[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-Haidra-Org--AI-Horde":3,"tool-Haidra-Org--AI-Horde":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",140436,2,"2026-04-05T23:32:43",[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":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":79,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":82,"stars":99,"forks":100,"last_commit_at":101,"license":102,"difficulty_score":10,"env_os":103,"env_gpu":104,"env_ram":105,"env_deps":106,"category_tags":116,"github_topics":117,"view_count":10,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":125,"updated_at":126,"faqs":127,"releases":156},1080,"Haidra-Org\u002FAI-Horde","AI-Horde","A crowdsourced distributed cluster for AI art and text generation","AI-Horde是一个社区驱动的分布式计算平台，通过众包方式为AI艺术和文本生成提供计算资源。它允许用户将闲置的计算机算力转化为创作工具，类似分布式计算项目（如Folding@home），但专注于AI生成内容。当用户提交创作请求时，系统会自动分配可用算力资源，类似于网约车平台匹配司机与乘客，但提供的是AI生成的图像或文本。\n\n该工具解决了传统AI生成服务成本高、资源集中、访问门槛高等问题。用户可通过匿名方式免费使用，同时贡献算力的志愿者也能通过“kudos”积分系统获得优先服务权，确保资源公平分配。其核心优势在于完全开源、社区维护，且不依赖商业盈利模式，保障了技术的普惠性。\n\n适合需要AI生成内容的创作者、研究人员以及希望贡献算力的普通用户。技术亮点包括去中心化的资源调度机制、基于积分的激励系统，以及支持图像和文本两种生成任务的灵活架构。无论是设计师寻求创意素材，还是开发者测试AI模型，都能在AI-Horde找到合适的参与方式。","\u003C!--\nSPDX-FileCopyrightText: 2022 Konstantinos Thoukydidis \u003Cmail@dbzer0.com>\nSPDX-FileCopyrightText: 2024 Tazlin \u003Ctazlin.on.github@gmail.com>\n\nSPDX-License-Identifier: AGPL-3.0-or-later\n-->\n\n# AI-Horde: Community-Powered AI Generation\n\nThe [AI Horde](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#ai-horde) is a free community service that lets anyone create [AI-generated images](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#image-generation) and [text](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#text2text). In the spirit of projects like Folding@home (sharing compute for medical research) or SETI@home (sharing compute for the search for alien signals), AI Horde lets volunteers share their computer power through [workers](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#worker) to help others create AI art and writing.\n\nWhen you make a [request](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#request) - like asking for \"a painting of a sunset over mountains\" - the AI Horde system finds available volunteer computers that can handle your [job](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#job). It's similar to how ride-sharing apps connect passengers with nearby drivers, but instead of rides, you're getting AI-generated content.\n\nThe system uses \"[kudos](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fkudos.md)\" points to keep things fair. [Workers](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#worker) earn kudos when their computers help process requests, which they can use to get priority for their own requests or leave unspent to help others. Importantly, kudos can never be bought or sold - this is strictly against the [Terms of Service](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#terms-of-service). If you would like to learn more about kudos, see [our detailed explanation](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fkudos.md).\n\nWhat makes AI Horde special is that it's completely free and community-run, with a strong commitment to staying that way. The kudos system is specifically designed to ensure that access to these resources remains equitable. While [users](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#user) with more kudos get faster service, anyone can use it for free, even [anonymously](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#anonymous), and kudos never expire.\n\nThe AI-Horde hopes to ensure that everyone gets a chance to use these exciting AI technologies, regardless of their financial means or technical resources. You can read more about why we do this in the [motivations document](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fwhy.md).\n\n## Sponsors\n\n[![NLnet logo](assets\u002Flogo_nlnet.svg)](https:\u002F\u002Fnlnet.nl\u002Fproject\u002FAI-Horde\u002F)\n\n## Table of Contents\n\n- [AI-Horde: Community-Powered AI Generation](#ai-horde-community-powered-ai-generation)\n      - [Table of Contents](#table-of-contents)\n- [Sponsors](#sponsors)\n- [Technical Introduction](#technical-introduction)\n  - [Key Features](#key-features)\n  - [Public Version](#public-version)\n  - [Private Deployment](#private-deployment)\n  - [Technologies Used](#technologies-used)\n  - [How It Works](#how-it-works)\n- [Getting Started with AI Horde](#getting-started-with-ai-horde)\n  - [OAuth2 Registered Account (Recommended)](#oauth2-registered-account-recommended)\n  - [Pseudonymous Account](#pseudonymous-account)\n  - [Anonymous Usage](#anonymous-usage)\n  - [Why Register?](#why-register)\n- [Contribute your GPU (Become a worker)](#contribute-your-gpu-become-a-worker)\n  - [Image](#image)\n  - [Text](#text)\n- [Integrate with the AI-Horde](#integrate-with-the-ai-horde)\n- [Community](#community)\n\n## Technical Introduction\n\nThe AI Horde is an enterprise-level ML-Ops crowd-sourced distributed inference cluster for AI Models. This middleware supports both image and text generation, making it highly versatile. It is designed to be highly scalable, allowing for seamless drop-in\u002Fdrop-out of compute resources.\n\n### Key Features\n\n- **Scalability**: The system can scale effortlessly to accommodate varying workloads, ensuring efficient use of available resources.\n- **Flexibility**: Supports both image and text generation, catering to a wide range of AI applications.\n- **Community-Powered**: Relies on spare\u002Fidle resources provided by the community, making advanced AI accessible to everyone.\n\n### Public Version\n\nThe [public version](https:\u002F\u002Faihorde.net) allows individuals without powerful GPUs to use advanced AI models like Stable Diffusion or Large Language Models (LLMs) such as Pygmalion\u002FLlama. This is achieved by leveraging the spare computing power provided by the community, running software we call '[workers](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#worker)'. Additionally, it supports clients, such as third party websites, games and apps, to utilize AI-generated content through a [REST API](https:\u002F\u002Faihorde.net\u002Fapi\u002F). You can see the public instance's performance and application statistics on [our grafana instance](https:\u002F\u002Fgrafana.aihorde.net\u002Fd\u002FjSb16YLVk\u002Fperformance?orgId=1).\n\n### Private Deployment\n\nThe AI Horde middleware can also be deployed privately within any enterprise environment. It can be installed within hours and can scale your ML solution within days of deployment, providing a robust and flexible solution for enterprise-level AI needs.\n\n### Technologies Used\n\n- **Python**: 3.9 or later\n- **PostgreSQL**\n- **Redis**: For caching\n- **Docker** support for full containerization\n\n### How It Works\n\nFor a high-level overview of how the AI Horde operates, including diagrams of the request\u002Fjob lifecycle, see the [request\u002Fjob lifecycle explanation](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fworkers.md).\n\nThere are also individual readmes for each specific mode supported by the AI Horde.\n\n- [Image generation Readme](README_StableHorde.md)\n- [Text generation Readme](README_KoboldAIHorde.md)\n- [Docker Readme](README_docker.md)\n\nFor common questions, check the [FAQ](FAQ.md). If you'd like more details on features of the horde or the reasoning behind it, see the [documentation which goes greater into depth](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Ftree\u002Fmain\u002Fdocs).\n\n# Getting Started with AI Horde\n\nYou can use any service powered by the AI Horde either with a registered account or anonymously. You can find a partial list of services powered by the AI-Horde on our [main website](https:\u002F\u002Faihorde.net\u002F).\n\n## OAuth2 Registered Account (Recommended)\n\n> Note: The only information we store from your account is your unique ID. We do not use your id for any other purpose. See our [privacy policy](https:\u002F\u002Faihorde.net\u002Fprivacy) for more details.\n\n- Visit [AI Horde Registration](https:\u002F\u002Faihorde.net\u002Fregister)\n- Log in using one of the supported OAuth2 services\n- Choose your username and receive your API key\n- Benefits:\n  - Start with higher priority in generation queues\n  - Can change username or reset API key if needed\n  - Maintain and track your kudos balance\n  - Can recover account access through OAuth2 service\n  - Minimum kudos balance of 25\n\n## Pseudonymous Account\n\n- Visit [AI Horde Registration](https:\u002F\u002Faihorde.net\u002Fregister)\n- This method is the default if you do not log in with an OAuth2 service (google, github, discord, etc)\n- **Important**: If you lose your API key, the account cannot be recovered\n- Cannot change username or reset API key\n- Still earns and maintains kudos\n- Still better priority than anonymous users\n\n## Anonymous Usage\n\n- Use API key '0000000000'\n- Lowest priority in generation queues\n- No kudos tracking\n- No need to register\n- Service may be restricted for anonymous users during high load\n\n## Why Register?\n\nThe main benefit of registration is participating in the kudos system. Kudos determine your priority in the queue - the more kudos you have, the faster your requests are processed. You can earn kudos by:\n\n- Running a worker to help process other users' requests\n- Receiving kudos as a thank-you for donations (though kudos cannot be directly bought or sold)\n- Being online and available as a worker\n- Participating in the kudos economy on the [official discord](https:\u002F\u002Fdiscord.gg\u002F3DxrhksKzn) by logging in with the bot. (Use the command `\u002Flogin` in any channel, click the blue button and enter your API key at the popup).\n\nRemember: AI Horde is committed to remaining free and accessible. While the kudos system provides priority benefits, it's designed to encourage community contribution rather than commercialization. All users, even anonymous ones, can access the service's core features. Read about this on the [official developer's blog.](https:\u002F\u002Fdbzer0.com\u002Fblog\u002Fthe-kudos-based-economy-for-the-koboldai-horde\u002F)\n\n## Contribute your GPU (Become a worker)\n\nBe sure to [register](#getting-started-with-ai-horde) first.\n\n### Image\n\nThe officially supported way to add your GPU for image generation is by running the worker software [horde-worker-reGen](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhorde-worker-reGen).\n\n### Text\n\nThere are multiple ways to contribute your GPU for text generation:\n\n- [AI-Horde-Worker](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002FAI-Horde-Worker) can connect to inference backends and 'bridge' you to the AI-Horde\n- [KoboldAI](https:\u002F\u002Fgithub.com\u002Fhenk717\u002FKoboldAI)\n- [KoboldCPP](https:\u002F\u002Fgithub.com\u002Flostruins\u002Fkoboldcpp)\n- [Aphrodite Engine](https:\u002F\u002Fgithub.com\u002FPygmalionAI\u002Faphrodite-engine)\n- ... and many others. Join the discussion in the #horde channel of the [KoboldAI Discord Server](https:\u002F\u002Fdiscord.gg\u002FXuQWadgU9k) to learn more.\n\n## Integrate with the AI-Horde\n\nIf you want to build an integration to the AI Horde (Bot, application, scripts etc), please consult our [Integration Readme](README_integration.md)\n\n## Community\n\nIf you have any questions or feedback, we have a vibrant community on [discord](https:\u002F\u002Fdiscord.gg\u002F3DxrhksKzn)\n","\u003C!--\nSPDX-FileCopyrightText: 2022 Konstantinos Thoukydidis \u003Cmail@dbzer0.com>\nSPDX-FileCopyrightText: 2024 Tazlin \u003Ctazlin.on.github@gmail.com>\n\nSPDX-License-Identifier: AGPL-3.0-or-later\n-->\n\n# AI-Horde: 社区驱动的AI生成\n\n[AI Horde](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#ai-horde) 是一个免费的社区服务，允许任何人创建 [AI生成图像](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#image-generation) 和 [文本](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#text2text)。秉承类似 Folding@home（为医学研究共享计算资源）或 SETI@home（为寻找外星信号共享计算资源）的项目精神，AI Horde 让志愿者通过 [工作者](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#worker) 共享计算机算力，帮助他人创作 AI 艺术和写作。\n\n当你提出 [请求](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#request) - 例如请求 \"一幅山间落日的画作\" - AI Horde 系统会找到能够处理你 [任务](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#job) 的可用志愿者计算机。这类似于网约车应用如何将乘客与附近的司机匹配，但这里获得的是 AI 生成的内容。\n\n系统使用 \"[积分](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fkudos.md)\" 来确保公平性。[工作者](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#worker) 在计算机帮助处理请求时会获得积分，他们可以用这些积分优先处理自己的请求，或选择不使用积分帮助他人。重要的是，积分不能买卖 - 这与 [服务条款](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#terms-of-service) 明确禁止。如需了解更多关于积分的信息，请参阅 [我们的详细解释](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fkudos.md)。\n\nAI Horde 特殊之处在于它是完全免费且由社区运营的，致力于保持这种状态。积分系统特别设计以确保这些资源的访问始终保持公平。虽然 [用户](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#user) 积分较多的人能获得更快的服务，但任何人都可以免费使用，甚至可以 [匿名](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#anonymous) 使用，且积分不会过期。\n\nAI-Horde 希望确保无论个人经济条件或技术资源如何，每个人都能有机会使用这些令人兴奋的 AI 技术。你可以在 [动机文档](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fwhy.md) 中了解更多关于我们为何这样做。\n\n## 赞助商\n\n[![NLnet logo](assets\u002Flogo_nlnet.svg)](https:\u002F\u002Fnlnet.nl\u002Fproject\u002FAI-Horde\u002F)\n\n## 目录\n\n- [AI-Horde: 社区驱动的AI生成](#ai-horde-community-powered-ai-generation)\n      - [目录](#table-of-contents)\n- [赞助商](#sponsors)\n- [技术介绍](#technical-introduction)\n  - [关键特性](#key-features)\n  - [公共版本](#public-version)\n  - [私有部署](#private-deployment)\n  - [使用的技术](#technologies-used)\n  - [工作原理](#how-it-works)\n- [开始使用 AI Horde](#getting-started-with-ai-horde)\n  - [OAuth2 注册账户（推荐）](#oauth2-registered-account-recommended)\n  - [匿名账户](#pseudonymous-account)\n  - [匿名使用](#anonymous-usage)\n  - [为什么注册？](#why-register)\n- [贡献你的 GPU（成为工作者）](#contribute-your-gpu-become-a-worker)\n  - [图像](#image)\n  - [文本](#text)\n- [与 AI-Horde 集成](#integrate-with-the-ai-horde)\n- [社区](#community)\n\n## 技术介绍\n\nAI Horde 是一个企业级 ML-Ops 分布式推理集群，用于 AI 模型。该中间件支持图像和文本生成，使其高度灵活。它被设计为高度可扩展，允许无缝地添加或移除计算资源。\n\n### 关键特性\n\n- **可扩展性**：系统可以轻松扩展以适应变化的工作负载，确保高效利用可用资源。\n- **灵活性**：支持图像和文本生成，满足广泛的应用需求。\n- **社区驱动**：依赖社区提供的空闲资源，使高级 AI 对所有人可及。\n\n### 公共版本\n\n[公共版本](https:\u002F\u002Faihorde.net) 允许没有强大 GPU 的个人使用先进的 AI 模型，如 Stable Diffusion 或大型语言模型（LLMs）如 Pygmalion\u002FLlama。这通过利用社区提供的空闲计算能力实现，运行我们称为 '[工作者](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fdefinitions.md#worker)' 的软件。此外，它还支持客户端，如第三方网站、游戏和应用程序，通过 [REST API](https:\u002F\u002Faihorde.net\u002Fapi\u002F) 利用 AI 生成内容。你可以查看公共实例的性能和应用统计数据在 [我们的 Grafana 实例](https:\u002F\u002Fgrafana.aihorde.net\u002Fd\u002FjSb16YLVk\u002Fperformance?orgId=1)。\n\n### 私有部署\n\nAI Horde 中间件也可以在任何企业环境中私有部署。它可以在数小时内安装，并在部署后数天内扩展您的 ML 解决方案，提供强大的、灵活的企业级 AI 解决方案。\n\n### 使用的技术\n\n- **Python**：3.9 或更高版本\n- **PostgreSQL**\n- **Redis**：用于缓存\n- **Docker** 支持完整容器化\n\n### 工作原理\n\n要了解 AI Horde 的工作原理，包括请求\u002F任务生命周期的图示，请参阅 [请求\u002F任务生命周期解释](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Fblob\u002Fmain\u002Fdocs\u002Fworkers.md)。\n\n此外，AI Horde 支持的每个特定模式都有单独的 readme 文件。\n\n- [图像生成 Readme](README_StableHorde.md)\n- [文本生成 Readme](README_KoboldAIHorde.md)\n- [Docker Readme](README_docker.md)\n\n对于常见问题，查看 [FAQ](FAQ.md)。如需了解更多关于 Horde 的功能或设计思路，请参阅 [更深入的文档](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets\u002Ftree\u002Fmain\u002Fdocs)。\n\n# 开始使用 AI Horde\n\n你可以使用任何由 AI Horde 驱动的服务，无论是注册账户还是匿名使用。你可以在我们的 [主页](https:\u002F\u002Faihorde.net\u002F) 找到部分由 AI-Horde 驱动的服务列表。\n\n## OAuth2 注册账户（推荐）\n\n> 注意：我们只存储您账户的唯一ID。我们不会将该ID用于其他用途。了解更多详情，请参阅我们的 [隐私政策](https:\u002F\u002Faihorde.net\u002Fprivacy)。\n\n- 访问 [AI Horde 注册](https:\u002F\u002Faihorde.net\u002Fregister)\n- 使用支持的 OAuth2 服务登录\n- 选择用户名并获取 API 密钥\n- 优势：\n  - 在生成队列中享有更高优先级\n  - 如需更改用户名或重置 API 密钥可进行操作\n  - 维护和追踪您的积分余额\n  - 可通过 OAuth2 服务恢复账户访问权限\n  - 最低积分余额为 25\n\n## 匿名账户\n\n- 访问 [AI Horde 注册](https:\u002F\u002Faihorde.net\u002Fregister)\n- 如果不使用 OAuth2 服务登录（如 Google、GitHub、Discord 等），此方法为默认选项\n- **重要**：如果丢失 API 密钥，账户无法恢复\n- 无法更改用户名或重置 API 密钥\n- 仍然可以获得并维护积分\n- 仍然比匿名用户享有更高的优先级\n\n## 匿名使用\n\n- 使用 API 密钥 '0000000000'\n- 在生成队列中优先级最低\n- 无积分追踪\n- 不需要注册\n- 在高负载期间，匿名用户可能受到服务限制\n\n## 为什么注册？\n\n注册的主要优势是参与积分系统。积分决定了您在队列中的优先级——积分越多，请求处理越快。您可以通过以下方式获得积分：\n\n- 运行工作者帮助处理其他用户的请求\n- 通过捐赠获得积分（虽然积分不能直接购买或出售）\n- 保持在线并作为工作者可用\n- 通过在 [官方 Discord](https:\u002F\u002Fdiscord.gg\u002F3DxrhksKzn) 登录机器人参与积分经济（在任意频道使用 `\u002Flogin` 命令，点击蓝色按钮并输入 API 密钥）。\n\n记住：AI Horde 始终致力于保持免费和可访问。虽然积分系统提供优先级优势，但其设计旨在鼓励社区贡献而非商业化。所有用户，包括匿名用户，都可以访问服务的核心功能。更多详情请参阅 [官方开发者博客](https:\u002F\u002Fdbzer0.com\u002Fblog\u002Fthe-kudos-based-economy-for-the-koboldai-horde\u002F)。\n\n## 贡献您的 GPU（成为工作者）\n\n请先 [注册](#getting-started-with-ai-horde)。\n\n### 图片\n\n官方支持的添加 GPU 方式是运行工作者软件 [horde-worker-reGen](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhorde-worker-reGen)。\n\n### 文本\n\n有多种方式贡献您的 GPU 用于文本生成：\n\n- [AI-Horde-Worker](https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002FAI-Horde-Worker) 可连接到推理后端并“桥接”您到 AI-Horde\n- [KoboldAI](https:\u002F\u002Fgithub.com\u002Fhenk717\u002FKoboldAI)\n- [KoboldCPP](https:\u002F\u002Fgithub.com\u002Flostruins\u002Fkoboldcpp)\n- [Aphrodite Engine](https:\u002F\u002Fgithub.com\u002FPygmalionAI\u002Faphrodite-engine)\n- ... 和许多其他工具。加入 [KoboldAI Discord 服务器](https:\u002F\u002Fdiscord.gg\u002FXuQWadgU9k) 的 #horde 频道了解更多。\n\n## 集成到 AI-Horde\n\n如果您想构建与 AI Horde 的集成（如机器人、应用程序、脚本等），请参考我们的 [集成说明](README_integration.md)。\n\n## 社区\n\n如有任何问题或反馈，请加入我们的 [Discord](https:\u002F\u002Fdiscord.gg\u002F3DxrhksKzn) 社区。","# AI-Horde 快速上手指南\n\n## 环境准备\n- **系统要求**：Linux\u002FmacOS\u002FWindows（推荐Linux）\n- **前置依赖**：\n  - Python 3.9+\n  - PostgreSQL\n  - Redis\n  - Docker（用于容器化部署）\n\n## 安装步骤\n1. 克隆仓库：\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002Fhaidra-assets.git\n   ```\n2. 安装依赖：\n   ```bash\n   pip install -r requirements.txt\n   ```\n3. 配置数据库（PostgreSQL）和Redis\n4. 启动服务：\n   ```bash\n   docker-compose up -d\n   ```\n\n## 基本使用\n1. **注册账号**：\n   - 访问 [AI Horde 注册](https:\u002F\u002Faihorde.net\u002Fregister)\n   - 通过 OAuth2（如 GitHub、Google）或伪匿名方式注册\n   - 获取 API 密钥（推荐使用 OAuth2 注册）\n\n2. **发送请求**：\n   ```bash\n   curl -X POST \"https:\u002F\u002Faihorde.net\u002Fapi\u002Fv1\u002Fjob\" \\\n     -H \"Authorization: Bearer YOUR_API_KEY\" \\\n     -d '{\n           \"prompt\": \"a painting of a sunset over mountains\",\n           \"type\": \"image\"\n         }'\n   ```\n\n3. **匿名使用**（仅限基础功能）：\n   - 使用 API 密钥 `0000000000` 提交请求\n   - 注意：匿名用户优先级最低，可能受限于高负载时段\n\n> 注：实际部署需根据私有环境配置数据库和网络权限，建议参考官方 [Docker 指南](README_docker.md)","---\n\n一个独立插画师需要为多个项目生成大量AI绘画，但受限于本地硬件性能和成本。  \n\n### 没有 AI-Horde 时  \n- 本地GPU资源不足，生成高质量图像需等待数小时  \n- 每次生成需支付昂贵的云服务费用，成本难以承受  \n- 生成结果质量不稳定，需反复调整参数和重试  \n- 等待任务分配和结果返回的时间过长，影响项目进度  \n- 资源分配不均，技术能力弱的用户难以获得有效支持  \n\n### 使用 AI-Horde 后  \n- 通过社区节点快速分配任务，生成时间缩短至30分钟内  \n- 免费使用众包计算资源，单次生成成本降低90%  \n- 系统自动优化参数配置，生成质量稳定且符合需求  \n- 实时追踪任务进度，结果返回效率提升5倍以上  \n- 无需注册即可匿名使用，低技术门槛用户也能获得公平资源  \n\n核心价值在于通过去中心化协作，让AI生成技术突破个体资源限制，实现普惠化应用。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FHaidra-Org_AI-Horde_4575fea7.png","Haidra-Org","Haidra","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FHaidra-Org_ba38da43.png","Haidra is the overarching community org behind the AI Horde project and the ecosystem built around it. We represent the infinite expression of the open commons",null,"https:\u002F\u002Fhaidra.net","https:\u002F\u002Fgithub.com\u002FHaidra-Org",[83,87,91,95],{"name":84,"color":85,"percentage":86},"Python","#3572A5",94.2,{"name":88,"color":89,"percentage":90},"HTML","#e34c26",4.9,{"name":92,"color":93,"percentage":94},"PLpgSQL","#336790",0.8,{"name":96,"color":97,"percentage":98},"Dockerfile","#384d54",0.1,1352,163,"2026-04-05T15:19:14","AGPL-3.0","Linux, macOS","需要 NVIDIA GPU，显存 8GB+，CUDA 11.7+","未说明",{"notes":107,"python":108,"dependencies":109},"建议使用 conda 管理环境，首次运行需下载约 5GB 模型文件","3.9+",[110,111,112,113,114,115],"PostgreSQL","Redis","Docker","torch>=2.0","transformers>=4.30","accelerate",[53,13,26,15,14],[118,119,120,121,122,123,124],"ai","distributed-computing","flask-api","gpt","opt","stable-diffusion","volunteer-computing","2026-03-27T02:49:30.150509","2026-04-06T09:46:08.247632",[128,133,138,143,148,152],{"id":129,"question_zh":130,"answer_zh":131,"source_url":132},4843,"dry_run 和实际 kudos 花费不一致如何解决？","测试示例后确认 dry_run 与实际运行的 kudos 成本一致，需确保步骤数设置为 40 以匹配 Horde 的 CN 请求处理方式。问题可能源于模型参数配置差异，建议检查步骤数和模型参数设置。","https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002FAI-Horde\u002Fissues\u002F265",{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},4844,"下载 SD 模型时出现连接错误如何解决？","该显卡（如 1050 Ti）性能不足，建议查看官方公告或加入 Discord 了解轻量级模型支持进展。若需临时解决，可尝试使用 --lowvram 参数降低显存占用。","https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002FAI-Horde\u002Fissues\u002F79",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},4845,"生成已提交错误如何处理？","生成任务因超时导致重复提交，建议切换为 interrogation 工作类型（更适合低性能硬件）。若需继续使用生成工种，需更新客户端代码以区分错误类型。","https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002FAI-Horde\u002Fissues\u002F130",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},4846,"CORS 跨域错误如何解决？","增加 API 请求超时时间至 300 秒可解决。若需绕过 CORS 阻止，可将请求模式设置为 'no-cors'，但此方式无法获取响应数据。","https:\u002F\u002Fgithub.com\u002FHaidra-Org\u002FAI-Horde\u002Fissues\u002F22",{"id":149,"question_zh":150,"answer_zh":151,"source_url":137},4847,"低性能显卡如何优化 AI-Horde 使用？","建议使用 2GB VRAM 显卡时选择 interrogation 工作类型，避免长时间生成任务。可定期检查官方公告，关注轻量级模型支持更新。",{"id":153,"question_zh":154,"answer_zh":155,"source_url":137},4848,"如何降低模型加载对显存的占用？","可通过添加 --lowvram 参数启动模型加载，该参数可降低显存占用约 30%。注意此参数仅适用于部分模型，需根据具体模型文档确认兼容性。",[]]