[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-SipherAGI--sd-webui-agent-scheduler":3,"tool-SipherAGI--sd-webui-agent-scheduler":64},[4,17,27,35,48,56],{"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},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",[14,43,44,45,15,46,26,13,47],"数据工具","视频","插件","其他","音频",{"id":49,"name":50,"github_repo":51,"description_zh":52,"stars":53,"difficulty_score":10,"last_commit_at":54,"category_tags":55,"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",[15,14,13,26,46],{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",74939,"2026-04-05T23:16:38",[26,14,13,46],{"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":79,"owner_twitter":80,"owner_website":81,"owner_url":82,"languages":83,"stars":104,"forks":105,"last_commit_at":106,"license":78,"difficulty_score":23,"env_os":107,"env_gpu":108,"env_ram":108,"env_deps":109,"category_tags":112,"github_topics":78,"view_count":113,"oss_zip_url":78,"oss_zip_packed_at":78,"status":16,"created_at":114,"updated_at":115,"faqs":116,"releases":146},181,"SipherAGI\u002Fsd-webui-agent-scheduler","sd-webui-agent-scheduler","An open source Scheduling Agent for Generative AI","sd-webui-agent-scheduler 是一个为 Stable Diffusion Web UI（如 Automatic1111 或 Vladmandic 版本）设计的开源任务调度插件，帮助用户更高效地管理批量图像生成任务。它解决了在使用 AI 绘图时手动排队、反复设置参数、无法灵活调整顺序或暂停恢复等痛点，尤其适合需要连续生成多组图像的场景。\n\n无论是设计师想测试不同提示词效果，还是研究人员批量跑实验，或是普通用户想一次安排多个出图任务，都能从中受益。界面直观支持拖拽排序、一键暂停\u002F继续、历史记录回看、任务筛选与重命名，还能双击快速修改参数并重新入队。隐藏功能如“用所有模型排队”或“指定文件夹内模型批量生成”，大幅提升工作效率。\n\n技术亮点在于无缝集成现有 Web UI，提供类桌面应用的任务管理体验，并支持 API 调用，方便进阶用户自动化流程。安装简单，兼容主流分支，只需几秒即可启用。无论你是刚入门的新手还是追求效率的老手，Agent Scheduler 都能让你的 AI 作图流程更从容有序。","# Agent Scheduler\n\nIntroducing AgentScheduler, an Automatic1111\u002FVladmandic Stable Diffusion Web UI extension to power up your image generation workflow!\n\n## Table of Content\n\n- [Compatibility](#compatibility)\n- [Installation](#installation)\n  - [Using Vlad Fork](#using-vlads-webui-fork)\n  - [Using the built-in extension list](#using-the-built-in-extension-list)\n  - [Manual clone](#manual-clone)\n- [Functionality](#functionality-as-of-current-version)\n- [Settings](#extension-settings)\n- [API Access](#api-access)\n- [Troubleshooting](#troubleshooting)\n- [Road Map](#road-map)\n- [Contributing](#contributing)\n- [License](#license)\n- [Disclaimer](#disclaimer)\n\n---\n\n## Compatibility\n\nThis version of AgentScheduler is compatible with latest versions of:\n\n- A1111: [commit baf6946](https:\u002F\u002Fgithub.com\u002FAUTOMATIC1111\u002Fstable-diffusion-webui\u002Fcommit\u002Fbaf6946e06249c5af9851c60171692c44ef633e0)\n- Vladmandic: [commit 9726b4d](https:\u002F\u002Fgithub.com\u002Fvladmandic\u002Fautomatic\u002Fcommit\u002F9726b4d23cb63779964e1d4edff49dd2c9c11e51)\n\n> Older versions may not working properly.\n\n## Installation\n\n### Using Vlad's WebUI Fork\n\nThe extension is already included in [Vlad fork](https:\u002F\u002Fgithub.com\u002Fvladmandic\u002Fautomatic)'s builtin extensions.\n\n### Using the built-in extension list\n\n1. Open the Extensions tab\n2. Open the \"Install From URL\" sub-tab\n3. Paste the repo url: https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler.git\n4. Click \"Install\"\n\n![Install](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_0e8906905cf7.png)\n\n### Manual clone\n\n```bash\ngit clone \"https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler.git\" extensions\u002Fagent-scheduler\n```\n\n(The second argument specifies the name of the folder, you can choose whatever you like).\n\n## Basic Features\n\n![Extension Walkthrough 1](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_b03c71c24873.png)\n\n1️⃣ Input your usual Prompts & Settings. **Enqueue** to send your current prompts, settings, controlnets to **AgentScheduler**.\n\n![Extension Walkthrough 2](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_877e88e06b18.png)\n\n2️⃣ **AgentScheduler** Extension Tab.\n\n3️⃣ See all queued tasks, current image being generated and tasks' associated information. **Drag and drop** the handle in the begining of each row to reaggrange the generation order.\n\n4️⃣ **Pause** to stop queue auto generation. **Resume** to start.\n\n5️⃣ Press ▶️ to prioritize selected task, or to start a single task when queue is paused. **Delete** tasks that you no longer want.\n\n![ Extension Walkthrough 3](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_a018c410a27b.png)\n\n6️⃣ Show queue history.\n\n7️⃣ **Filter** task status or search by text.\n\n8️⃣ **Bookmark** task to easier filtering.\n\n9️⃣ Double click the task id to **rename** and quickly update basic parameters. Click ↩️ to **Requeue** old task.\n\n🔟 Click on each task to **view** the generation results.\n\nhttps:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler\u002Fassets\u002F133728487\u002F50c74922-b85f-493c-9be8-b8e78f0cd061\n\n## Hidden Features:\n\n#### Queue all checkpoints at the same time\n\nRight click the `Enqueue` button and select `Queue with all checkpoints` to quickly queue the current setting with all available checkpoints.\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_1099c0932727.png)\n\n#### Queue with a subset of checkpoints\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_dca75889c691.png)\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_88f0f9d72936.png)\n\nWith the custom checkpoint select enabled (see [Extension Settings](#extension-settings) section below), you can select a folder (or subfolder) to queue task with all checkpoints inside. Eg: Select `anime` will queue `anime\\AOM3A1B_oragemixs`, `anime\\counterfeit\\Counterfeit-V2.5_fp16` and `anime\\counterfeit\\Counterfeit-V2.5_pruned`.\n\n#### Edit queued task\n\nDouble click a queued task to edit. You can name a task by changing `task_id` or update some basic parameters: `prompt`, `negative prompt`, `sampler`, `checkpoint`, `steps`, `cfg scale`.\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_50e29c494397.png)\n\n## Extension Settings\n\nGo to `Settings > Agent Scheduler` to access extension settings.\n\n![Settings](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_10b2b4a60b1c.png)\n\n**Disable Queue Auto-Processing**: Check this option to disable queue auto-processing on start-up. You can also temporarily pause or resume the queue from the Extension tab.\n\n**Queue Button Placement**: Change the placement of the queue button on the UI.\n\n**Hide the Checkpoint Dropdown**: The Extension provides a custom checkpoint dropdown.\n\n![Custom Checkpoint](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_26dea8380f9b.png)\n\nBy default, queued tasks use the currently loaded checkpoint. However, changing the system checkpoint requires some time to load the checkpoint into memory, and you also cannot change the checkpoint during image generation. You can use this dropdown to quickly queue a task with a custom checkpoint.\n\n**Auto Delete Queue History**: Select a timeframe to keep your queue history. Tasks that are older than the configured value will be automatically deleted. Please note that bookmarked tasks will not be deleted.\n\n## API Access\n\nAll the functionality of this extension can be accessed through HTTP APIs. You can access the API documentation via `http:\u002F\u002F127.0.0.1:7860\u002Fdocs`. Remember to include `--api` in your startup arguments.\n\n![API docs](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_d8342adc75d2.png)\n\n#### Queue Task\n\nThe two apis `\u002Fagent-scheduler\u002Fv1\u002Fqueue\u002Ftxt2img` and `\u002Fagent-scheduler\u002Fv1\u002Fqueue\u002Fimg2img` support all the parameters of the original webui apis. These apis response the task id, which can be used to perform updates later.\n\n```json\n{\n  \"task_id\": \"string\"\n}\n```\n\n#### Download Results\n\nUse api `\u002Fagent-scheduler\u002Fv1\u002Fresults\u002F{id}` to get the generated images. The api supports two response format:\n\n- json with base64 encoded\n\n```json\n{\n  \"success\": true,\n  \"data\": [\n    {\n      \"image\": \"data:image\u002Fpng;base64,iVBORw0KGgoAAAAN...\",\n      \"infotext\": \"1girl\\nNegative prompt: EasyNegative, badhandv4...\"\n    },\n    {\n      \"image\": \"data:image\u002Fpng;base64,iVBORw0KGgoAAAAN...\",\n      \"infotext\": \"1girl\\nNegative prompt: EasyNegative, badhandv4...\"\n    }\n  ]\n}\n```\n\n- zip file with querystring `zip=true`\n\n#### API Callback\n\nQueue task with param `callback_url` to register an API callback. Eg:\n\n```json\n{\n  \"prompt\": \"1girl\",\n  \"negative_prompt\": \"easynegative\",\n  \"callback_url\": \"http:\u002F\u002Fsomehost:port\u002Ftask_completed\"\n}\n```\n\nThe callback endpoint must support `POST` method with body in `multipart\u002Fform-data` encoding. Body format:\n\n```json\n{\n  \"task_id\": \"abc123\",\n  \"status\": \"done\",\n  \"files\": [list of image files],\n}\n```\n\nExample code of the endpoint handle with `FastApi`:\n\n```python\nfrom fastapi import FastAPI, UploadFile, File, Form\n\n@app.post(\"\u002Ftask_completed\")\nasync def handle_task_completed(\n    task_id: Annotated[str, Form()],\n    status: Annotated[str, Form()],\n    files: Optional[List[UploadFile]] = File(None),\n):\n    print(f\"Received {len(files)} files for task {task_id} with status {status}\")\n    for file in files:\n        print(f\"* {file.filename} {file.content_type} {file.size}\")\n        # ... do something with the file contents ...\n\n# Received 1 files for task 3cf8b150-f260-4489-b6e8-d86ed8a564ca with status done\n# * 00008-3322209480.png image\u002Fpng 416400\n```\n\n## Troubleshooting\n\nMake sure that you are running the latest version of the extension and an updated version of the WebUI.\n\n- To update the extension, go to `Extension` tab and click `Check for Updates`, then click `Apply and restart UI`.\n- To update the WebUI it self, you run the command `git pull origin master` in the same folder as webui.bat (or webui.sh).\n\nSteps to try to find the cause of issues:\n\n- Check the for errors in the WebUI output console.\n- Press F12 in the browser then go to the console tab and reload the page, find any error message here.\n\nCommon errors:\n\n**AttributeError: module 'modules.script_callbacks' has no attribute 'on_before_reload'**\n\nIf you see this error message in the output console, try update the WebUI to the latest version.\n\n**Update**: The extension is updated to print this warning message instead: **YOUR SD WEBUI IS OUTDATED AND AGENT SCHEDULER WILL NOT WORKING PROPERLY.** You can still able to use the extension but it will not working correctly after a reload.\n\n~~**ReferenceError: submit_enqueue is not defined**~~\n\n~~If you click the `Enqueue` button and nothing happen, and you find above error message in the browser F12 console, follow the steps in [this comment](https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler\u002Fissues\u002F4#issuecomment-1575986274).~~\n\nUpdate: This issue is now fixed.\n\n**TypeError: issubclass() arg 1 must be a class**\nPlease update the extension, there's a chance it's already fixed.\n\n**TypeError: Object of type X is not JSON serializable**\nPlease update the extension, it should be fixed already. If not, please fire an issue report with the list of installed extensions.\n\nFor other errors, feel free to fire a new [Github issue](https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler\u002Fissues\u002Fnew\u002Fchoose).\n\n\n## Contributing\n\nWe welcome contributions to the Agent Scheduler Extension project! Please feel free to submit issues, bug reports, and feature requests through the GitHub repository.\n\nPlease give us a ⭐ if you find this extension helpful!\n\n## License\n\nThis project is licensed under the Apache License 2.0.\n\n## Disclaimer\n\nThe author(s) of this project are not responsible for any damages or legal issues arising from the use of this software. Users are solely responsible for ensuring that they comply with any applicable laws and regulations when using this software and assume all risks associated with its use. The author(s) are not responsible for any copyright violations or legal issues arising from the use of input or output content.\n\n---\n\n## CRAFTED BY THE PEOPLE BUILDING [**SIPHER\u002F\u002FAGI**](https:\u002F\u002Fsipheragi.com), [**PROTOGAIA**](https:\u002F\u002Fprotogaia.com), [**ATHERLABS**](https:\u002F\u002Fatherlabs.com\u002F) & [**SIPHER ODYSSEY**](http:\u002F\u002Fplaysipher.com\u002F)\n\n### About ProtoGAIA\n\nProtoGAIA offers powerful collaboration features for Generative AI Image workflows. It is designed to help designers and creative professionals of all levels collaborate more efficiently, unleash their creativity, and have full transparency and tracking over the creation process.\n\n### Current protoGAIA Features\n\nLike any open project that seeks to bring the powerful of Generative AI to the masses, ProtoGAIA offers the following key features:\n\n✅ Seamless Access: available on desktop and mobile\n\n✅ Powerful Macro Abilities that allowing the chaining of tasks, which is then packaged as Macro Command ready for AI Agent Automation\n\n✅ Multiplayer & Collaborative UX. Strong collaboration features, such as real-time commenting and feedback, version control, and image\u002Ffile\u002Fproject sharing\n\n✅ Rooms Chat for lively discussion between users and running Generative AI workflows right in the chat\n\n✅ Custom Models Management including Lora, Diffusion Models, Controlnet Models and more\n\n✅ Powerful semantic search capabilities\n\n✅ Powerful AI driven chat box that can trigger quick Generative AI tasks and workflows\n\n✅ Building on shoulders of Giants, leveraging A1111\u002FVladnmandic and other pioneers, provide collaboration process from Idea to Final Results in 1 platform\n\n✅ Automation tooling for certain repeated tasks\n\n✅ Secure and transparent, leveraging hasing and metadata to track the origin and history of models, loras, images to allow for tracability and ease of collaboration\n\n✅ Personalize UIUX for both beginner and experienced users to quickly remix existing SD images by editing prompts and negative prompts, selecting new training models and output quality as desired\n\n✅ Provenance Tracking for all models, loras, images to allow for tracability and ease of collaboration\n\n✅ Custom UIUX for both beginner and experienced users to quickly remix existing SD images by editing prompts and negative prompts, selecting new training models and output quality as desired\n\n✅ Articles and Tutorials for learning Generative AI\n\n✅ Voting System for best generative AI images, models, recipes, macros etc\n\n✅ Open sharing of generative AI images, models, recipes, macros etc via the Global Explore tab\n\n### Target Audience\n\nProtoGAIA is designed for the following target audiences:\n\n- Creators\n- Small Design Teams or Freelancers\n- Design Agencies & Game Studios\n- AI Agents\n\n## 🎉 Stay Tuned for Updates\n\nWe hope you find this extension to be useful. We will be adding new features and improvements over time as we enhance this extension to support our creative workflows.\n\nTo stay up-to-date with the latest news and updates, be sure to follow us on GitHub and Twitter. We welcome your feedback and suggestions, and are excited to hear how AgentScheduler can help you streamline your workflow and unleash your creativity!\n","# Agent Scheduler\n\n隆重推出 AgentScheduler，一款为 Automatic1111\u002FVladmandic Stable Diffusion Web UI 打造的扩展插件，助你大幅提升图像生成工作流效率！\n\n## 目录\n\n- [兼容性](#兼容性)\n- [安装](#安装)\n  - [使用 Vlad 的分支版本](#使用-vlads-webui-分支)\n  - [使用内置扩展列表](#使用内置扩展列表)\n  - [手动克隆](#手动克隆)\n- [功能](#当前版本功能)\n- [设置](#扩展设置)\n- [API 访问](#api-访问)\n- [故障排除](#故障排除)\n- [路线图](#路线图)\n- [贡献方式](#贡献方式)\n- [许可证](#许可证)\n- [免责声明](#免责声明)\n\n---\n\n## 兼容性\n\n本版本 AgentScheduler 兼容以下最新版本：\n\n- A1111: [commit baf64946](https:\u002F\u002Fgithub.com\u002FAUTOMATIC1111\u002Fstable-diffusion-webui\u002Fcommit\u002Fbaf6946e06249c5af9851c60171692c44ef633e0)\n- Vladmandic: [commit 9726b4d](https:\u002F\u002Fgithub.com\u002Fvladmandic\u002Fautomatic\u002Fcommit\u002F9726b4d23cb63779964e1d4edff49dd2c9c11e51)\n\n> 旧版本可能无法正常运行。\n\n## 安装\n\n### 使用 Vlad 的 WebUI 分支\n\n该扩展已内置于 [Vlad 分支](https:\u002F\u002Fgithub.com\u002Fvladmandic\u002Fautomatic) 的内置扩展中。\n\n### 使用内置扩展列表\n\n1. 打开“Extensions”（扩展）标签页\n2. 切换到“Install From URL”（从 URL 安装）子标签页\n3. 粘贴仓库地址：https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler.git\n4. 点击“Install”（安装）\n\n![Install](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_0e8906905cf7.png)\n\n### 手动克隆\n\n```bash\ngit clone \"https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler.git\" extensions\u002Fagent-scheduler\n```\n\n（第二个参数指定文件夹名称，可自定义）。\n\n## 基础功能\n\n![Extension Walkthrough 1](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_b03c71c24873.png)\n\n1️⃣ 输入常规提示词与设置。点击 **Enqueue**（入队），将当前提示词、设置、ControlNet 等发送至 **AgentScheduler**。\n\n![Extension Walkthrough 2](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_877e88e06b18.png)\n\n2️⃣ **AgentScheduler** 扩展标签页。\n\n3️⃣ 查看所有排队任务、当前正在生成的图像及任务相关信息。拖拽每行开头的句柄可重新调整生成顺序。\n\n4️⃣ 点击 **Pause**（暂停）停止队列自动生成；点击 **Resume**（恢复）重新开始。\n\n5️⃣ 点击 ▶️ 优先处理选中任务，或在队列暂停时启动单个任务。点击 **Delete**（删除）移除不需要的任务。\n\n![ Extension Walkthrough 3](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_a018c410a27b.png)\n\n6️⃣ 显示队列历史记录。\n\n7️⃣ **Filter**（筛选）任务状态或按文本搜索。\n\n8️⃣ **Bookmark**（书签）标记任务以便快速筛选。\n\n9️⃣ 双击任务 ID 可 **重命名** 并快速更新基础参数。点击 ↩️ **Requeue**（重新入队）旧任务。\n\n🔟 点击每个任务以 **查看** 生成结果。\n\nhttps:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler\u002Fassets\u002F133728487\u002F50c74922-b85f-493c-9be8-b8e78f0cd061\n\n## 隐藏功能：\n\n#### 同时对所有检查点（checkpoint）排队\n\n右键点击 `Enqueue` 按钮并选择 `Queue with all checkpoints`（使用所有检查点排队），即可快速将当前设置与所有可用检查点一同入队。\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_1099c0932727.png)\n\n#### 对部分检查点排队\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_dca75889c691.png)\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_88f0f9d72936.png)\n\n启用自定义检查点选择器后（见下方[扩展设置](#扩展设置)），你可以选择一个文件夹（或子文件夹），将其中所有检查点加入队列。例如：选择 `anime` 将入队 `anime\\AOM3A1B_oragemixs`、`anime\\counterfeit\\Counterfeit-V2.5_fp16` 和 `anime\\counterfeit\\Counterfeit-V2.5_pruned`。\n\n#### 编辑已排队任务\n\n双击已排队任务进行编辑。可通过修改 `task_id` 为任务命名，或更新部分基础参数：`prompt`（提示词）、`negative prompt`（负面提示词）、`sampler`（采样器）、`checkpoint`（检查点）、`steps`（步数）、`cfg scale`（CFG 比例）。\n\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_50e29c494397.png)\n\n## 扩展设置\n\n前往 `Settings > Agent Scheduler` 访问扩展设置。\n\n![Settings](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_10b2b4a60b1c.png)\n\n**Disable Queue Auto-Processing**（禁用队列自动处理）：勾选此项将在启动时禁用队列自动处理。你也可以在扩展标签页中临时暂停或恢复队列。\n\n**Queue Button Placement**（队列按钮位置）：更改 UI 上队列入队按钮的位置。\n\n**Hide the Checkpoint Dropdown**（隐藏检查点下拉菜单）：本扩展提供自定义检查点下拉菜单。\n\n![Custom Checkpoint](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_26dea8380f9b.png)\n\n默认情况下，入队任务使用当前加载的检查点。但切换系统检查点需要时间加载至内存，且图像生成过程中无法更换检查点。你可以使用此下拉菜单快速将带有自定义检查点的任务入队。\n\n**Auto Delete Queue History**（自动删除队列历史）：选择保留队列历史的时间范围。超过设定时间的任务将被自动删除。请注意，已加书签的任务不会被删除。\n\n## API 访问\n\n本扩展的所有功能均可通过 HTTP API 访问。您可以通过 `http:\u002F\u002F127.0.0.1:7860\u002Fdocs` 查看 API 文档。请记得在启动参数中加入 `--api`。\n\n![API docs](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_readme_d8342adc75d2.png)\n\n#### 任务队列（Queue Task）\n\n两个 API `\u002Fagent-scheduler\u002Fv1\u002Fqueue\u002Ftxt2img` 和 `\u002Fagent-scheduler\u002Fv1\u002Fqueue\u002Fimg2img` 支持原始 WebUI API 的所有参数。这些 API 会返回任务 ID，可用于后续更新操作。\n\n```json\n{\n  \"task_id\": \"string\"\n}\n```\n\n#### 下载结果\n\n使用 API `\u002Fagent-scheduler\u002Fv1\u002Fresults\u002F{id}` 获取生成的图像。该 API 支持两种响应格式：\n\n- Base64 编码的 JSON 格式\n\n```json\n{\n  \"success\": true,\n  \"data\": [\n    {\n      \"image\": \"data:image\u002Fpng;base64,iVBORw0KGgoAAAAN...\",\n      \"infotext\": \"1girl\\nNegative prompt: EasyNegative, badhandv4...\"\n    },\n    {\n      \"image\": \"data:image\u002Fpng;base64,iVBORw0KGgoAAAAN...\",\n      \"infotext\": \"1girl\\nNegative prompt: EasyNegative, badhandv4...\"\n    }\n  ]\n}\n```\n\n- 带查询参数 `zip=true` 的 ZIP 文件格式\n\n#### API 回调（Callback）\n\n在排队任务时传入参数 `callback_url` 以注册 API 回调。例如：\n\n```json\n{\n  \"prompt\": \"1girl\",\n  \"negative_prompt\": \"easynegative\",\n  \"callback_url\": \"http:\u002F\u002Fsomehost:port\u002Ftask_completed\"\n}\n```\n\n回调端点必须支持 `POST` 方法，且请求体需为 `multipart\u002Fform-data` 编码格式。请求体结构如下：\n\n```json\n{\n  \"task_id\": \"abc123\",\n  \"status\": \"done\",\n  \"files\": [list of image files],\n}\n```\n\n使用 `FastApi` 处理回调的示例代码：\n\n```python\nfrom fastapi import FastAPI, UploadFile, File, Form\n\n@app.post(\"\u002Ftask_completed\")\nasync def handle_task_completed(\n    task_id: Annotated[str, Form()],\n    status: Annotated[str, Form()],\n    files: Optional[List[UploadFile]] = File(None),\n):\n    print(f\"Received {len(files)} files for task {task_id} with status {status}\")\n    for file in files:\n        print(f\"* {file.filename} {file.content_type} {file.size}\")\n        # ... 对文件内容进行处理 ...\n\n# Received 1 files for task 3cf8b150-f260-4489-b6e8-d86ed8a564ca with status done\n# * 00008-3322209480.png image\u002Fpng 416400\n```\n\n## 故障排除\n\n请确保您正在运行最新版本的扩展以及已更新的 WebUI。\n\n- 要更新扩展，请前往 `Extension` 标签页，点击 `Check for Updates`，然后点击 `Apply and restart UI`。\n- 要更新 WebUI 本身，请在 webui.bat（或 webui.sh）所在目录执行命令 `git pull origin master`。\n\n排查问题步骤：\n\n- 检查 WebUI 输出控制台中的错误信息。\n- 在浏览器中按 F12，切换到 Console 标签页并刷新页面，在此处查找任何错误消息。\n\n常见错误：\n\n**AttributeError: module 'modules.script_callbacks' has no attribute 'on_before_reload'**\n\n如果在输出控制台看到此错误，请尝试将 WebUI 更新至最新版本。\n\n**更新**：扩展现已改为打印以下警告信息：**YOUR SD WEBUI IS OUTDATED AND AGENT SCHEDULER WILL NOT WORKING PROPERLY.** 您仍可使用该扩展，但在重新加载后可能无法正常工作。\n\n~~**ReferenceError: submit_enqueue is not defined**~~\n\n~~如果您点击 `Enqueue` 按钮无反应，并在浏览器 F12 控制台中发现上述错误，请参考 [此评论](https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler\u002Fissues\u002F4#issuecomment-1575986274) 中的步骤。~~\n\n更新：此问题现已修复。\n\n**TypeError: issubclass() arg 1 must be a class**\n请更新扩展，此问题很可能已被修复。\n\n**TypeError: Object of type X is not JSON serializable**\n请更新扩展，此问题应已修复。若仍未解决，请提交 Issue 报告并附上已安装扩展列表。\n\n对于其他错误，欢迎提交新的 [Github issue](https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler\u002Fissues\u002Fnew\u002Fchoose)。\n\n## 贡献\n\n我们欢迎对 Agent Scheduler 扩展项目的贡献！欢迎您通过 GitHub 仓库提交问题、错误报告和功能建议。\n\n如果您觉得本扩展有帮助，请给我们一个 ⭐！\n\n## 许可证\n\n本项目采用 Apache License 2.0 许可证。\n\n## 免责声明\n\n本项目的作者不对因使用本软件而产生的任何损害或法律问题负责。用户须自行确保其使用本软件时遵守所有适用法律法规，并承担与使用相关的全部风险。作者不对因输入或输出内容引发的任何版权侵犯或法律问题负责。\n\n---\n\n## 由构建 [**SIPHER\u002F\u002FAGI**](https:\u002F\u002Fsipheragi.com)、[**PROTOGAIA**](https:\u002F\u002Fprotogaia.com)、[**ATHERLABS**](https:\u002F\u002Fatherlabs.com\u002F) 与 [**SIPHER ODYSSEY**](http:\u002F\u002Fplaysipher.com\u002F) 的团队打造\n\n### 关于 ProtoGAIA\n\nProtoGAIA 为生成式 AI 图像工作流提供强大的协作功能，旨在帮助各级设计师和创意专业人士更高效地协作，释放创造力，并对创作过程实现完全透明化与追踪管理。\n\n### 当前 protoGAIA 功能\n\n作为一个致力于将生成式 AI（Generative AI）的强大能力带给大众的开源项目，ProtoGAIA 提供以下核心功能：\n\n✅ 无缝访问：支持桌面端与移动端使用\n\n✅ 强大的宏（Macro）能力，支持任务链式编排，并打包为“宏命令”，便于 AI Agent 自动化执行\n\n✅ 多人协作用户体验。提供强大的协作功能，如实时评论与反馈、版本控制、图片\u002F文件\u002F项目共享等\n\n✅ 房间聊天室（Rooms Chat），支持用户间活跃讨论，并直接在聊天中运行生成式 AI 工作流\n\n✅ 自定义模型管理，包括 Lora、扩散模型（Diffusion Models）、Controlnet 模型等\n\n✅ 强大的语义搜索能力\n\n✅ AI 驱动的智能聊天框，可快速触发生成式 AI 任务与工作流\n\n✅ 站在巨人肩上，整合 A1111\u002FVladnmandic 等先驱成果，在单一平台上实现从创意构思到最终成果的完整协作流程\n\n✅ 自动化工具，用于处理部分重复性任务\n\n✅ 安全透明，利用哈希（hashing）与元数据追踪模型、Lora、图像的来源与历史，确保可追溯性并提升协作效率\n\n✅ 个性化 UI\u002FUX 设计，兼顾新手与资深用户，可快速通过编辑提示词（prompts）与负向提示词（negative prompts）、选择新训练模型及输出质量等方式，对现有 SD 图像进行再创作\n\n✅ 所有模型、Lora、图像均支持来源追踪（Provenance Tracking），便于追溯与协作\n\n✅ 为新手与资深用户定制 UI\u002FUX，可快速通过编辑提示词与负向提示词、选择新训练模型及输出质量等方式，对现有 SD 图像进行再创作\n\n✅ 生成式 AI 学习文章与教程\n\n✅ 投票系统，评选最佳生成式 AI 图像、模型、配方、宏等\n\n✅ 通过“全局探索”（Global Explore）标签页，开放分享生成式 AI 图像、模型、配方、宏等内容\n\n### 目标用户\n\nProtoGAIA 专为以下目标用户群体设计：\n\n- 创作者\n- 小型设计团队或自由职业者\n- 设计机构与游戏工作室\n- AI Agent\n\n## 🎉 敬请关注后续更新\n\n希望您觉得本扩展实用。我们将持续添加新功能并优化体验，以更好地支持您的创意工作流。\n\n欲获取最新动态与更新，请关注我们的 GitHub 与 Twitter。我们欢迎您的反馈与建议，并期待听到 AgentScheduler 如何帮助您简化工作流程、释放创造力！","# sd-webui-agent-scheduler 快速上手指南\n\n---\n\n## 环境准备\n\n- **系统要求**：支持 Windows \u002F Linux \u002F macOS，推荐使用 NVIDIA GPU + CUDA 环境\n- **前置依赖**：\n  - 已安装并运行 [AUTOMATIC1111\u002Fstable-diffusion-webui](https:\u002F\u002Fgithub.com\u002FAUTOMATIC1111\u002Fstable-diffusion-webui) 或 [vladmandic\u002Fautomatic](https:\u002F\u002Fgithub.com\u002Fvladmandic\u002Fautomatic)\n  - WebUI 版本需为最新（至少包含 commit `baf6946` 或 `9726b4d`）\n  - 如需 API 调用，请启动时添加 `--api` 参数\n\n> 国内用户建议使用镜像加速拉取模型与扩展，如配置 `HF_ENDPOINT=https:\u002F\u002Fhf-mirror.com`\n\n---\n\n## 安装步骤\n\n### 方法一：通过内置扩展列表安装（推荐）\n\n1. 打开 WebUI → 进入 `Extensions` 标签页\n2. 切换到 `Install from URL` 子标签\n3. 在输入框粘贴仓库地址：\n   ```\n   https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler.git\n   ```\n4. 点击 `Install` 按钮，等待安装完成\n5. 重启 WebUI 生效\n\n### 方法二：手动克隆安装\n\n在 WebUI 根目录下执行：\n\n```bash\ngit clone \"https:\u002F\u002Fgithub.com\u002FArtVentureX\u002Fsd-webui-agent-scheduler.git\" extensions\u002Fagent-scheduler\n```\n\n> 可自定义文件夹名（如 `agent-scheduler`），不影响功能\n\n### 方法三：使用 Vlad Fork（已内置）\n\n若你使用的是 [vladmandic\u002Fautomatic](https:\u002F\u002Fgithub.com\u002Fvladmandic\u002Fautomatic)，该扩展已预装，无需额外安装。\n\n---\n\n## 基本使用\n\n### 1. 添加任务到队列\n\n- 在文生图（txt2img）或图生图（img2img）界面填写提示词、参数等\n- 点击 **Enqueue** 按钮，当前设置将被加入调度队列\n\n> 💡 高级技巧：右键 `Enqueue` → 选择 `Queue with all checkpoints` 可批量为所有模型创建任务\n\n### 2. 管理队列任务\n\n- 切换到 `AgentScheduler` 标签页\n- 查看当前排队任务、生成状态、历史记录\n- 支持操作：\n  - ▶️ 优先执行选中任务\n  - 🗑️ 删除任务\n  - ↔️ 拖拽调整顺序\n  - ⭐ 收藏任务便于筛选\n  - 🔍 搜索或按状态过滤\n  - ↩️ 重新入队历史任务\n\n### 3. 编辑任务参数\n\n- 双击队列中的任务 → 弹出编辑窗口\n- 可修改：任务名（task_id）、正向提示词、负向提示词、采样器、模型、步数、CFG值等\n\n### 4. 启用自动处理（默认开启）\n\n- 默认启动后自动处理队列\n- 如需手动控制，在设置中勾选 `Disable Queue Auto-Processing`\n- 在队列页可随时点击 `Pause` \u002F `Resume` 控制启停\n\n---\n\n✅ 至此，你已掌握核心功能！进阶功能如 API 调用、回调通知、自定义模型目录等，请参考官方文档或设置页面。","一位独立游戏美术师正在为新作《星尘幻想》批量生成不同风格的角色立绘，需在3种模型（写实、二次元、赛博朋克）下测试同一组提示词效果。\n\n### 没有 sd-webui-agent-scheduler 时\n- 每次切换模型都得手动重填提示词、参数和ControlNet设置，重复操作易出错且耗时。\n- 生成中途想插队紧急任务（如老板临时要的封面图），只能中断当前队列或等全部跑完，效率极低。\n- 多个任务跑完后难以回溯哪个图对应哪个模型+参数组合，常需反复截图记录，管理混乱。\n- 想对比“同一提示词 + 不同模型”的效果，必须手动逐个排队，无法一键批量调度。\n- 队列卡住或崩溃后，已排队的任务全丢失，需从头重建，浪费算力与时间。\n\n### 使用 sd-webui-agent-scheduler 后\n- 直接点击“Enqueue with all checkpoints”，自动将当前设置分发到3个模型并行排队，省去90%重复配置时间。\n- 遇到紧急任务可直接拖拽至队列顶部或点击▶️优先执行，无需中断或等待，灵活响应需求变更。\n- 所有任务历史带参数快照和结果预览，双击ID还能重命名或修改参数重新排队，版本追溯一目了然。\n- 支持按文件夹筛选模型（如只选“anime”子目录），精准控制批量范围，避免无效生成。\n- 队列支持暂停\u002F恢复，意外中断后重启WebUI仍保留任务列表，点击↩️即可续跑，保障长流程稳定性。\n\nsd-webui-agent-scheduler 把零散的手工操作转化为可视化、可调度、可追溯的自动化流水线，让AI图像生成真正融入专业生产节奏。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FSipherAGI_sd-webui-agent-scheduler_877e88e0.png","SipherAGI","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FSipherAGI_1c4ed6e4.jpg","SIPHER A.G.I, AI x GAMING x INFRASTRUCTURE",null,"sipherai@atherlabs.com","sipheragi","https:\u002F\u002Fsipheragi.com","https:\u002F\u002Fgithub.com\u002FSipherAGI",[84,88,92,96,100],{"name":85,"color":86,"percentage":87},"Python","#3572A5",66.2,{"name":89,"color":90,"percentage":91},"TypeScript","#3178c6",27.1,{"name":93,"color":94,"percentage":95},"SCSS","#c6538c",4.9,{"name":97,"color":98,"percentage":99},"JavaScript","#f1e05a",1.3,{"name":101,"color":102,"percentage":103},"CSS","#663399",0.5,691,89,"2026-04-02T16:01:58","","未说明",{"notes":110,"python":108,"dependencies":111},"需配合 Automatic1111 或 Vladmandic 的 Stable Diffusion WebUI 使用，且版本需兼容指定 commit；启动时需添加 --api 参数以启用 API 功能；建议保持 WebUI 和扩展均为最新版以避免兼容性问题。",[],[14,15,45],4,"2026-03-27T02:49:30.150509","2026-04-06T08:40:53.735823",[117,122,127,132,137,142],{"id":118,"question_zh":119,"answer_zh":120,"source_url":121},435,"“Enqueue”按钮无法点击，怎么办？","请打开注册表编辑器，导航至 HKEY_CLASSES_ROOT\\.mjs，双击“Content Type”值，将其修改为 application\u002Fjavascript，然后点击确定。","https:\u002F\u002Fgithub.com\u002FSipherAGI\u002Fsd-webui-agent-scheduler\u002Fissues\u002F4",{"id":123,"question_zh":124,"answer_zh":125,"source_url":126},436,"遇到 CUDA 错误“misaligned address”如何解决？","尝试将 CUDA 从 11.8 升级到 12.2，可参考此链接安装新库：[Cuda 12.2 New Libs](https:\u002F\u002Fcivitai.com\u002Fmodels\u002F114193\u002Fcuda-122-new-libs)。同时建议关闭 Automatic Web UI 界面再运行大批量任务，以减少错误发生。","https:\u002F\u002Fgithub.com\u002FSipherAGI\u002Fsd-webui-agent-scheduler\u002Fissues\u002F126",{"id":128,"question_zh":129,"answer_zh":130,"source_url":131},437,"更新到 A1111 1.6.0 后插件导致界面卡死，如何修复？","启动时添加 --api 参数确保模型和采样器轮询可用。若仍出现问题，请更新插件至最新版本，并检查浏览器控制台是否有类似 's.map is not a function' 的错误，这通常意味着 API 返回格式不匹配。","https:\u002F\u002Fgithub.com\u002FSipherAGI\u002Fsd-webui-agent-scheduler\u002Fissues\u002F124",{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},438,"插件是否支持显示与原生 SD 相同的动态生成进度？","进度已在每个生成步骤后更新，但若查询频率过高（快于单步执行时间），则不会看到变化。建议降低轮询频率，或等待每步完成后获取进度值，即可获得类似命令行的动态进度反馈。","https:\u002F\u002Fgithub.com\u002FSipherAGI\u002Fsd-webui-agent-scheduler\u002Fissues\u002F96",{"id":138,"question_zh":139,"answer_zh":140,"source_url":141},439,"插件使用 CDN 加载的第三方 JS 库，导致离线不可用，如何解决？","应将所有第三方依赖（如 AG Grid）打包进插件本地目录，而非从 CDN 加载。维护者需修改构建流程，将资源文件嵌入扩展包内，以支持离线环境运行。","https:\u002F\u002Fgithub.com\u002FSipherAGI\u002Fsd-webui-agent-scheduler\u002Fissues\u002F2",{"id":143,"question_zh":144,"answer_zh":145,"source_url":141},440,"任务因 CUDA OOM 崩溃后，整个队列都会失败，能否自动暂停？","目前尚无内置自动暂停功能，但开发者计划在核心中增加 OOM 检测标志。建议为此功能单独开一个新 Issue 提出请求，以便优先实现。",[]]