while highlighting recent applications and techniques such as multimodal transformers and neuro-symbolic models. \n- [11-877: Advanced Topics in MultiModal Machine Learning (Fall 2022) - Carnegie Mellon University](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fadv-mmml-course\u002Fspring2022\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - This course explores Multimodal Machine Learning (MMML), covering technical challenges and recent achievements. It emphasizes critical thinking and future research trends, with weekly updates, discussion probes, and research highlights on the course website. \n\n## 🧠 Deep Learning\n- [Neural Networks\u002FDeep Learning - StatQuest](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLblh5JKOoLUIxGDQs4LFFD--41Vzf-ME1)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Discover the intricacies of Neural Networks in this highly popular YouTube playlist, seamlessly blending informative graphics with expert teachings, captivating countless students from basics to advanced image classification with Convolutional Neural Networks.\n- [Neural Networks - 3Blue1Brown](https:\u002F\u002Fwww.3blue1brown.com\u002Ftopics\u002Fneural-networks)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 3Blue1Brown unveils the magic of neural networks through vivid animations and clear explanations, diving deep into hand-written digit recognition, the nuances of gradient descent, and the intricate calculus behind backpropagation. \n- [Neural Networks: Zero to Hero - Andrej Karpathy](https:\u002F\u002Fkarpathy.ai\u002Fzero-to-hero.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Andrej Karpathy's course guides students from the foundational backpropagation to advanced neural networks like GPT, emphasizing language models as a versatile gateway to mastering deep learning, with prerequisites in Python programming and basic math. \n- [Practical Deep Learning for Coders - fast.ai](https:\u002F\u002Fcourse.fast.ai\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Practical Deep Learning for Coders 2022 is a free course offering hands-on experience in building, training, and deploying deep learning models across various domains using tools like PyTorch and fastai, suitable for those with coding knowledge and without the need for advanced math. \n- [Deep Learning Specialization - Andrew Ng](https:\u002F\u002Fwww.deeplearning.ai\u002Fcourses\u002Fdeep-learning-specialization\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Andrew Ng's Deep Learning Specialization is a top-rated, self-paced program on Coursera with over 1 million learners, offering clear modules and practical techniques in AI, supported by a vast community and breaking down the latest in machine learning into understandable content.\n- [6.S191: Introduction to Deep Learning - Massachusetts Institute of Technology](http:\u002F\u002Fintrotodeeplearning.com\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - MIT's intensive bootcamp on deep learning fundamentals, covering applications from computer vision to biology, with hands-on TensorFlow practice and a culminating project competition. Basic calculus and linear algebra knowledge required; Python experience beneficial. \n- [CS25: Transformers United V2 - Stanford University](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Explore the transformative power of transformers in deep learning across diverse domains, from NLP to biology, in a seminar featuring expert lectures, breakthrough discussions, and insights from leading researchers, aiming to foster understanding and cross-collaborative innovation.\n- [Deep Learning Lecture Series 2020 - DeepMind x University College London](https:\u002F\u002Fwww.deepmind.com\u002Flearning-resources\u002Fdeep-learning-lecture-series-2020)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - DeepMind presents a 12-lecture series on Deep Learning, diving from foundational topics to advanced techniques, encompassing areas from object recognition to responsible AI innovation, all delivered by leading research experts.\n- [Reinforcement Learning Lecture Series 2021 - DeepMind x University College London](https:\u002F\u002Fwww.deepmind.com\u002Flearning-resources\u002Freinforcement-learning-lecture-series-2021)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - DeepMind and UCL present a comprehensive 13-lecture series on modern reinforcement learning, from foundational concepts to advanced deep RL techniques, led by expert researchers Hado van Hasselt, Diana Borsa, and Matteo Hessel.\n  \n## 💻 AI System\n- [AI-Sys-Sp22 Machine Learning Systems - University of California, Berkeley](https:\u002F\u002Fucbrise.github.io\u002Fcs294-ai-sys-sp22\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - Delve into the symbiotic relationship between cutting-edge AI applications and the systems supporting them, exploring advancements in hardware, software, and AI-driven optimization techniques, through lectures, discussions, and collaborative hands-on projects.\n- [Deep Learning Systems: Algorithms and Implementation - Tianqi Chen, Zico Kolter](https:\u002F\u002Fdlsyscourse.org\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Explore the foundations of deep learning systems by constructing a complete library, understanding every layer from model design to efficient algorithms, utilizing Python and C\u002FC++. \n- [CS 329S: Machine Learning Systems Design - Stanford University](https:\u002F\u002Fstanford-cs329s.github.io\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - Master the intricacies of designing robust, scalable, and deployable machine learning systems, focusing on stakeholders, evolving requirements, and holistic system design, while addressing critical issues like privacy, fairness, and security.\n- [AI-Systems (LLM Edition) 294-162 - University of California, Berkeley](https:\u002F\u002Flearning-systems.notion.site\u002Flearning-systems\u002FAI-Systems-LLM-Edition-294-162-Fall-2023-661887583bd340fa851e6a8da8e29abb)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - This course delves into the nexus of hardware\u002Fsoftware advancements and generative AI, emphasizing how these innovations propel the scaling and capabilities of AI models.\n- [15-849: Machine Learning Systems - Carnegie Mellon University](https:\u002F\u002Fwww.cs.cmu.edu\u002F~zhihaoj2\u002F15-849\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - Dive into the architecture of modern ML systems, unraveling the journey from high-level model design to low-level kernel execution on heterogeneous hardware, while uncovering the principles and challenges of next-gen ML applications and platforms. \n- [Computer Science 598D - Systems and Machine Learning - Princeton University](https:\u002F\u002Fwww.cs.princeton.edu\u002Fcourses\u002Farchive\u002Fspring21\u002Fcos598D\u002Fgeneral.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - Explore the synergy between systems and machine learning by dissecting recent research on efficient ML hardware\u002Fsoftware and applying ML to system design, culminating in hands-on projects and deep discussions for graduate students.\n\n## 🗂 Miscellaneous\n\n### ✨ Star History\n[![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fluban-agi_Awesome-AIGC-Tutorials_readme_e33a76a5fdb9.png)](https:\u002F\u002Fstar-history.com\u002F#luban-agi\u002FAwesome-AIGC-Tutorials&Date)\n\n### 🤝 Friendship Links\n- [WayToAGI](http:\u002F\u002Fwaytoagi.com\u002F)\n  - WaytoAGI.com is the most comprehensive Chinese resource hub for AIGC, guiding users on an optimized learning journey to understand and harness the power of AI.\n- [Codefuse-ChatBot](https:\u002F\u002Fgithub.com\u002Fcodefuse-ai\u002Fcodefuse-chatbot)\n  - Codefuse-ChatBot is an open-source AI smart assistant designed to support the software development lifecycle with conversational access to tools, knowledge, and platform integration.\n- [Codefuse DevOps Eval](https:\u002F\u002Fgithub.com\u002Fcodefuse-ai\u002Fcodefuse-devops-eval)\n  - DevOps-Eval is a GitHub repository offering a specialized suite for evaluating and improving foundation models in the DevOps sector, including a rich set of AIOps exercises.\n","# 令人惊叹的 AIGC 教程 \n\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fluban-agi\u002Fawesome-aigc-tutorials) \n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT) \n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fluban-agi\u002FAwesome-AIGC-Tutorials?color=green)\n[![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fluban-agi\u002FAwesome-AIGC-Tutorials?style=social)](https:\u002F\u002Fgithub.com\u002Fluban-agi\u002FAwesome-AIGC-Tutorials)\n\n英语 | [中文版](README_zh.md)\n\n\n“令人惊叹的 AIGC 教程”收录了一系列精心挑选的教程和资源，涵盖大型语言模型、AI 绘画及相关领域。无论你是初学者还是高级 AI 爱好者，都能在这里找到深入的见解与知识。\n\n## 🔔 最新动态\n\n- [2024-02-18] - 🌈 新增课程：多模态领域的 [CSCI-GA.3033-102 特别专题——使用大型语言和视觉模型学习](https:\u002F\u002Fwww.sainingxie.com\u002Fllvm-fall23\u002F)。\n- [2024-02-14] - 💬 新增课程：大型语言模型领域的 [CS11-711 高级自然语言处理](https:\u002F\u002Fphontron.com\u002Fclass\u002Fanlp2024\u002F)。\n- [2024-02-14] - 💬 新增研讨会：AI 系统领域的 [AI-Systems (LLM Edition) 294-162](https:\u002F\u002Flearning-systems.notion.site\u002Flearning-systems\u002FAI-Systems-LLM-Edition-294-162-Fall-2023-661887583bd340fa851e6a8da8e29abb)。\n\n## 🌱 如何贡献\n\n我们热烈欢迎所有人的参与！无论是发现错别字、漏洞，提出建议，还是分享与 AIGC 相关的资源，都欢迎加入我们的行列。有关如何贡献的详细说明，请参阅我们的 [CONTRIBUTING.md](CONTRIBUTING.md) 文件。\n\n## 📜 内容\n- [👋 引言](#-introduction)\n- [💬 大型语言模型](#-large-language-models)\n  - [💡 提示工程](#-prompt-engineering)\n  - [🔧 大型语言模型实战](#-llms-in-practice)\n  - [🔬 大型语言模型理论](#-theory-of-llms)\n- [🎨 AI 绘画](#-ai-painting)\n  - [🧑‍🎨 艺术基础与 AI 绘画技巧](#-art-fundamentals-and-ai-painting-techniques)\n  - [🌊 Stable Diffusion 原理与应用](#-stable-diffusion-principles-and-applications)\n- [🔊 AI 音频](#-ai-audio)\n- [🌈 多模态](#-multimodal)\n- [🧠 深度学习](#-deep-learning)\n- [💻 AI 系统](#-ai-system)\n- [🗂 杂项](#-miscellaneous)\n  - [✨ 星标历史](#-star-history)\n  - [🤝 友情链接](#-friendship-links)\n\n## 👋 引言\n- [面向所有人的人工智能——吴恩达](https:\u002F\u002Fwww.deeplearning.ai\u002Fcourses\u002Fai-for-everyone\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - “面向所有人的人工智能”是一本面向初学者的指南，旨在帮助大家理解人工智能的实际应用、局限性及其社会影响，非常适合企业专业人士和领导者。\n- [教师与学生实用人工智能——沃顿商学院](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLwRdpYzPkkn302_rL5RrXvQE8j0jLP02j)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 沃顿互动推出的速成课程深入探讨了大型语言模型的机制及其影响，重点介绍了 OpenAI 的 ChatGPT4、微软必应的创意模式以及谷歌的 Bard 等模型。\n- [面向初学者的人工智能——微软](https:\u002F\u002Fmicrosoft.github.io\u002FAI-For-Beginners\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 这套由微软提供的为期12周的课程深入讲解了人工智能的各种方法论，从符号人工智能到神经网络，并着重介绍了 TensorFlow 和 PyTorch 框架，但未涉及商业应用、经典机器学习及某些特定于云的技术主题。\n- [生成式 AI 学习路径——谷歌云](https:\u002F\u002Fwww.cloudskillsboost.google\u002Fjourneys\u002F118)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 该学习路径提供了一个全面的旅程，从大型语言模型的基础知识开始，逐步过渡到在谷歌云上部署生成式 AI 解决方案。\n\n## 💬 大型语言模型\n\n### 💡 提示工程\n- [面向开发者的 ChatGPT 提示工程 - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Fchatgpt-prompt-engineering-for-developers\u002F) ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - 由 OpenAI 和 DeepLearning.AI 联合授课，本课程指导学习者利用大型语言模型完成摘要生成、文本转换等任务，并在 Jupyter 笔记本环境中进行实践操作。\n- [使用 ChatGPT API 构建系统 - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Fbuilding-systems-with-chatgpt\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - 由 OpenAI 和 DeepLearning.AI 的专家主讲，本课程教授如何使用语言模型自动化工作流、构建提示链、集成 Python 以及设计聊天机器人，所有内容均通过 Jupyter 笔记本的动手练习实现，仅需具备基础的 Python 知识。\n- [LangChain 用于 LLM 应用开发 - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Flangchain-for-llm-application-development\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - 由 LangChain 的创始人与吴恩达共同指导，本课程深入探讨高级 LLM 技术，如操作链化及将模型用作推理代理，使学习者能够在掌握基础 Python 知识的前提下快速构建稳健的应用程序。\n- [LangChain：与你的数据对话 - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Flangchain-chat-with-your-data\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - 使用 LangChain 深入了解检索增强生成技术及基于文档内容的聊天机器人开发，涵盖数据加载、分割、嵌入、高级检索技术以及交互式聊天机器人的构建，专为精通 Python 并希望充分利用大型语言模型的开发者设计。\n- [ChatGPT 提示工程 - 范德堡大学](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fprompt-engineering?utm_medium=sem&utm_source=gg&utm_campaign=B2C_EMEA_prompt-engineering_vanderbilt_FTCOF_learn_country-GB-country-UK&campaignid=20462816306&adgroupid=157715342052&device=c&keyword=prompt%20engineering%20coursera&matchtype=b&network=g&devicemodel=&adposition=&creativeid=670151312123&hide_mobile_promo&gclid=Cj0KCQjwuZGnBhD1ARIsACxbAVg8RCaUF0lwFyVnMuP7T7bHoH0jST0XXhQ3S1vmDxtZc8O1WlJ8FXQaAtG-EALw_wcB)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 通过掌握提示工程，释放 ChatGPT 等大型语言模型的潜力，从基础提示逐步过渡到复杂提示，从而实现从写作到模拟等多种应用，适合任何具备基本计算机技能的人。\n- [提示工程指南 - DAIR.AI](https:\u002F\u002Fwww.promptingguide.ai\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green) \n  - 本指南介绍了提示工程这一优化与大型语言模型交互的学科，并提供了丰富的资源、研究和工具。\n- [Learn Prompting](https:\u002F\u002Flearnprompting.org\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 这是一份面向初学者的生成式 AI 和提示工程指南，汇集了行业巨头的见解，探讨这些工具如何革新内容创作和未来的工作方式。\n- [LangChain AI 手册 - James Briggs 和 Francisco Ingham](https:\u002F\u002Fwww.pinecone.io\u002Flearn\u002Fseries\u002Flangchain\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBook-%2391672c)\n  - 探索 LangChain 带来的变革性世界，掌握核心组件、编写有效提示，并利用先进的 AI 代理、会话记忆和自定义工具来构建尖端应用。\n\n### 🔧 LLM 实践\n- [LLM 训练营 - The Full Stack](https:\u002F\u002Ffullstackdeeplearning.com\u002Fllm-bootcamp\u002Fspring-2023\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 深入探讨提示工程、LLM 运算、语言界面的用户体验设计、增强型语言模型技术、LLM 的基础知识、动手项目以及 LLM 的未来发展方向，并辅以行业领袖关于训练和智能体设计的专家讲座。\n- [微调大型语言模型 - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Ffinetuning-large-language-models\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - 在 Sharon Zhou 的指导下学习微调大型语言模型（LLM）的技术，掌握数据准备、训练以及更新神经网络权重的方法，以针对您的数据获得更好的效果。\n- [CS25：Transformer 联盟 V3 - 斯坦福大学](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002Findex.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 本课程深入探讨 Transformer 在深度学习中的变革性作用，尤其是其对 ChatGPT 和 GPT-4 等语言模型发展的推动作用。\n- [学习生成式 AI 的基础知识及其在现实世界中的应用 - AWS x DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fcourses\u002Fgenerative-ai-with-llms\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 本课程与 AWS 合作，深入解析生成式 AI 和大型语言模型（LLMs）。参与者将从 AWS 的 AI 专家那里学习 LLM 的工作机制、优化方法以及实际应用。适合人工智能和机器学习领域的专业人士，完成课程后可获得 Coursera 证书。建议具备基础的 Python 和机器学习知识。\n\n### 🔬 大型语言模型理论\n- [CS324 - 基础模型前沿 - 斯坦福大学](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2023\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  - CS 324 深入探讨 GPT-3 和 DALL-E 等基础模型，涵盖其原理、系统架构、伦理问题及应用，并以一个实践性的研究项目或应用设计作为课程的最终成果。\n- [CS11-711 高级自然语言处理 - 卡内基梅隆大学](https:\u002F\u002Fphontron.com\u002Fclass\u002Fanlp2024\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - CMU 的高级 NLP 课程探索用于理解和创新自然语言处理的现代神经网络方法。\n- [CS 601.471\u002F671 NLP：自监督模型 - 约翰霍普金斯大学](https:\u002F\u002Fself-supervised.cs.jhu.edu\u002Fsp2024\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 本课程深入探讨 NLP 中的自监督学习技术，培养学生使用 PyTorch 设计和实现神经网络模型的能力，重点在于各种语言模型架构。\n- [11-667：大型语言模型方法与应用 - 卡内基梅隆大学](https:\u002F\u002Fcmu-llms.org\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 这门研究生课程全面概述了大型语言模型（LLMs），内容包括基础知识、涌现能力、应用、扩展技术、部署考量以及未来挑战，旨在为学生在 AI 时代的研究和应用做好准备。\n- [CS224N：深度学习驱动的自然语言处理 - 斯坦福大学](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 本课程通过 PyTorch 提供对 NLP 中深度学习的全面洞察，强调端到端的神经网络模型，无需针对特定任务进行特征工程，使学生具备构建自有神经网络解决方案的能力。\n- [TinyML 与高效深度学习计算 - 马萨诸塞理工学院](https:\u002F\u002Fhanlab.mit.edu\u002Fcourses\u002F2023-fall-65940?schedule)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 本课程探讨在资源受限设备上进行深度学习的高效 AI 计算技术，内容涵盖模型压缩、剪枝、量化、架构搜索、分布式训练以及量子机器学习等，并提供动手实践机会，在笔记本电脑上部署 LLaMA 2 等大型模型。\n- [语音与语言处理 - 丹·朱拉夫斯基和詹姆斯·H·马丁](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBook-%2391672c)\n  - 由该领域顶尖专家撰写，这本权威教材深入探讨了现代自然语言处理和语音识别的算法与数学模型，并不断更新以反映 NLP 领域的快速进展。\n- [COS 597G（2022 年秋季）：理解大型语言模型 - 普林斯顿大学](https:\u002F\u002Fwww.cs.princeton.edu\u002Fcourses\u002Farchive\u002Ffall22\u002Fcos597G\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - 一门深入探索 LLM 变革性领域的高级课程，讨论最先进的一系列模型、它们的强大功能及其相关挑战，重点在于深入研究、伦理考量和实践项目经验，专为精通机器学习和深度 NLP 框架的资深学生设计。\n\n## 🎨 AI 绘画\n\n### 🧑‍🎨 艺术基础与 AI 绘画技巧\n- [讲座系列：每周一个有趣的艺术基础主题 - Niji Academy](https:\u002F\u002Fwww.niji.academy\u002Fwork\u002Flecture)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  - Niji Academy 将艺术基础与 AI 相结合，提升绘画技能并加速艺术学习进程。\n\n### 🌊 Stable Diffusion 原理与应用\n\n- [扩散模型的工作原理 - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Fhow-diffusion-models-work\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow) ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - 在 Sharon Zhou 主讲的中级课程《扩散模型的工作原理》中掌握生成式 AI 技术，亲手从零开始构建扩散模型，辅以丰富的动手编码和实验环节，适合熟练掌握 Python、TensorFlow 或 PyTorch 的学员。\n- [Hugging Face 扩散模型课程](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusion-models-class)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)\n  - Hugging Face 的课程深入讲解扩散模型，指导学员利用 Diffusers 库进行媒体生成、动手训练和模型定制，具备 Python 和深度学习的基础知识将有助于获得最佳学习体验。\n- [面向程序员的实用深度学习第 2 部分：深度学习基础至 Stable Diffusion - fast.ai](https:\u002F\u002Fcourse.fast.ai\u002FLessons\u002Fpart2.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 本课程深入探讨 Stable Diffusion 算法，涵盖先进的深度学习技术及基于 PyTorch 的实践项目，帮助学生掌握尖端扩散模型的专业知识。\n\n## 🔊 AI 音频\n- [Hugging Face 音频课程](https:\u002F\u002Fhuggingface.co\u002Flearn\u002Faudio-course\u002Fchapter0\u002Fintroduction)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - Hugging Face 音频课程教授如何使用 Transformer 模型完成各类音频任务，从语音识别到文本转语音，将理论与动手练习相结合，适合熟悉深度学习的学习者。\n- [CS224S：口语处理 - 斯坦福大学](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224s\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 一门沉浸式的口语处理技术课程，涵盖对话系统、语音识别与合成中的深度学习等内容，并通过 PyTorch、Alexa Skills Kit 和 SpeechBrain 等现代工具开展实践项目，最终以学生主导的研究或系统设计项目收尾。\n\n## 🌈 多模态\n- [CSCI-GA.3033-102 特别专题——大型语言与视觉模型的学习](https:\u002F\u002Fwww.sainingxie.com\u002Fllvm-fall23\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 研究生课程，探讨大型语言和视觉模型的影响，涵盖多模态与生成式AI，并为学生从事AI研究做好准备。\n- [多模态机器学习教程（ICML 2023）——卡内基梅隆大学](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fmmml-tutorial\u002Ficml2023\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 本课程深入探讨多模态机器学习，结合最新版综述论文及卡内基梅隆大学的学术成果，剖析其独特挑战与未来发展方向。\n- [11-777：多模态机器学习（2022年秋季）——卡内基梅隆大学](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fmmml-course\u002Ffall2022\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 本课程深入研究多模态机器学习（MMML），涵盖其数学基础、最先进概率模型及关键挑战，同时介绍近期应用与技术，如多模态Transformer和神经符号模型。\n- [11-877：多模态机器学习高级专题（2022年秋季）——卡内基梅隆大学](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fadv-mmml-course\u002Fspring2022\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - 本课程探讨多模态机器学习（MMML），覆盖技术挑战与最新成果。课程强调批判性思维与未来研究趋势，并在课程网站上提供每周更新、讨论引导及研究亮点。\n\n## 🧠 深度学习\n- [神经网络\u002F深度学习——StatQuest](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLblh5JKOoLUIxGDQs4LFFD--41Vzf-ME1)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 在这个广受欢迎的YouTube播放列表中，探索神经网络的奥秘，将信息丰富的图形与专家讲解完美结合，从基础知识到卷积神经网络的高级图像分类，吸引了无数学生。\n- [神经网络——3Blue1Brown](https:\u002F\u002Fwww.3blue1brown.com\u002Ftopics\u002Fneural-networks)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 3Blue1Brown通过生动的动画和清晰的解释，揭示神经网络的神奇之处，深入探讨手写数字识别、梯度下降的细微差别以及反向传播背后的复杂微积分。\n- [神经网络：从零到英雄——Andrej Karpathy](https:\u002F\u002Fkarpathy.ai\u002Fzero-to-hero.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Andrej Karpathy的课程带领学生从基础的反向传播逐步深入到GPT等高级神经网络，强调语言模型是掌握深度学习的多功能入口，要求具备Python编程和基础数学知识。\n- [面向编码者的实用深度学习——fast.ai](https:\u002F\u002Fcourse.fast.ai\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 2022年的《面向编码者的实用深度学习》是一门免费课程，提供动手实践的机会，使用PyTorch和fastai等工具，在多个领域构建、训练和部署深度学习模型，适合有编程基础但无需高深数学知识的人。\n- [深度学习专项课程——Andrew Ng](https:\u002F\u002Fwww.deeplearning.ai\u002Fcourses\u002Fdeep-learning-specialization\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - Andrew Ng的深度学习专项课程是Coursera上备受好评的自定进度课程，拥有超过100万名学员，提供清晰的模块和实用的AI技术，背后有庞大的社区支持，将最新的机器学习内容分解为易于理解的形式。\n- [6.S191：深度学习导论——麻省理工学院](http:\u002F\u002Fintrotodeeplearning.com\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - MIT推出的深度学习基础强化训练营，涵盖从计算机视觉到生物学的应用，配有TensorFlow实操练习和最终项目竞赛。要求具备基础微积分和线性代数知识；有Python经验者更佳。\n- [CS25：Transformer大联合V2——斯坦福大学](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 探讨Transformer在深度学习中的变革性力量，涉及自然语言处理、生物等多个领域，课程包括专家讲座、前沿讨论及顶尖研究人员的见解，旨在促进理解与跨学科创新。\n- [2020年深度学习系列讲座——DeepMind × 伦敦大学学院](https:\u002F\u002Fwww.deepmind.com\u002Flearning-resources\u002Fdeep-learning-lecture-series-2020)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - DeepMind推出12讲深度学习系列课程，从基础主题深入到高级技术，涵盖目标识别到负责任的AI创新等领域，均由顶尖研究专家主讲。\n- [2021年强化学习系列讲座——DeepMind × 伦敦大学学院](https:\u002F\u002Fwww.deepmind.com\u002Flearning-resources\u002Freinforcement-learning-lecture-series-2021)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - DeepMind与UCL联合推出13讲现代强化学习全面系列课程，从基础概念到高级深度强化学习技术，由Hado van Hasselt、Diana Borsa和Matteo Hessel等专家研究员主讲。\n\n## 💻 AI 系统\n- [AI-Sys-Sp22 机器学习系统 - 加州大学伯克利分校](https:\u002F\u002Fucbrise.github.io\u002Fcs294-ai-sys-sp22\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 通过讲座、讨论和协作式实践项目，深入探讨前沿 AI 应用与其支撑系统之间的共生关系，探索硬件、软件以及 AI 驱动的优化技术方面的最新进展。\n- [深度学习系统：算法与实现 - 陈天奇、Zico Kolter](https:\u002F\u002Fdlsyscourse.org\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)\n  - 构建一个完整的深度学习库，从模型设计到高效算法，逐层理解深度学习系统的底层原理，并使用 Python 和 C\u002FC++ 进行实践。\n- [CS 329S：机器学习系统设计 - 斯坦福大学](https:\u002F\u002Fstanford-cs329s.github.io\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)\n  - 掌握设计健壮、可扩展且可部署的机器学习系统的复杂性，重点关注利益相关者、不断变化的需求以及整体系统设计，同时解决隐私、公平性和安全性等关键问题。\n- [AI-Systems (LLM Edition) 294-162 - 加州大学伯克利分校](https:\u002F\u002Flearning-systems.notion.site\u002Flearning-systems\u002FAI-Systems-LLM-Edition-294-162-Fall-2023-661887583bd340fa851e6a8da8e29abb)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - 本课程深入研究硬件\u002F软件进步与生成式 AI 之间的联系，强调这些创新如何推动 AI 模型的规模化和能力提升。\n- [15-849：机器学习系统 - 卡内基梅隆大学](https:\u002F\u002Fwww.cs.cmu.edu\u002F~zhihaoj2\u002F15-849\u002F)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - 深入探讨现代 ML 系统的架构，揭示从高层模型设计到异构硬件上低层内核执行的全过程，同时剖析下一代 ML 应用和平台的原则与挑战。\n- [计算机科学 598D - 系统与机器学习 - 普林斯顿大学](https:\u002F\u002Fwww.cs.princeton.edu\u002Fcourses\u002Farchive\u002Fspring21\u002Fcos598D\u002Fgeneral.html)\n  ![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Hard-red)\n  - 通过剖析高效的 ML 系统硬件\u002F软件相关最新研究，并将 ML 应用于系统设计，探索系统与机器学习之间的协同效应，最终以实践项目和深入讨论为研究生课程的高潮。\n\n## 🗂 其他\n\n### ✨ 星标历史\n[![星标历史图表](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fluban-agi_Awesome-AIGC-Tutorials_readme_e33a76a5fdb9.png)](https:\u002F\u002Fstar-history.com\u002F#luban-agi\u002FAwesome-AIGC-Tutorials&Date)\n\n### 🤝 友情链接\n- [WayToAGI](http:\u002F\u002Fwaytoagi.com\u002F)\n  - WaytoAGI.com 是最全面的中文 AIGC 资源中心，引导用户踏上优化的学习旅程，以理解和利用 AI 的强大功能。\n- [Codefuse-ChatBot](https:\u002F\u002Fgithub.com\u002Fcodefuse-ai\u002Fcodefuse-chatbot)\n  - Codefuse-ChatBot 是一款开源的 AI 智能助手，旨在通过对话式访问工具、知识和平台集成来支持软件开发生命周期。\n- [Codefuse DevOps Eval](https:\u002F\u002Fgithub.com\u002Fcodefuse-ai\u002Fcodefuse-devops-eval)\n  - DevOps-Eval 是一个 GitHub 仓库，提供专门用于评估和改进 DevOps 领域基础模型的工具集，其中包括丰富的 AIOps 练习。","# Awesome-AIGC-Tutorials 快速上手指南\n\n**Awesome-AIGC-Tutorials** 并非一个需要安装运行的软件工具或代码库，而是一个**精选的 AIGC（生成式人工智能）教程与资源索引列表**。它汇集了大语言模型（LLM）、AI 绘画、多模态等领域的优质课程、论文和实践指南。\n\n因此，本指南将指导你如何**访问、浏览及利用**该资源库中的内容，而非执行传统的软件安装流程。\n\n## 1. 环境准备\n\n由于本项目是资源导航，无需特定的操作系统或复杂的依赖环境。你只需要：\n\n*   **硬件要求**：任意可联网的设备（PC、平板或手机）。\n    *   *注：若你根据列表中的教程进行本地模型训练或推理（如 Stable Diffusion），则需参考具体教程的显卡（GPU）要求。*\n*   **软件要求**：\n    *   现代网页浏览器（推荐 Chrome, Edge, Firefox）。\n    *   Git（可选，用于克隆仓库到本地离线浏览）。\n*   **网络环境**：\n    *   部分链接指向 Coursera、YouTube 或国外大学课程网站，国内访问可能受限。建议配置合适的网络环境，或寻找对应的 Bilibili\u002F国内镜像搬运版本（部分热门课程在国内社区已有汉化资源）。\n\n## 2. 获取与访问步骤\n\n你可以通过以下两种方式访问资源：\n\n### 方式一：在线直接浏览（推荐）\n直接访问 GitHub 仓库页面查看最新整理的目录：\n```bash\nhttps:\u002F\u002Fgithub.com\u002Fluban-agi\u002FAwesome-AIGC-Tutorials\n```\n*提示：仓库根目录已提供 [中文版 (README_zh.md)](https:\u002F\u002Fgithub.com\u002Fluban-agi\u002FAwesome-AIGC-Tutorials\u002Fblob\u002Fmain\u002FREADME_zh.md) 链接，点击即可切换至中文界面。*\n\n### 方式二：克隆到本地\n如果你希望离线查看或在本地维护这份清单，可以使用 Git 克隆：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fluban-agi\u002FAwesome-AIGC-Tutorials.git\ncd Awesome-AIGC-Tutorials\n```\n\n## 3. 基本使用指南\n\n该项目的核心用法是**按图索骥**，根据你的学习阶段和需求，在目录中找到对应的课程链接并跳转学习。\n\n### 步骤 1：确定学习方向\n打开 `README.md` 或 `README_zh.md`，查看 **📜 Content** 目录结构，主要包含以下板块：\n*   **👋 Introduction**: AI 通识（适合零基础）。\n*   **💬 Large Language Models**: 大语言模型（含提示词工程、实战、理论）。\n*   **🎨 AI Painting**: AI 绘画（含艺术基础、Stable Diffusion 原理）。\n*   **🔊 AI Audio**: AI 音频。\n*   **🌈 Multimodal**: 多模态技术。\n*   **🧠 Deep Learning** & **💻 AI System**: 深度学习基础与系统架构。\n\n### 步骤 2：筛选适合的课程\n每个资源条目后都标记了难度等级和资源类型，请根据自身情况选择：\n*   `![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Easy-green)`：**入门级**，适合初学者。\n*   `![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLevel-Medium-yellow)`：**进阶级**，需要一定编程或理论基础。\n*   `![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVideo-blue)`：视频课程。\n*   `![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNotebook-orange)`：包含代码实战（Jupyter Notebook）。\n\n### 步骤 3：开始学习（示例）\n假设你想学习 **提示词工程 (Prompt Engineering)**：\n\n1.  在文档中找到 `💬 Large Language Models` -> `💡 Prompt Engineering` 章节。\n2.  选择标记为 `Easy` 且包含 `Notebook` 的课程，例如：\n    *   **[ChatGPT Prompt Engineering for Developers - DeepLearning.AI](https:\u002F\u002Fwww.deeplearning.ai\u002Fshort-courses\u002Fchatgpt-prompt-engineering-for-developers\u002F)**\n3.  点击链接跳转至课程官网。\n4.  按照该外部课程的指引注册账号、观看视频并运行提供的代码示例。\n\n### 步骤 4：贡献资源（可选）\n如果你发现了新的优质教程，可以通过以下方式贡献：\n1.  阅读仓库中的 `CONTRIBUTING.md` 文件了解规范。\n2.  在 GitHub 上提交 Issue 或 Pull Request 添加新链接。\n\n---\n*注意：本仓库仅为“地图”，具体的学习环境搭建（如 Python 环境、PyTorch 安装、API Key 获取等）需参照你点击进去的具体课程文档进行操作。*","某高校人工智能实验室的研究生团队正计划开展一项关于“多模态大模型在教育领域应用”的研究，成员背景各异，既有刚入门的本科生，也有需要深入系统架构的博士生。\n\n### 没有 Awesome-AIGC-Tutorials 时\n- **资源检索低效**：团队成员需在 Google、GitHub 和各类论坛中大海捞针，花费数周时间筛选过时或质量参差不齐的教程，严重拖慢项目启动进度。\n- **学习路径断层**：初学者面对复杂的数学公式望而却步，而进阶研究者又找不到关于 AI System 底层优化的深度课程，导致团队内部知识水位难以拉齐。\n- **前沿技术滞后**：由于缺乏统一的更新源，团队未能及时获取如\"Learning with Large Language and Vision Models\"等 2024 年最新课程，研究方案可能基于旧范式，存在方向性风险。\n- **领域覆盖不全**：在尝试结合 AI 绘画与文本生成时，发现手头资料仅侧重单一模态，缺乏跨模态（Multimodal）的系统性指导，导致技术整合困难。\n\n### 使用 Awesome-AIGC-Tutorials 后\n- **一站式精准获取**：团队直接利用该仓库 curated 的分类目录，半天内即可为不同成员匹配从\"AI for Everyone\"入门到\"AI-Systems (LLM Edition)\"进阶的精准资源。\n- **分级学习体系**：借助清晰的难度标签（Easy\u002FMedium），本科生通过吴恩达的视频课快速建立认知，博士生则直接深入 LLM 理论与系统实现，团队协作效率显著提升。\n- **实时同步前沿**：依托仓库频繁的近期更新（Recent Updates），团队迅速引入了 2024 年 2 月新增的多模态与 NLP 高级课程，确保研究起点处于行业最前沿。\n- **跨域技术融合**：通过\"Multimodal\"和\"AI Painting\"板块，团队找到了艺术基础与 Stable Diffusion 原理的结合点，顺利打通了图文生成的技术链路。\n\nAwesome-AIGC-Tutorials 通过构建结构化、实时更新的知识图谱，将原本分散且高门槛的 AIGC 学习成本降低了 80%，成为科研团队从入门到精通的加速引擎。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fluban-agi_Awesome-AIGC-Tutorials_9910735d.png","luban-agi","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fluban-agi_0b4a47ee.jpg",null,"https:\u002F\u002Fgithub.com\u002Fluban-agi",4493,301,"2026-04-06T09:28:36","MIT",1,"","未说明",{"notes":84,"python":85,"dependencies":86},"该项目是一个教程和资源合集（Awesome List），本身不是一个可执行的软件工具，因此没有具体的操作系统、GPU、内存或依赖库安装要求。列出的资源多为在线课程、文档或指向其他独立开源项目的链接，具体运行环境需参考各个子项目的说明。","部分课程建议具备基础 Python 知识",[],[15,88,13,35,14],"其他",[90,91,92,93,94,95,96,97,98,99,100,101,102],"aigc","llm","ai","midjourney","stable-diffusion","deep-learning","tutorials","courses-resource","prompt-engineering","nlp","awesome","chatgpt","multimodal","2026-03-27T02:49:30.150509","2026-04-07T10:53:05.682895",[],[]]