[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-yolain--ComfyUI-Easy-Use":3,"tool-yolain--ComfyUI-Easy-Use":61},[4,18,26,35,44,52],{"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},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。",108322,2,"2026-04-10T11:39:34",[14,15,13],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":32,"last_commit_at":41,"category_tags":42,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[43,13,15,14],"插件",{"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",[43,14],{"id":53,"name":54,"github_repo":55,"description_zh":56,"stars":57,"difficulty_score":10,"last_commit_at":58,"category_tags":59,"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",[60,15,13,14],"语言模型",{"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":75,"owner_location":75,"owner_email":75,"owner_twitter":75,"owner_website":75,"owner_url":76,"languages":77,"stars":97,"forks":98,"last_commit_at":99,"license":100,"difficulty_score":32,"env_os":101,"env_gpu":102,"env_ram":103,"env_deps":104,"category_tags":112,"github_topics":75,"view_count":32,"oss_zip_url":75,"oss_zip_packed_at":75,"status":17,"created_at":113,"updated_at":114,"faqs":115,"releases":156},6839,"yolain\u002FComfyUI-Easy-Use","ComfyUI-Easy-Use","In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.","ComfyUI-Easy-Use 是一款专为提升 ComfyUI 使用效率而设计的自定义节点集成包。它在 TinyTerraNodes 的基础上进行了深度优化，将众多流行的功能节点整合为一套流畅的工作流解决方案，旨在让用户在保留高度自由度的同时，获得接近 Stable Diffusion WebUI 的顺滑绘图体验。\n\n该工具主要解决了原生 ComfyUI 节点连接繁琐、工作流搭建耗时较长的问题。通过美化用户界面、提供预设采样参数配置节点以及简化 SD1.x、SDXL、Flux、Kolors 等多种模型的操作流程，它大幅降低了上手门槛。此外，它还集成了 Fooocus 风格提示词选择器、A1111 提示词模式兼容、智能逻辑判断（如循环与条件语句）以及高效的背景移除等实用功能，让复杂的图像生成任务变得简单直观。\n\n无论是希望快速出图的设计师、追求工作流效率的 AI 创作者，还是想要简化实验过程的研究人员，都能从中受益。其独特的亮点在于对多模型架构的统一简化支持，以及在保证功能强大的前提下，极大减少了用户在节点连线与参数调试上的时间成本，让创意构思能更快速地转化为视觉成果。","![comfyui-easy-use](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyolain_ComfyUI-Easy-Use_readme_0ec8423f3c11.png)\r\n\r\n\u003Cdiv align=\"center\">\r\n\u003Ca href=\"https:\u002F\u002Fspace.bilibili.com\u002F1840885116\">Video Tutorial\u003C\u002Fa> |\r\n\u003Ca href=\"https:\u002F\u002Fdocs.easyuse.yolain.com\">Docs\u003C\u002Fa> | \r\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\">Workflow Collection\u003C\u002Fa> |\r\n\u003Ca href=\"#%EF%B8%8F-donation\">Donation\u003C\u002Fa> \r\n\u003Cbr>\u003Cbr>\r\n\u003Ca href=\".\u002FREADME.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F🇬🇧English-0b8cf5\">\u003C\u002Fa>\r\n\u003Ca href=\".\u002FREADME.ZH_CN.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F🇨🇳中文简体-e9e9e9\">\u003C\u002Fa>\r\n\u003C\u002Fdiv>\r\n\r\n**ComfyUI-Easy-Use** is an efficiency custom nodes integration package, which is extended on the basis of [TinyTerraNodes](https:\u002F\u002Fgithub.com\u002FTinyTerra\u002FComfyUI_tinyterraNodes). It has been integrated and optimized for many popular awesome custom nodes to achieve the purpose of faster and more convenient use of ComfyUI. While ensuring the degree of freedom, it restores the ultimate smooth image production experience that belongs to Stable Diffusion.\r\n\r\n## 👨🏻‍🎨 Introduction\r\n\r\n- Inspired by [tinyterraNodes](https:\u002F\u002Fgithub.com\u002FTinyTerra\u002FComfyUI_tinyterraNodes), which greatly reduces the time cost of tossing workflows。\r\n- UI interface beautification, the first time you install the user, if you need to use the UI theme, please switch the theme in Settings -> Color Palette and refresh page.\r\n- Added a node for pre-sampling parameter configuration, which can be separated from the sampling node for easier previewing.\r\n- Wildcards and lora's are supported, for Lora Block Weight usage, ensure that the custom node package has the [ComfyUI-Inspire-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Inspire-Pack).\r\n- Multi-selectable styled cue word selector, default is Fooocus style json, custom json can be placed under styles, samples folder can be placed in the preview image (name and name consistent, image file name such as spaces need to be converted to underscores '_').\r\n- The loader enables the A1111 prompt mode, which reproduces nearly identical images to those generated by webui. \r\n- Noise injection into the latent space can be achieved using the `easy latentNoisy` or `easy preSamplingNoiseIn` node.\r\n- Simplified processes for SD1.x, SD2.x, SDXL, SVD, Zero123, etc. [Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#StableDiffusion).\r\n- Simplified Stable Cascade [Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#StableCascade).\r\n- Simplified Layer Diffuse [Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#LayerDiffusion)，The first time you use it you may need to run `pip install -r requirements.txt` to install the required dependencies.\r\n- Simplified InstantID [Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#InstantID), You need to make sure that the custom node package has the [ComfyUI_InstantID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_InstantID).\r\n- Extending the usability of XYplot.\r\n- Fooocus Inpaint integration.\r\n- Integration of common logical calculations, conversion of types, display of all types, etc.\r\n- Background removal nodes for the RMBG-1.4 model supporting BriaAI, [BriaAI Guide](https:\u002F\u002Fhuggingface.co\u002Fbriaai\u002FRMBG-1.4).\r\n- Forcibly cleared the memory usage of the comfy UI model are supported.\r\n- Stable Diffusion 3 multi-account API nodes are supported.\r\n- Support SD3's model.\r\n- Support Kolors‘s model.\r\n- Support Flux's model.\r\n- Support lazy if else and for loops.\r\n\r\n## 👨🏻‍🔧 Installation\r\nClone the repo into the **custom_nodes** directory and install the requirements:\r\n```shell\r\n#1. Clone the repo\r\ngit clone https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\r\n#2. Install the requirements\r\nDouble-click install.bat to install the required dependencies\r\n```\r\n\r\n## 📜 Changelog\r\n\r\n**v1.3.6**\r\n\r\n- Restored `easy showAnything` support for list types (but displaying large data in some cases may still cause ComfyUI to crash)\r\n- Fix custom widgets to support subgraph and Nodes 2.0 #942\r\n- Add `easy multiAngle` node\r\n- Convert `prompt.py` to V3 Schema\r\n- Fix `easy humanSegmentation` error\r\n- Add `easy stringJoinLines`，`easy stringToIntList`, `easy simpleMath`\r\n- Fix `easy ifElse` and `easy anythingIndexSwitch` fails in certain environments\r\n\r\n**v1.3.5**\r\n\r\n- Fix `isNone`\r\n- Add `preview_rescale` to `easy imageChooser`\r\n- Fix widget hidden #910\r\n- Add max parameter to `wildcardsPromptMatrix` offset #909\r\n- Fix title box style on subgraph node\r\n- Add `remove_empty_lines` on `easy promptLine`\r\n\r\n**v1.3.4**\r\n\r\n- Fix `easy seedList` max_num #879\r\n- Add controlnet input to xyplot #877\r\n- Support `nagative indexing` for `easy indexAnything`\r\n\r\n**v1.3.3**\r\n\r\n- Removed the definition of the CSS class name gird-cols-1 #859\r\n- Fix lock seed not working in `easy promptAwait`\r\n- Rename the nodes map\r\n- Fix `easy imageChooser` output error type #845\r\n\r\n**v1.3.2**\r\n\r\n- Revamp `easy imageChooser` node to adapt frontend>=v1.24.2, solution referenced from [Comfyui_LG_Tools](https:\u002F\u002Fgithub.com\u002FLAOGOU-666\u002FComfyui_LG_Tools)\r\n- Revamp `easy stylesSelector` node, and you can download [other styles files](https:\u002F\u002Fgithub.com\u002Fyolain\u002FEasyUse-Styles-Templates) to the `styles` folder\r\n- Revamp `easy humanSegmentation` node\r\n- Fix `easy makeImageForICLora` node issue, that occurred when the heights of two images were the same during image stitching on.\r\n- Add `easy joycaption3API` node\r\n- Add `easy promptAwait` node\r\n\r\n**v1.3.1**\r\n\r\n- Rewrite drawNodeWidget and fix the GroupNode preview issue.\r\n- Updated some features of XYPlot  by [mekinney](https:\u002F\u002Fgithub.com\u002Fmekinney)\r\n- Add `easy seedList` node (It's useful for in loops)\r\n\r\n**v1.3.0**\r\n\r\n- Set loop nodes maximum number of inputs and outputs to 20\r\n- Add `uniform width` method to `easy makeImageForICLora`\r\n- Add `wildcardsPromptMatrix` Node by [Rosmeowtis](https:\u002F\u002Fgithub.com\u002FRosmeowtis)\r\n\r\n**v1.2.9**\r\n\r\n- Fix ImageChooser causes workflow processing to cancel\r\n- Fix brushnet tensor(640) error\r\n- Fix widgets not hidden after v1.6.0 frontend\r\n- Fix image chooser can not select images\r\n- Fix contextMenu monkey patching to affect custom scripts (pysssss) nodes\r\n\r\n**v1.2.8**\r\n\r\n- Added the multi-language catalog \r\n- Fix CLIP vision model download URLs for IPAdapter and DynamiCrafter\r\n- Improve error handling for model downloads with clearer error messages and better handling of download failures\r\n\r\n**v1.2.7**\r\n\r\n- Optimize display of the node maps\r\n- Added `ben2` on `easy imageRemBg`\r\n- Using a new way to display the models thumbnails in the loaders (supported diffusion_models、lors、checkpoints)\r\n\r\n**v1.2.6**\r\n\r\n- Fix missing the \"Red Rect\" styles when you are missing custom nodes.\r\n- Adjust the default value of `clip_skip` from `-1` to `-2` in some easy loaders.\r\n- Fix the issue due to set nodes missing custom nodes which their connected, causing canvas to be messed up.\r\n- Fix the `easy imageChooser` can not using in a loop.\r\n\r\n**v1.2.5**\r\n\r\n- Added `enable (GPU=A1111)` noise mode on `easy preSamplingCustom` and `easy preSamplingAdvanced` \r\n- Added `easy makeImageForICLora`\r\n- Added `REGULAR - FLUX and SD3.5 only (high strength)` preset for InstantX Flux ipadapter on `easy ipadapterApply`\r\n- Fix brushnet can not be used with startup arg `--fast` mode\r\n- Support briaai RMBG-2.0\r\n- Support mochi \r\n- Implement reuse of end nodes output in the loop body (e.g: previewImage and showAnything and sth.) \r\n\r\n**v1.2.4**\r\n\r\n- Added `easy imageSplitTiles` and `easy imageTilesFromBatch`\r\n- Support `model_override`,`vae_override`,`clip_override` can be input separately to `easy fullLoader`\r\n- Added `easy saveImageLazy`\r\n- Added `easy loadImageForLoop`\r\n- Added `easy isFileExist`\r\n- Added `easy saveText`\r\n\r\n**v1.2.3**\r\n\r\n- `easy showAnything` and `easy cleanGPUUsed` added slot of output\r\n- Added human parts segmentation to `easy humanSegmentation` - Code based on [ComfyUI_Human_Parts](https:\u002F\u002Fgithub.com\u002Fmetal3d\u002FComfyUI_Human_Parts)\r\n- Using FluxGuidance when you are using a flux model and choose basicGuider and set the cfg>0 on `easy preSamplingCustom`\r\n- Added `easy loraStackApply` and `easy controlnetStackApply` - Apply loraStack and controlnetStack\r\n\r\n**v1.2.2**\r\n\r\n- Added `easy batchAny`\r\n- Added `easy anythingIndexSwitch`\r\n- Added `easy forLoopStart` and `easy forLoopEnd`  \r\n- Added `easy ifElse`  \r\n- Added v2 web frond-end code\r\n- Added `easy fluxLoader`\r\n- Added support for `controlnetApply` Related nodes with SD3 and hunyuanDiT\r\n- Fixed after using `easy applyFooocusInpaint`, all lora models become unusable\r\n\r\n**v1.2.1**\r\n\r\n- Added `easy ipadapterApplyFaceIDKolors`\r\n- Added **inspyrenet** to `easy imageRemBg` \r\n- Added `easy controlnetLoader++`\r\n- Added **PLUS (kolors genernal)** and **FACEID PLUS KOLORS** preset to `easy ipadapterApply` and `easy ipadapterApplyADV` (Supported kolors ipadapter）\r\n- Added `easy kolorsLoader` - Code based on [MinusZoneAI](https:\u002F\u002Fgithub.com\u002FMinusZoneAI\u002FComfyUI-Kolors-MZ)'s and [kijai](https:\u002F\u002Fgithub.com\u002Fkijai\u002FComfyUI-KwaiKolorsWrapper)'s repo, thanks for their contribution.\r\n\r\n**v1.2.0**\r\n\r\n- Added `easy pulIDApply` and `easy pulIDApplyADV`\r\n- Added `easy huanyuanDiTLoader` and `easy pixArtLoader`\r\n- Added **easy sliderControl** - Slider control node, which can currently be used to control the parameters of ipadapterMS (double-click the slider to reset to default)\r\n- Added **layer_weights** in `easy ipadapterApplyADV`\r\n\r\n**v1.1.9**\r\n\r\n- Added **gitsScheduler**\r\n- Added `easy imageBatchToImageList` and `easy imageListToImageBatch` \r\n- Recursive subcategories nested for models\r\n- Support for Stable Diffusion 3 model\r\n- Added `easy applyInpaint` - All inpainting mode in this node\r\n\r\n**v1.1.8**\r\n\r\n- Added `easy controlnetStack`\r\n- Added `easy applyBrushNet` - [Workflow Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4brushnet_1.1.8.json)\r\n- Added `easy applyPowerPaint` - [Workflow Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4powerpaint_outpaint_1.1.8.json)\r\n\r\n**v1.1.7**\r\n\r\n- Added `easy prompt` - Subject and light presets, maybe adjusted later\r\n- Added `easy icLightApply` - Light and shadow migration, Code based on [ComfyUI-IC-Light](https:\u002F\u002Fgithub.com\u002Fhuchenlei\u002FComfyUI-IC-Light)\r\n- Added `easy imageSplitGrid`\r\n- `easy kSamplerInpainting` added options such as different diffusion and brushnet in **additional** widget\r\n- Support for brushnet model loading - [ComfyUI-BrushNet](https:\u002F\u002Fgithub.com\u002Fnullquant\u002FComfyUI-BrushNet)\r\n- Added `easy applyFooocusInpaint` - Replace FooocusInpaintLoader\r\n- Removed `easy fooocusInpaintLoader`\r\n\r\n**v1.1.6**\r\n\r\n- Added **alignYourSteps** to **schedulder** widget in all `easy preSampling` and `easy fullkSampler`\r\n- Added **Preview&Choose** to **image_output** widget in `easy kSampler` & `easy fullkSampler`\r\n- Added `easy styleAlignedBatchAlign` - Credit of [style_aligned_comfy](https:\u002F\u002Fgithub.com\u002Fbrianfitzgerald\u002Fstyle_aligned_comfy)\r\n- Added `easy ckptNames`\r\n- Added `easy controlnetNames`\r\n- Added `easy imagesSplitimage` - Batch images split into single images\r\n- Added `easy imageCount` - Get Image Count\r\n- Added `easy textSwitch` - Text Switch\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.1.5\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Rewrite `easy cleanGPUUsed` - the memory usage of the comfyUI can to be cleared\r\n- Added `easy humanSegmentation` - Human Part Segmentation\r\n- Added `easy imageColorMatch`\r\n- Added `easy ipadapterApplyRegional`\r\n- Added `easy ipadapterApplyFromParams`\r\n- Added `easy imageInterrogator` - Image To Prompt\r\n- Added `easy stableDiffusion3API` - Easy Stable Diffusion 3 Multiple accounts API Node\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.1.4\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy preSamplingCustom` - Custom-PreSampling, can be supported cosXL-edit\r\n- Added `easy ipadapterStyleComposition`\r\n- Added the right-click menu to view checkpoints and lora information in all Loaders\r\n- Fixed `easy preSamplingNoiseIn`、`easy latentNoisy`、`east Unsampler` compatible with ComfyUI Revision>=2098 [0542088e] or later\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.1.3\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- `easy ipadapterApply` Added **COMPOSITION** preset\r\n- Supported [ResAdapter](https:\u002F\u002Fhuggingface.co\u002Fjiaxiangc\u002Fres-adapter) when load ResAdapter lora\r\n- Added `easy promptLine`\r\n- Added `easy promptReplace`\r\n- Added `easy promptConcat`\r\n- `easy wildcards` Added **multiline_mode**  \r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.1.2\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Optimized some of the recommended nodes for slots related to EasyUse\r\n- Added **Enable ContextMenu Auto Nest Subdirectories** The setting item is enabled by default, and it can be classified into subdirectories, checkpoints and loras previews\r\n- Added `easy sv3dLoader` \r\n- Added `easy dynamiCrafterLoader` \r\n- Added `easy ipadapterApply`\r\n- Added `easy ipadapterApplyADV`\r\n- Added `easy ipadapterApplyEncoder`\r\n- Added `easy ipadapterApplyEmbeds`\r\n- Added `easy preMaskDetailerFix`\r\n- Fixed `easy stylesSelector` is change the prompt when not select the style\r\n- Fixed `easy pipeEdit` error when add lora to prompt\r\n- Fixed layerDiffuse xyplot bug\r\n- `easy kSamplerInpainting` add *additional* widget，you can choose 'Differential Diffusion' or 'Only InpaintModelConditioning'\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.1.1\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- The issue that the seed is 0 when a node with a seed control is added and **control before generate** is fixed for the first time run queue prompt.\r\n- `easy preSamplingAdvanced` Added **return_with_leftover_noise**\r\n- Fixed `easy stylesSelector` error when choose the custom file\r\n- `easy preSamplingLayerDiffusion` Added optional input parameter for mask\r\n- Renamed all nodes widget name named seed_num to seed\r\n- Remove forced **control_before_generate** settings。 If you want to use control_before_generate, change widget_value_control_mode to before in system settings\r\n- Added `easy imageRemBg` - The default is BriaAI's RMBG-1.4 model, which removes the background effect more and faster\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.1.0\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy imageSplitList` - to split every N images\r\n- Added `easy preSamplingDiffusionADDTL` - It can modify foreground、background or blended additional prompt\r\n- Added `easy preSamplingNoiseIn` It can replace the `easy latentNoisy` node that needs to be fronted to achieve better noise injection\r\n- `easy pipeEdit` Added conditioning splicing mode selection, you can choose to replace, concat, combine, average, and set timestep range\r\n- Added `easy pipeEdit` - nodes that can edit pipes (including re-enterable prompts)\r\n- Added `easy preSamplingLayerDiffusion` and `easy kSamplerLayerDiffusion`\r\n- Added a convenient menu to right-click on nodes such as Loader, Presampler, Sampler, Controlnet, etc. to quickly replace nodes of the same type\r\n- Added `easy instantIDApplyADV` can link positive and negative\r\n- Fixed layerDiffusion error when batch size greater than 1\r\n- Fixed `easy wildcards` When LoRa is not filled in completely, LoRa is not automatically retrieved, resulting in failure to load LoRa\r\n- Fixed the issue that 'BREAK' non-initiation when didn't use a1111 prompt style\r\n- Fixed `easy instantIDApply` mask not input right\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.9\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Fixed the error when ComfyUI-Impack-Pack and ComfyUI_InstantID were not installed\r\n- Fixed `easy pipeIn`\r\n- Added `easy instantIDApply` - you need installed [ComfyUI_InstantID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_InstantID) fisrt, Workflow[Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fblob\u002Fmain\u002FREADME.en.md#InstantID)\r\n- Fixed `easy detailerFix` not added to the list of nodes available for saving images formatting extensions\r\n- Fixed `easy XYInputs: PromptSR` errors are reported when replacing negative prompts\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.8\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- `easy cascadeLoader` stage_c and stage_b support the checkpoint model (Download [checkpoints](https:\u002F\u002Fhuggingface.co\u002Fstabilityai\u002Fstable-cascade\u002Ftree\u002Fmain\u002Fcomfyui_checkpoints) models) \r\n- `easy styleSelector` The search box is modified to be case-insensitive\r\n- `easy fullLoader` **positive**、**negative**、**latent** added to the output items\r\n- Fixed the issue that 'easy preSampling' and other similar node, latent could not be generated based on the batch index after passing in\r\n- Fixed `easy svdLoader` error when the positive or negative is empty\r\n- Fixed the error of SDXLClipModel in ComfyUI revision 2016[c2cb8e88] and above (the revision number was judged to be compatible with the old revision)\r\n- Fixed `easy detailerFix` generation error when batch size is greater than 1\r\n- Optimize the code, reduce a lot of redundant code and improve the running speed\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.7\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy cascadeLoader` - stable cascade Loader\r\n- Added `easy preSamplingCascade` - stable cascade preSampling Settings\r\n- Added `easy fullCascadeKSampler` - stable cascade stage-c ksampler full\r\n- Added `easy cascadeKSampler` - stable cascade stage-c ksampler simple\r\n- \r\n- Optimize the image to image[Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fblob\u002Fmain\u002FREADME.en.md#image-to-image)\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.6\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy XYInputs: Checkpoint`\r\n- Added `easy XYInputs: Lora`\r\n- `easy seed` can manually switch the random seed when increasing the fixed seed value\r\n- Fixed `easy fullLoader` and all loaders to automatically adjust the node size when switching LoRa\r\n- Removed the original ttn image saving logic and adapted to the default image saving format extension of ComfyUI\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.5\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy isSDXL` \r\n- Added prompt word control on `easy svdLoader`, which can be used with open_clip model\r\n- Added **populated_text** on `easy wildcards`, wildcard populated text can be output\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.4\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- `easy showAnything` added support for converting other types (e.g., tensor conditions, images, etc.)\r\n- Added `easy showLoaderSettingsNames` can display the model and VAE name in the output loader assembly\r\n- Added `easy promptList`\r\n- Added `easy fooocusInpaintLoader` （only the process of SDXLModel is supported）\r\n- Added **Logic** nodes\r\n- Added `easy imageSave` - Image saving node with date conversion and aspect and height formatting\r\n- Added `easy joinImageBatch`\r\n- `easy kSamplerInpainting` Added the **patch** input value to be used with the FooocusInpaintLoader node\r\n\r\n- Fixed xyplot error when with Pillow>9.5\r\n- Fixed `easy wildcards` An error is reported when running with the PS extension\r\n- Fixed `easy XYInputs: ControlNet` Error\r\n- Fixed `easy loraStack` error when **toggle** is disabled\r\n\r\n\r\n- Changing the first-time install node package no longer automatically replaces the theme, you need to manually adjust and refresh the page\r\n- `easy imageSave` added **only_preivew**\r\n- Adjust the `easy latentCompositeMaskedWithCond` node\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.3\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy stylesSelector`\r\n- Added **scale_soft_weights** in `easy controlnetLoader` and `easy controlnetLoaderADV` \r\n- Added the queue progress bar setting item, which is not enabled by default\r\n\r\n\r\n- Fixed `easy XYInputs: Sampler\u002FScheduler` Error\r\n- Fixed the right menu has a problem when clicking the button\r\n- Fixed `easy comfyLoader` error\r\n- Fixed xyPlot error when connecting to zero123\r\n- Fixed the error message in the loader when the prompt word was component\r\n- Fixed `easy getNode` and `easy setNode` the title does not change when loading\r\n- Fixed all samplers using subdirectories to store images\r\n\r\n\r\n- Adjust the UI theme, divided into two sets of styles: the official default background and the dark black background, which can be switched in the color palette in the settings\r\n- Modify the styles path to be compatible with other environments\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.2\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy XYPlotAdvanced` and some nodes about `easy XYInputs`\r\n- Added **Alt+1-Alt+9** Shortcut keys to quickly paste node presets for Node templates (corresponding to 1~9 sequences)\r\n- Added a `📜Groups Map(EasyUse)` to the context menu.\r\n- An `autocomplete` folder has been added, If you have [ComfyUI-Custom-Scripts](https:\u002F\u002Fgithub.com\u002Fpythongosssss\u002FComfyUI-Custom-Scripts) installed, the txt files in that folder will be merged and overwritten to the autocomplete .txt file of the pyssss package at startup.\r\n\r\n\r\n- Fixed XYPlot is not working when `a1111_prompt_style` is True\r\n- Fixed UI loading failure in the new version of ComfyUI\r\n- `easy XYInputs ModelMergeBlocks` Values can be imported from CSV files\r\n- Fixed `easy pipeToBasicPipe` Bug\r\n\r\n- Removed `easy imageRemBg`\r\n- Remove the introductory diagram and workflow files from the package to reduce the package size\r\n- Replaced the font file used in the generation of XY diagrams\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.1\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Fixed `easy comfyLoader` error\r\n- Fixed All nodes that contain the value of the image size\r\n- Added `easy kSamplerInpainting`\r\n- Added `easy pipeToBasicPipe`\r\n- Fixed `width` and `height` can not customize in `easy svdLoader`\r\n- Fixed all preview image path (Previously, it was not possible to preview the image on the Mac system)\r\n- Fixed `vae_name` is not working in `easy fullLoader` and `easy a1111Loader` and `easy comfyLoader`\r\n- Fixed `easy fullkSampler` outputs error\r\n- Fixed `model_override` is not working in `easy fullLoader`\r\n- Fixed `easy hiresFix` error\r\n- Fixed `easy xyplot` font file path error\r\n- Fixed seed that cannot be fixed when you convert `seed_num` to `easy seed` \r\n- Fixed `easy pipeIn` inputs bug\r\n- `easy preDetailerFix` have added a new parameter `optional_image`\r\n- Fixed `easy zero123Loader` and `easy svdLoader` model into cache.\r\n- Added `easy seed`\r\n- Fixed `image_output` default value is \"Preview\"\r\n- `easy fullLoader` and `easy a1111Loader` have added a new parameter `a1111_prompt_style`,that can reproduce the same image generated from stable-diffusion-webui on comfyui, but you need to install [ComfyUI_smZNodes](https:\u002F\u002Fgithub.com\u002Fshiimizu\u002FComfyUI_smZNodes) to use this feature in the current version\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>v1.0.0\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- Added `easy positive` - simple positive prompt text\r\n- Added `easy negative` - simple negative prompt text\r\n- Added `easy wildcards` - support for wildcards and hint text selected by Lora\r\n- Added `easy portraitMaster` - PortraitMaster v2.2\r\n- Added `easy loraStack` - Lora stack\r\n- Added `easy fullLoader` - full version of the loader\r\n- Added `easy zero123Loader` - simple zero123 loader\r\n- Added `easy svdLoader` - easy svd loader\r\n- Added `easy fullkSampler` - full version of the sampler (no separation)\r\n- Added `easy hiresFix` - support for HD repair of Pipe\r\n- Added `easy predetailerFix` and `easy DetailerFix` - support for Pipe detail fixing\r\n- Added `easy ultralyticsDetectorPipe` and `easy samLoaderPipe` - Detect loader (detail fixed input)\r\n- Added `easy pipein` `easy pipeout` - Pipe input and output\r\n- Added `easy xyPlot` - simple xyplot (more controllable parameters will be updated in the future)\r\n- Added `easy imageRemoveBG` - image to remove background\r\n- Added `easy imagePixelPerfect` - image pixel perfect\r\n- Added `easy poseEditor` - Pose editor\r\n- New UI Theme (Obsidian) - Auto-load UI by default, which can also be changed in the settings \r\n\r\n- Fixed `easy globalSeed` is not working\r\n- Fixed an issue where all `seed_num` values were out of order due to [cg-use-everywhere](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-use-everywhere) updating the chart in real time\r\n- Fixed `easy imageSize`, `easy imageSizeBySide`, `easy imageSizeByLongerSide` as end nodes\r\n- Fixed the bug that `seed_num` (random seed value) could not be read consistently in history\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>Updated at 12\u002F14\u002F2023\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n- `easy a1111Loader` and `easy comfyLoader` added `batch_size` of required input parameters \r\n- Added the `easy controlnetLoaderADV` node\r\n- `easy controlnetLoaderADV` and `easy controlnetLoader` added `control_net ` of optional input parameters\r\n- `easy preSampling` and `easy preSamplingAdvanced` added `image_to_latent` optional input parameters\r\n- Added the `easy imageSizeBySide` node, which can be output as a long side or a short side\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>Updated at 12\u002F13\u002F2023\u003C\u002Fb>\u003C\u002Fsummary>\r\n\r\n-  Added the `easy LLLiteLoader` node, if you have pre-installed the kohya-ss\u002FControlNet-LLLite-ComfyUI package, please move the model files in the models to `ComfyUI\\models\\controlnet\\` (i.e. in the default controlnet path of comfy, please do not change the file name of the model, otherwise it will not be read).\r\n-  Modify `easy controlnetLoader` to the bottom of the loader category.\r\n-  Added size display for `easy imageSize` and `easy imageSizeByLongerSize` outputs.\r\n\u003C\u002Fdetails>\r\n\r\n\u003Cdetails>\r\n\u003Csummary>\u003Cb>Updated at 12\u002F11\u002F2023\u003C\u002Fb>\u003C\u002Fsummary>\r\n-  Added the `showSpentTime` node to display the time spent on image diffusion and the time spent on VAE decoding images\r\n\u003C\u002Fdetails>\r\n\r\n## The relevant node package involved\r\n\r\nDisclaimer: Opened source was not easy. I have a lot of respect for the contributions of these original authors. I just did some integration and optimization.\r\n\r\n| Nodes Name(Search Name)        | Related libraries                                                                        | Library-related node     |\r\n|:-------------------------------|:----------------------------------------------------------------------------|:-------------------------|\r\n| easy setNode                   | [ComfyUI-extensions](https:\u002F\u002Fgithub.com\u002Fdiffus3\u002FComfyUI-extensions) | diffus3.SetNode          |\r\n| easy getNode                   | [ComfyUI-extensions](https:\u002F\u002Fgithub.com\u002Fdiffus3\u002FComfyUI-extensions) | diffus3.GetNode          |\r\n| easy bookmark                  | [rgthree-comfy](https:\u002F\u002Fgithub.com\u002Frgthree\u002Frgthree-comfy) | Bookmark 🔖              |\r\n| easy portraitMarker            | [comfyui-portrait-master](https:\u002F\u002Fgithub.com\u002Fflorestefano1975\u002Fcomfyui-portrait-master) | Portrait Master          |\r\n| easy LLLiteLoader              | [ControlNet-LLLite-ComfyUI](https:\u002F\u002Fgithub.com\u002Fkohya-ss\u002FControlNet-LLLite-ComfyUI) | LLLiteLoader             |\r\n| easy globalSeed                | [ComfyUI-Inspire-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Inspire-Pack) | Global Seed (Inspire)    | \r\n| easy preSamplingDynamicCFG     | [sd-dynamic-thresholding](https:\u002F\u002Fgithub.com\u002Fmcmonkeyprojects\u002Fsd-dynamic-thresholding) | DynamicThresholdingFull  | \r\n| dynamicThresholdingFull        | [sd-dynamic-thresholding](https:\u002F\u002Fgithub.com\u002Fmcmonkeyprojects\u002Fsd-dynamic-thresholding) | DynamicThresholdingFull  | \r\n| easy imageInsetCrop            | [rgthree-comfy](https:\u002F\u002Fgithub.com\u002Frgthree\u002Frgthree-comfy) | ImageInsetCrop           | \r\n| easy poseEditor                | [ComfyUI_Custom_Nodes_AlekPet](https:\u002F\u002Fgithub.com\u002FAlekPet\u002FComfyUI_Custom_Nodes_AlekPet) | poseNode                 | \r\n| easy preSamplingLayerDiffusion | [ComfyUI-layerdiffusion](https:\u002F\u002Fgithub.com\u002Fhuchenlei\u002FComfyUI-layerdiffusion) | LayeredDiffusionApply... | \r\n| easy dynamiCrafterLoader       | [ComfyUI-layerdiffusion](https:\u002F\u002Fgithub.com\u002FExponentialML\u002FComfyUI_Native_DynamiCrafter) | Apply Dynamicrafter    | \r\n| easy imageChooser              | [cg-image-picker](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-image-picker) | Preview Chooser         | \r\n| easy styleAlignedBatchAlign              | [style_aligned_comfy](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-image-picker) | styleAlignedBatchAlign       | \r\n| easy kolorsLoader              | [ComfyUI-Kolors-MZ](https:\u002F\u002Fgithub.com\u002FMinusZoneAI\u002FComfyUI-Kolors-MZ) | kolorsLoader            |\r\n\r\n\r\n## Credits\r\n\r\n[ComfyUI](https:\u002F\u002Fgithub.com\u002Fcomfyanonymous\u002FComfyUI) - Powerful and modular Stable Diffusion GUI\r\n\r\n[ComfyUI-ComfyUI-Manager](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Manager) - ComfyUI Manager\r\n\r\n[tinyterraNodes](https:\u002F\u002Fgithub.com\u002FTinyTerra\u002FComfyUI_tinyterraNodes) - Pipe nodes (node bundles) allow users to reduce unnecessary connections\r\n\r\n[ComfyUI-extensions](https:\u002F\u002Fgithub.com\u002Fdiffus3\u002FComfyUI-extensions) - Diffus3 gets and sets points that allow the user to detach the composition of the workflow \r\n\r\n[ComfyUI-Impact-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Impact-Pack) - General modpack 1\r\n\r\n[ComfyUI-Inspire-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Inspire-Pack) - General Modpack 2\r\n\r\n[ComfyUI-ResAdapter](https:\u002F\u002Fgithub.com\u002Fjiaxiangc\u002FComfyUI-ResAdapter) - Make model generation independent of training resolution\r\n\r\n[ComfyUI_IPAdapter_plus](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_IPAdapter_plus) - Style migration\r\n\r\n[ComfyUI_InstantID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_InstantID) - Face migration\r\n\r\n[ComfyUI_PuLID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FPuLID_ComfyUI) - Face migration\r\n\r\n[ComfyUI-Custom-Scripts](https:\u002F\u002Fgithub.com\u002Fpythongosssss\u002FComfyUI-Custom-Scripts) - pyssss🐍\r\n\r\n[cg-image-picker](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-image-picker) - Image Preview Chooser\r\n\r\n[ComfyUI_ExtraModels](https:\u002F\u002Fgithub.com\u002Fcity96\u002FComfyUI_ExtraModels) - DiT custom nodes\r\n\r\n## Disclaimer\r\n\r\nThis software is provided “as is,” without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.\r\n\r\nUsers are solely responsible for ensuring that their use of this software complies with all applicable laws and regulations in the jurisdiction where they use the software or publish content generated by it. The authors and copyright holders are not responsible for any violations of laws or regulations by users in their respective locations.\r\n\r\n## ☕️ Donation\r\n\r\n**Comfyui-Easy-Use** is an GPL-licensed open source project. In order to achieve better and sustainable development of the project, i expect to gain more backers. \u003Cbr>\r\nIf my custom nodes has added value to your day, consider indulging in a coffee to fuel it further! \u003Cbr>\r\n💖You can support me in any of the following ways:\r\n\r\n- [BiliBili](https:\u002F\u002Fspace.bilibili.com\u002F1840885116)\r\n- [Wechat \u002F Alipay](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F803469bd-ed6a-4fab-932d-50e5088a2d03)\r\n\r\n##  🌟Stargazers\r\n\r\nMy gratitude extends to the generous souls who bestow a star. Your support is much appreciated!\r\n\r\n[![Stargazers repo roster for @yolain\u002FComfyUI-Easy-Use](https:\u002F\u002Freporoster.com\u002Fstars\u002Fyolain\u002FComfyUI-Easy-Use)](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fstargazers)\r\n\r\n","![comfyui-easy-use](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyolain_ComfyUI-Easy-Use_readme_0ec8423f3c11.png)\n\n\u003Cdiv align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fspace.bilibili.com\u002F1840885116\">视频教程\u003C\u002Fa> |\n\u003Ca href=\"https:\u002F\u002Fdocs.easyuse.yolain.com\">文档\u003C\u002Fa> | \n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\">工作流合集\u003C\u002Fa> |\n\u003Ca href=\"#%EF%B8%8F-donation\">捐赠\u003C\u002Fa> \n\u003Cbr>\u003Cbr>\n\u003Ca href=\".\u002FREADME.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F🇬🇧English-0b8cf5\">\u003C\u002Fa>\n\u003Ca href=\".\u002FREADME.ZH_CN.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F🇨🇳中文简体-e9e9e9\">\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n**ComfyUI-Easy-Use** 是一个效率型自定义节点集成包，基于 [TinyTerraNodes](https:\u002F\u002Fgithub.com\u002FTinyTerra\u002FComfyUI_tinyterraNodes) 进行扩展。它整合并优化了众多热门且强大的自定义节点，旨在让 ComfyUI 的使用更加高效便捷，在保证自由度的同时，还原 Stable Diffusion 系统下极致流畅的图像生成体验。\n\n## 👨🏻‍🎨 简介\n\n- 受 [tinyterraNodes](https:\u002F\u002Fgithub.com\u002FTinyTerra\u002FComfyUI_tinyterraNodes) 启发，大幅减少工作流搭建的时间成本。\n- 界面美化：首次安装时，若需使用 UI 主题，请在“设置 -> 颜色方案”中切换主题并刷新页面。\n- 新增预采样参数配置节点，可与采样节点分离，便于预览。\n- 支持通配符和 LoRA 模型；如需使用 LoRA 权重块功能，确保自定义节点包中已包含 [ComfyUI-Inspire-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Inspire-Pack)。\n- 提供多选式风格提示词选择器，默认使用 Fooocus 风格 JSON 文件；自定义 JSON 文件可放置于 `styles` 文件夹下，预览图则应放在 `samples` 文件夹中（文件名需保持一致，空格需替换为下划线 `_`）。\n- 加载器支持 A1111 提示词模式，可复现与 WebUI 生成效果几乎完全一致的图像。\n- 可通过 `easy latentNoisy` 或 `easy preSamplingNoiseIn` 节点向潜在空间注入噪声。\n- 简化了 SD1.x、SD2.x、SDXL、SVD、Zero123 等模型的流程。[示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#StableDiffusion)。\n- 简化了 Stable Cascade 流程。[示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#StableCascade)。\n- 简化了 Layer Diffusion 流程。[示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#LayerDiffusion)。首次使用时，可能需要运行 `pip install -r requirements.txt` 安装所需依赖。\n- 简化了 InstantID 流程。[示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use?tab=readme-ov-file#InstantID)。请确保自定义节点包中已包含 [ComfyUI_InstantID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_InstantID)。\n- 扩展了 XYplot 的实用性。\n- 集成了 Fooocus 掩码修复功能。\n- 整合了常见的逻辑运算、类型转换及各类显示功能等。\n- 提供基于 RMBG-1.4 模型的背景移除节点，支持 BriaAI。[BriaAI 使用指南](https:\u002F\u002Fhuggingface.co\u002Fbriaai\u002FRMBG-1.4)。\n- 支持强制清理 ComfyUI 模型占用的显存。\n- 支持 Stable Diffusion 3 多账号 API 节点。\n- 支持 SD3 模型。\n- 支持 Kolors 模型。\n- 支持 Flux 模型。\n- 支持懒惰版 if-else 和 for 循环。\n\n## 👨🏻‍🔧 安装\n将仓库克隆至 **custom_nodes** 目录，并安装依赖：\n```shell\n#1. 克隆仓库\ngit clone https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\n#2. 安装依赖\n双击运行 `install.bat` 以安装所需依赖\n```\n\n## 📜 更改记录\n\n**v1.3.6**\n\n- 恢复了 `easy showAnything` 对列表类型的支持（但在某些情况下显示大量数据仍可能导致 ComfyUI 崩溃）\n- 修复自定义组件以支持子图和 Nodes 2.0 #942\n- 添加 `easy multiAngle` 节点\n- 将 `prompt.py` 转换为 V3 Schema\n- 修复 `easy humanSegmentation` 错误\n- 添加 `easy stringJoinLines`、`easy stringToIntList`、`easy simpleMath`\n- 修复 `easy ifElse` 和 `easy anythingIndexSwitch` 在某些环境下的失败问题\n\n**v1.3.5**\n\n- 修复 `isNone`\n- 向 `easy imageChooser` 添加 `preview_rescale`\n- 修复组件隐藏问题 #910\n- 向 `wildcardsPromptMatrix` 添加最大参数偏移 #909\n- 修复子图节点上的标题框样式\n- 在 `easy promptLine` 上添加 `remove_empty_lines`\n\n**v1.3.4**\n\n- 修复 `easy seedList` 的 max_num #879\n- 向 xyplot 添加 ControlNet 输入 #877\n- 支持 `easy indexAnything` 的负索引\n\n**v1.3.3**\n\n- 移除了 CSS 类名 gird-cols-1 的定义 #859\n- 修复 `easy promptAwait` 中锁定种子无效的问题\n- 重命名节点映射\n- 修复 `easy imageChooser` 输出错误类型 #845\n\n**v1.3.2**\n\n- 重构 `easy imageChooser` 节点，以适配前端>=v1.24.2，解决方案参考自 [Comfyui_LG_Tools](https:\u002F\u002Fgithub.com\u002FLAOGOU-666\u002FComfyui_LG_Tools)\n- 重构 `easy stylesSelector` 节点，并可将[其他样式文件](https:\u002F\u002Fgithub.com\u002Fyolain\u002FEasyUse-Styles-Templates)下载到 `styles` 文件夹中\n- 重构 `easy humanSegmentation` 节点\n- 修复 `easy makeImageForICLora` 节点在图像拼接时两幅图像高度相同导致的问题\n- 添加 `easy joycaption3API` 节点\n- 添加 `easy promptAwait` 节点\n\n**v1.3.1**\n\n- 重写 drawNodeWidget 并修复 GroupNode 预览问题。\n- 由 [mekinney](https:\u002F\u002Fgithub.com\u002Fmekinney) 更新了 XYPlot 的部分功能\n- 添加 `easy seedList` 节点（在循环中非常有用）\n\n**v1.3.0**\n\n- 将循环节点的输入输出数量上限设置为 20\n- 向 `easy makeImageForICLora` 添加 `uniform width` 方法\n- 由 [Rosmeowtis](https:\u002F\u002Fgithub.com\u002FRosmeowtis) 添加 `wildcardsPromptMatrix` 节点\n\n**v1.2.9**\n\n- 修复 ImageChooser 导致工作流处理取消的问题\n- 修复 brushnet tensor(640) 错误\n- 修复前端 v1.6.0 之后组件未隐藏的问题\n- 修复 image chooser 无法选择图片的问题\n- 修复 contextMenu monkey patching 影响自定义脚本 (pysssss) 节点的问题\n\n**v1.2.8**\n\n- 添加多语言目录\n- 修复 IPAdapter 和 DynamiCrafter 的 CLIP 视觉模型下载地址\n- 改进模型下载的错误处理，提供更清晰的错误信息并更好地处理下载失败的情况\n\n**v1.2.7**\n\n- 优化节点地图的显示\n- 在 `easy imageRemBg` 上添加 `ben2`\n- 使用新方式在加载器中显示模型缩略图（支持 diffusion_models、lors、checkpoints）\n\n**v1.2.6**\n\n- 修复缺少自定义节点时“Red Rect”样式缺失的问题。\n- 在一些 easy 加载器中将 `clip_skip` 的默认值从 `-1` 调整为 `-2`。\n- 修复由于设置节点缺少其连接的自定义节点而导致画布混乱的问题。\n- 修复 `easy imageChooser` 无法在循环中使用的问题。\n\n**v1.2.5**\n\n- 在 `easy preSamplingCustom` 和 `easy preSamplingAdvanced` 上添加 `enable (GPU=A1111)` 噪音模式\n- 添加 `easy makeImageForICLora`\n- 在 `easy ipadapterApply` 上为 InstantX Flux ipadapter 添加 `REGULAR - FLUX and SD3.5 only (high strength)` 预设\n- 修复 brushnet 无法与启动参数 `--fast` 模式一起使用的问题\n- 支持 briaai RMBG-2.0\n- 支持 mochi \n- 实现循环体内末端节点输出的复用（例如：previewImage 和 showAnything 等）\n\n**v1.2.4**\n\n- 添加 `easy imageSplitTiles` 和 `easy imageTilesFromBatch`\n- 支持 `model_override`、`vae_override`、`clip_override` 可分别输入到 `easy fullLoader`\n- 添加 `easy saveImageLazy`\n- 添加 `easy loadImageForLoop`\n- 添加 `easy isFileExist`\n- 添加 `easy saveText`\n\n**v1.2.3**\n\n- `easy showAnything` 和 `easy cleanGPUUsed` 增加了输出槽位\n- 向 `easy humanSegmentation` 添加人体部位分割功能——代码基于 [ComfyUI_Human_Parts](https:\u002F\u002Fgithub.com\u002Fmetal3d\u002FComfyUI_Human_Parts)\n- 当使用 flux 模型并选择 basicGuider 且在 `easy preSamplingCustom` 上设置 cfg>0 时，使用 FluxGuidance\n- 添加 `easy loraStackApply` 和 `easy controlnetStackApply`——应用 loraStack 和 controlnetStack\n\n**v1.2.2**\n\n- 添加 `easy batchAny`\n- 添加 `easy anythingIndexSwitch`\n- 添加 `easy forLoopStart` 和 `easy forLoopEnd`\n- 添加 `easy ifElse`\n- 添加 v2 Web 前端代码\n- 添加 `easy fluxLoader`\n- 添加对 SD3 和 hunyuanDiT 相关节点 `controlnetApply` 的支持\n- 修复使用 `easy applyFooocusInpaint` 后所有 lora 模型都无法使用的问题\n\n**v1.2.1**\n\n- 添加 `easy ipadapterApplyFaceIDKolors`\n- 向 `easy imageRemBg` 添加 **inspyrenet**\n- 添加 `easy controlnetLoader++`\n- 在 `easy ipadapterApply` 和 `easy ipadapterApplyADV` 上添加 **PLUS (kolors genernal)** 和 **FACEID PLUS KOLORS** 预设（支持 kolors ipadapter）\n- 添加 `easy kolorsLoader`——代码基于 [MinusZoneAI](https:\u002F\u002Fgithub.com\u002FMinusZoneAI\u002FComfyUI-Kolors-MZ) 和 [kijai](https:\u002F\u002Fgithub.com\u002Fkijai\u002FComfyUI-KwaiKolorsWrapper) 的仓库，感谢他们的贡献。\n\n**v1.2.0**\n\n- 添加 `easy pulIDApply` 和 `easy pulIDApplyADV`\n- 添加 `easy huanyuanDiTLoader` 和 `easy pixArtLoader`\n- 添加 **easy sliderControl**——滑块控制节点，目前可用于控制 ipadapterMS 的参数（双击滑块可重置为默认值）\n- 在 `easy ipadapterApplyADV` 中添加 **layer_weights**\n\n**v1.1.9**\n\n- 添加 **gitsScheduler**\n- 添加 `easy imageBatchToImageList` 和 `easy imageListToImageBatch`\n- 模型递归嵌套子分类\n- 支持 Stable Diffusion 3 模型\n- 添加 `easy applyInpaint`——该节点包含所有 inpainting 模式\n\n**v1.1.8**\n\n- 添加 `easy controlnetStack`\n- 添加 `easy applyBrushNet`——[工作流示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4brushnet_1.1.8.json)\n- 添加 `easy applyPowerPaint`——[工作流示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4powerpaint_outpaint_1.1.8.json)\n\n**v1.1.7**\n\n- 添加 `easy prompt`——主题和光线预设，未来可能会调整\n- 添加 `easy icLightApply`——光影迁移，代码基于 [ComfyUI-IC-Light](https:\u002F\u002Fgithub.com\u002Fhuchenlei\u002FComfyUI-IC-Light)\n- 添加 `easy imageSplitGrid`\n- `easy kSamplerInpainting` 在**附加**组件中增加了不同扩散和 brushnet 等选项\n- 支持 brushnet 模型加载——[ComfyUI-BrushNet](https:\u002F\u002Fgithub.com\u002Fnullquant\u002FComfyUI-BrushNet)\n- 添加 `easy applyFooocusInpaint`——替代 FooocusInpaintLoader\n- 移除 `easy fooocusInpaintLoader`\n\n**v1.1.6**\n\n- 在所有 `easy preSampling` 和 `easy fullkSampler` 的 **schedulder** 组件中添加 **alignYourSteps**\n- 在 `easy kSampler` 和 `easy fullkSampler` 的 **image_output** 组件中添加 **Preview&Choose**\n- 添加 `easy styleAlignedBatchAlign`——灵感来自 [style_aligned_comfy](https:\u002F\u002Fgithub.com\u002Fbrianfitzgerald\u002Fstyle_aligned_comfy)\n- 添加 `easy ckptNames`\n- 添加 `easy controlnetNames`\n- 添加 `easy imagesSplitimage`——将批量图片拆分为单张图片\n- 添加 `easy imageCount`——获取图片数量\n- 添加 `easy textSwitch`——文本切换\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.1.5\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 重写 `easy cleanGPUUsed`——可以清除 ComfyUI 的内存占用\n- 添加 `easy humanSegmentation`——人体部位分割\n- 添加 `easy imageColorMatch`\n- 添加 `easy ipadapterApplyRegional`\n- 添加 `easy ipadapterApplyFromParams`\n- 添加 `easy imageInterrogator`——图片转提示词\n- 添加 `easy stableDiffusion3API`——简易 Stable Diffusion 3 多账户 API 节点\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.1.4\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy preSamplingCustom`——自定义预采样，可支持 cosXL-edit\n- 添加 `easy ipadapterStyleComposition`\n- 在所有加载器中添加右键菜单，用于查看检查点和 lora 信息\n- 修复 `easy preSamplingNoiseIn`、`easy latentNoisy`、`east Unsampler` 与 ComfyUI Revision>=2098 [0542088e] 或更高版本兼容\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.1.3\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 在 `easy ipadapterApply` 中添加 **COMPOSITION** 预设\n- 支持在加载 ResAdapter lora 时使用 [ResAdapter](https:\u002F\u002Fhuggingface.co\u002Fjiaxiangc\u002Fres-adapter)\n- 添加 `easy promptLine`\n- 添加 `easy promptReplace`\n- 添加 `easy promptConcat`\n- `easy wildcards` 添加 **multiline_mode**\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.1.2\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 优化了一些 EasyUse 推荐节点的相关插槽\n- 添加 **启用 ContextMenu 自动嵌套子目录** 选项，默认开启，可按子目录对检查点和 loras 进行分类预览\n- 添加 `easy sv3dLoader`\n- 添加 `easy dynamiCrafterLoader`\n- 添加 `easy ipadapterApply`\n- 添加 `easy ipadapterApplyADV`\n- 添加 `easy ipadapterApplyEncoder`\n- 添加 `easy ipadapterApplyEmbeds`\n- 添加 `easy preMaskDetailerFix`\n- 修复 `easy stylesSelector` 在未选择风格时会更改提示词的问题\n- 修复 `easy pipeEdit` 在向提示词中添加 lora 时出现的错误\n- 修复 layerDiffuse xyplot 的 bug\n- `easy kSamplerInpainting` 添加 *额外* 组件，可以选择“差异扩散”或“仅 inpaintModelConditioning”\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.1.1\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 首次修复当添加带有种子控制的节点且**控制在生成前**时，首次运行队列提示词时种子为 0 的问题。\n- 在 `easy preSamplingAdvanced` 中添加 **return_with_leftover_noise**\n- 修复 `easy stylesSelector` 在选择自定义文件时的错误\n- 在 `easy preSamplingLayerDiffusion` 中添加可选的掩码输入参数\n- 将所有节点的 widget 名称 seed_num 重命名为 seed\n- 移除强制性的 **control_before_generate** 设置。如果需要使用 control_before_generate，可在系统设置中将 widget_value_control_mode 改为 before\n- 添加 `easy imageRemBg`——默认使用 BriaAI 的 RMBG-1.4 模型，去除背景效果更快更彻底\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.1.0\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy imageSplitList`——用于将每 N 张图片分开\n- 添加 `easy preSamplingDiffusionADDTL`——可以修改前景、背景或混合的附加提示词\n- 添加 `easy preSamplingNoiseIn`——可以替代需要前置的 `easy latentNoisy` 节点，以实现更好的噪声注入\n- 在 `easy pipeEdit` 中添加条件拼接模式选择，可选择替换、拼接、组合、平均，并设置时间步长范围\n- 添加 `easy pipeEdit`——可编辑管道（包括可重新输入的提示词）的节点\n- 添加 `easy preSamplingLayerDiffusion` 和 `easy kSamplerLayerDiffusion`\n- 添加便捷菜单，右键点击 Loader、Presampler、Sampler、Controlnet 等节点，可快速替换同类型节点\n- 添加 `easy instantIDApplyADV` 可链接正反面\n- 修复批量大于 1 时 layerDiffusion 的错误\n- 修复 `easy wildcards` 在 LoRa 未完全填写时无法自动检索 LoRa 导致加载失败的问题\n- 修复未使用 a1111 提示词风格时“BREAK”不生效的问题\n- 修复 `easy instantIDApply` 掩膜输入不正确的问题\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.9\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 修复 ComfyUI-Impack-Pack 和 ComfyUI_InstantID 未安装时的错误\n- 修复 `easy pipeIn`\n- 添加 `easy instantIDApply`——需先安装 [ComfyUI_InstantID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_InstantID)，工作流[示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fblob\u002Fmain\u002FREADME.en.md#InstantID)\n- 修复 `easy detailerFix` 未被加入可保存图片格式化扩展的节点列表的问题\n- 修复 `easy XYInputs: PromptSR` 在替换负面提示词时报告错误的问题\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.8\u003C\u002Fb>\u003C\u002Fsummary>\n\n- `easy cascadeLoader` stage_c 和 stage_b 支持检查点模型（可下载 [checkpoints](https:\u002F\u002Fhuggingface.co\u002Fstabilityai\u002Fstable-cascade\u002Ftree\u002Fmain\u002Fcomfyui_checkpoints) 模型）\n- 修改 `easy stylesSelector` 的搜索框为不区分大小写\n- `easy fullLoader` 的输出项中增加了 **positive**、**negative**、**latent**\n- 修复“easy preSampling”等类似节点在传入批次索引后无法根据索引生成 latent 的问题\n- 修复 `easy svdLoader` 在正负为空时的错误\n- 修复 ComfyUI 修订版 2016[c2cb8e88] 及以上版本中 SDXLClipModel 的错误（判断修订号是否与旧版本兼容）\n- 修复 `easy detailerFix` 在批量大于 1 时的生成错误\n- 优化代码，减少大量冗余代码，提升运行速度\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.7\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy cascadeLoader`——稳定级联加载器\n- 添加 `easy preSamplingCascade`——稳定级联预采样设置\n- 添加 `easy fullCascadeKSampler`——稳定级联 stage-c ksampler 全部\n- 添加 `easy cascadeKSampler`——稳定级联 stage-c ksampler 简单版\n- \n- 优化图像转图像[示例](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fblob\u002Fmain\u002FREADME.en.md#image-to-image)\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.6\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy XYInputs: Checkpoint`\n- 添加 `easy XYInputs: Lora`\n- `easy seed` 在增加固定种子值时可手动切换随机种子\n- 修复 `easy fullLoader` 和所有加载器在切换 Lora 时自动调整节点大小的问题\n- 移除原有的 ttn 图片保存逻辑，改为适配 ComfyUI 默认的图片保存格式扩展\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.5\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy isSDXL`\n- 在 `easy svdLoader` 上添加提示词控制，可与 open_clip 模型一起使用\n- 在 `easy wildcards` 上添加 **populated_text**，可输出填充后的通配符文本\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.4\u003C\u002Fb>\u003C\u002Fsummary>\n\n- `easy showAnything` 增加了对其他类型（如张量条件、图片等）转换的支持\n- 添加 `easy showLoaderSettingsNames`，可在输出加载器组件中显示模型和 VAE 名称\n- 添加 `easy promptList`\n- 添加 `easy fooocusInpaintLoader`（仅支持 SDXLModel 的流程）\n- 添加 **Logic** 节点\n- 添加 `easy imageSave`——带有日期转换以及宽高格式化的图片保存节点\n- 添加 `easy joinImageBatch`\n- `easy kSamplerInpainting` 增加了与 FooocusInpaintLoader 节点配合使用的 **patch** 输入值\n\n- 修复 Pillow>9.5 时 xyplot 的错误\n- 修复 `easy wildcards` 在使用 PS 扩展时报错的问题\n- 修复 `easy XYInputs: ControlNet` 的错误\n- 修复 `easy loraStack` 在禁用 **toggle** 时出现的错误\n\n\n- 更改首次安装节点包时不再自动替换主题，需手动调整并刷新页面\n- `easy imageSave` 增加了 **only_preivew**\n- 调整 `easy latentCompositeMaskedWithCond` 节点\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.3\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy stylesSelector`\n- 在 `easy controlnetLoader` 和 `easy controlnetLoaderADV` 中添加 **scale_soft_weights**\n- 添加队列进度条设置项，但默认未启用\n\n\n- 修复 `easy XYInputs: Sampler\u002FScheduler` 的错误\n- 修复右键菜单点击按钮时出现问题的情况\n- 修复 `easy comfyLoader` 的错误\n- 修复连接 zero123 时 xyPlot 的错误\n- 修复加载器中提示词为组件时的错误消息\n- 修复 `easy getNode` 和 `easy setNode` 在加载时标题不变化的问题\n- 修复所有采样器使用子目录存储图片的问题\n\n\n- 调整 UI 主题，分为官方默认背景和深黑色背景两套风格，可在设置中的调色板中切换\n- 修改样式路径，使其与其他环境兼容\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.2\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy XYPlotAdvanced` 和一些关于 `easy XYInputs` 的节点\n- 添加 **Alt+1-Alt+9** 快捷键，可快速粘贴节点模板预设（对应 1~9 序列）\n- 在上下文菜单中添加一个 `📜Groups Map(EasyUse)`\n- 添加了一个 `autocomplete` 文件夹，如果已安装 [ComfyUI-Custom-Scripts](https:\u002F\u002Fgithub.com\u002Fpythongosssss\u002FComfyUI-Custom-Scripts)，该文件夹中的 txt 文件将在启动时合并并覆盖到 pyssss 包的 autocomplete .txt 文件中。\n\n\n- 修复 XYPlot 在 `a1111_prompt_style` 为 True 时无法工作的问题\n- 修复新版 ComfyUI 中 UI 加载失败的问题\n- `easy XYInputs ModelMergeBlocks` 的数值可以从 CSV 文件中导入\n- 修复 `easy pipeToBasicPipe` 的 Bug\n\n- 移除 `easy imageRemBg`\n- 从包中移除介绍性图表和工作流文件，以减小包体积\n- 替换 XY 图表生成中使用的字体文件\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.1\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 修复 `easy comfyLoader` 的错误\n- 修复所有包含图片尺寸值的节点\n- 添加 `easy kSamplerInpainting`\n- 添加 `easy pipeToBasicPipe`\n- 修复 `easy svdLoader` 中无法自定义宽度和高度的问题\n- 修复所有预览图片路径（此前在 Mac 系统上无法预览图片）\n- 修复 `vae_name` 在 `easy fullLoader`、`easy a1111Loader` 和 `easy comfyLoader` 中不起作用的问题\n- 修复 `easy fullkSampler` 输出错误的问题\n- 修复 `model_override` 在 `easy fullLoader` 中不起作用的问题\n- 修复 `easy hiresFix` 的错误\n- 修复 `easy xyplot` 字体文件路径错误的问题\n- 修复将 `seed_num` 转换为 `easy seed` 时无法固定种子的问题\n- 修复 `easy pipeIn` 输入错误的问题\n- `easy preDetailerFix` 增加了一个新的参数 `optional_image`\n- 修复 `easy zero123Loader` 和 `easy svdLoader` 模型进入缓存的问题\n- 添加 `easy seed`\n- 修复 `image_output` 默认值为“Preview”的问题\n- `easy fullLoader` 和 `easy a1111Loader` 增加了一个新的参数 `a1111_prompt_style`，可以在 ComfyUI 上重现与 Stable-Diffusion-WebUI 生成的相同图片，但需要安装 [ComfyUI_smZNodes](https:\u002F\u002Fgithub.com\u002Fshiimizu\u002FComfyUI_smZNodes) 才能在当前版本中使用此功能\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>v1.0.0\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加 `easy positive`——简单的正面提示词\n- 添加 `easy negative`——简单的负面提示词\n- 添加 `easy wildcards`——支持通配符及由 Lora 选择的提示文本\n- 添加 `easy portraitMaster`——PortraitMaster v2.2\n- 添加 `easy loraStack`——Lora 堆栈\n- 添加 `easy fullLoader`——完整版加载器\n- 添加 `easy zero123Loader`——简单版 zero123 加载器\n- 添加 `easy svdLoader`——简易 svd 加载器\n- 添加 `easy fullkSampler`——完整版采样器（不分割）\n- 添加 `easy hiresFix`——支持高清修复 Pipe\n- 添加 `easy predetailerFix` 和 `easy DetailerFix`——支持 Pipe 细节修复\n- 添加 `easy ultralyticsDetectorPipe` 和 `easy samLoaderPipe`——检测加载器（细节修复输入）\n- 添加 `easy pipein` 和 `easy pipeout`——Pipe 输入和输出\n- 添加 `easy xyPlot`——简易 xyplot（未来将更新更多可控参数）\n- 添加 `easy imageRemoveBG`——去除背景的图片\n- 添加 `easy imagePixelPerfect`——像素完美的图片\n- 添加 `easy poseEditor`——姿势编辑器\n- 新 UI 主题（Obsidian）——默认自动加载 UI，也可在设置中更改\n\n- 修复 `easy globalSeed` 不起作用的问题\n- 修复因 [cg-use-everywhere](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-use-everywhere) 实时更新图表而导致所有 `seed_num` 值混乱的问题\n- 修复 `easy imageSize`、`easy imageSizeBySide`、`easy imageSizeByLongerSide` 作为末端节点的问题\n- 修复历史上 `seed_num`（随机种子值）无法一致读取的bug\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>更新于 2023年12月14日\u003C\u002Fb>\u003C\u002Fsummary>\n\n- `easy a1111Loader` 和 `easy comfyLoader` 增加了必需输入参数的 `batch_size`\n- 添加了 `easy controlnetLoaderADV` 节点\n- `easy controlnetLoaderADV` 和 `easy controlnetLoader` 增加了可选的 `control_net` 输入参数\n- `easy preSampling` 和 `easy preSamplingAdvanced` 增加了可选的 `image_to_latent` 输入参数\n- 添加了 `easy imageSizeBySide` 节点，可按长边或短边输出\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>更新于 2023年12月13日\u003C\u002Fb>\u003C\u002Fsummary>\n\n- 添加了 `easy LLLiteLoader` 节点，若已预先安装 kohya-ss\u002FControlNet-LLLite-ComfyUI 包，请将模型文件移至 `ComfyUI\\models\\controlnet\\`（即 ComfyUI 默认的 controlnet 路径，请勿更改模型文件名，否则将无法读取）。\n- 将 `easy controlnetLoader` 调整到加载器类别的底部。\n- 为 `easy imageSize` 和 `easy imageSizeByLongerSize` 的输出添加尺寸显示。\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>更新于 2023年12月11日\u003C\u002Fb>\u003C\u002Fsummary>\n- 添加了 `showSpentTime` 节点，用于显示图像扩散所花费的时间以及 VAE 解码图像所花费的时间。\n\u003C\u002Fdetails>\n\n## 涉及的相关节点包\n\n免责声明：开源工作并不容易。我对这些原作者的贡献深表敬意。我只是做了一些集成和优化。\n\n| 节点名称（搜索名称）        | 相关库                                                                        | 库相关节点     |\n|:-------------------------------|:----------------------------------------------------------------------------|:-------------------------|\n| easy setNode                   | [ComfyUI-extensions](https:\u002F\u002Fgithub.com\u002Fdiffus3\u002FComfyUI-extensions) | diffus3.SetNode          |\n| easy getNode                   | [ComfyUI-extensions](https:\u002F\u002Fgithub.com\u002Fdiffus3\u002FComfyUI-extensions) | diffus3.GetNode          |\n| easy bookmark                  | [rgthree-comfy](https:\u002F\u002Fgithub.com\u002Frgthree\u002Frgthree-comfy) | Bookmark 🔖              |\n| easy portraitMarker            | [comfyui-portrait-master](https:\u002F\u002Fgithub.com\u002Fflorestefano1975\u002Fcomfyui-portrait-master) | Portrait Master          |\n| easy LLLiteLoader              | [ControlNet-LLLite-ComfyUI](https:\u002F\u002Fgithub.com\u002Fkohya-ss\u002FControlNet-LLLite-ComfyUI) | LLLiteLoader             |\n| easy globalSeed                | [ComfyUI-Inspire-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Inspire-Pack) | Global Seed (Inspire)    | \n| easy preSamplingDynamicCFG     | [sd-dynamic-thresholding](https:\u002F\u002Fgithub.com\u002Fmcmonkeyprojects\u002Fsd-dynamic-thresholding) | DynamicThresholdingFull  | \n| dynamicThresholdingFull        | [sd-dynamic-thresholding](https:\u002F\u002Fgithub.com\u002Fmcmonkeyprojects\u002Fsd-dynamic-thresholding) | DynamicThresholdingFull  | \n| easy imageInsetCrop            | [rgthree-comfy](https:\u002F\u002Fgithub.com\u002Frgthree\u002Frgthree-comfy) | ImageInsetCrop           | \n| easy poseEditor                | [ComfyUI_Custom_Nodes_AlekPet](https:\u002F\u002Fgithub.com\u002FAlekPet\u002FComfyUI_Custom_Nodes_AlekPet) | poseNode                 | \n| easy preSamplingLayerDiffusion | [ComfyUI-layerdiffusion](https:\u002F\u002Fgithub.com\u002Fhuchenlei\u002FComfyUI-layerdiffusion) | LayeredDiffusionApply... | \n| easy dynamiCrafterLoader       | [ComfyUI-layerdiffusion](https:\u002F\u002Fgithub.com\u002FExponentialML\u002FComfyUI_Native_DynamiCrafter) | Apply Dynamicrafter    | \n| easy imageChooser              | [cg-image-picker](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-image-picker) | Preview Chooser         | \n| easy styleAlignedBatchAlign              | [style_aligned_comfy](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-image-picker) | styleAlignedBatchAlign       | \n| easy kolorsLoader              | [ComfyUI-Kolors-MZ](https:\u002F\u002Fgithub.com\u002FMinusZoneAI\u002FComfyUI-Kolors-MZ) | kolorsLoader            |\n\n\n## 致谢\n\n[ComfyUI](https:\u002F\u002Fgithub.com\u002Fcomfyanonymous\u002FComfyUI) - 功能强大且模块化的Stable Diffusion图形界面\n\n[ComfyUI-ComfyUI-Manager](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Manager) - ComfyUI管理器\n\n[tinyterraNodes](https:\u002F\u002Fgithub.com\u002FTinyTerra\u002FComfyUI_tinyterraNodes) - 管道节点（节点集合）使用户能够减少不必要的连接\n\n[ComfyUI-extensions](https:\u002F\u002Fgithub.com\u002Fdiffus3\u002FComfyUI-extensions) - Diffus3提供获取和设置点，允许用户解耦工作流的组成\n\n[ComfyUI-Impact-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Impact-Pack) - 通用模组包1\n\n[ComfyUI-Inspire-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Inspire-Pack) - 通用模组包2\n\n[ComfyUI-ResAdapter](https:\u002F\u002Fgithub.com\u002Fjiaxiangc\u002FComfyUI-ResAdapter) - 使模型生成独立于训练分辨率\n\n[ComfyUI_IPAdapter_plus](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_IPAdapter_plus) - 风格迁移\n\n[ComfyUI_InstantID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_InstantID) - 人脸迁移\n\n[ComfyUI_PuLID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FPuLID_ComfyUI) - 人脸迁移\n\n[ComfyUI-Custom-Scripts](https:\u002F\u002Fgithub.com\u002Fpythongosssss\u002FComfyUI-Custom-Scripts) - pyssss🐍\n\n[cg-image-picker](https:\u002F\u002Fgithub.com\u002Fchrisgoringe\u002Fcg-image-picker) - 图片预览选择器\n\n[ComfyUI_ExtraModels](https:\u002F\u002Fgithub.com\u002Fcity96\u002FComfyUI_ExtraModels) - DiT自定义节点\n\n## 免责声明\n\n本软件按“原样”提供，不提供任何形式的明示或暗示担保，包括但不限于适销性、特定用途适用性和非侵权性担保。在任何情况下，作者或版权所有者均不对因本软件或其使用或其他相关行为而引起的任何索赔、损害赔偿或其他责任承担任何责任，无论该等责任是基于合同、侵权行为或其他原因产生的。\n\n用户应自行负责确保其对本软件的使用符合其使用地或发布由该软件生成内容所在司法管辖区的所有适用法律和法规。作者和版权所有者对用户在其各自所在地违反法律或法规的行为不承担任何责任。\n\n## ☕️ 捐赠\n\n**Comfyui-Easy-Use** 是一个采用GPL许可的开源项目。为了实现项目的更好和可持续发展，我希望获得更多支持者的帮助。\u003Cbr>\n如果我的自定义节点为您的日常使用带来了价值，请考虑请我喝杯咖啡，以支持项目的进一步发展！\u003Cbr>\n💖您可以通过以下方式支持我：\n\n- [BiliBili](https:\u002F\u002Fspace.bilibili.com\u002F1840885116)\n- [微信 \u002F 支付宝](https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F803469bd-ed6a-4fab-932d-50e5088a2d03)\n\n##  🌟 星标用户\n\n我要感谢那些慷慨地为本项目点亮星标的朋友们。非常感谢您的支持！\n\n[![@yolain\u002FComfyUI-Easy-Use 的星标用户列表](https:\u002F\u002Freporoster.com\u002Fstars\u002Fyolain\u002FComfyUI-Easy-Use)](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fstargazers)","# ComfyUI-Easy-Use 快速上手指南\n\nComfyUI-Easy-Use 是一个基于 TinyTerraNodes 扩展的高效自定义节点集成包。它优化并整合了众多流行的自定义节点，旨在提供更流畅、便捷的 ComfyUI 使用体验，同时保留高度的自由度，还原 Stable Diffusion 极致的绘图体验。\n\n## 环境准备\n\n在开始之前，请确保您的系统满足以下要求：\n\n*   **操作系统**: Windows, Linux 或 macOS\n*   **核心依赖**: 已安装并配置好 [ComfyUI](https:\u002F\u002Fgithub.com\u002Fcomfyanonymous\u002FComfyUI) 基础环境。\n*   **Python 环境**: 建议使用 Python 3.10 或更高版本（与 ComfyUI 官方推荐一致）。\n*   **Git**: 用于克隆仓库。\n*   **可选依赖**:\n    *   若需使用 Lora Block Weight 功能，请预先安装 [ComfyUI-Inspire-Pack](https:\u002F\u002Fgithub.com\u002Fltdrdata\u002FComfyUI-Inspire-Pack)。\n    *   若需使用 InstantID 功能，请预先安装 [ComfyUI_InstantID](https:\u002F\u002Fgithub.com\u002Fcubiq\u002FComfyUI_InstantID)。\n    *   首次使用 Layer Diffuse 相关功能时，可能需要手动安装 `requirements.txt` 中的依赖。\n\n## 安装步骤\n\n请将此插件安装到 ComfyUI 的 `custom_nodes` 目录中。\n\n### 方法一：手动克隆（推荐）\n\n1.  进入 ComfyUI 根目录下的 `custom_nodes` 文件夹。\n2.  执行以下命令克隆仓库：\n    ```shell\n    git clone https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\n    ```\n    > **国内加速提示**：如果访问 GitHub 速度较慢，可使用国内镜像源（如 Gitee 镜像，若有）或配置 Git 代理。若无特定镜像，请确保网络通畅。\n\n3.  进入插件目录并安装依赖：\n    *   **Windows 用户**：直接双击运行目录下的 `install.bat` 文件。\n    *   **Linux\u002FMac 用户**：在终端执行以下命令：\n        ```shell\n        cd ComfyUI-Easy-Use\n        pip install -r requirements.txt\n        ```\n\n4.  **重启 ComfyUI** 以加载新节点。\n\n### 方法二：通过 ComfyUI Manager 安装\n\n如果您已安装 **ComfyUI Manager**：\n1.  点击 Manager 按钮。\n2.  选择 \"Install Custom Nodes\"。\n3.  搜索 `ComfyUI-Easy-Use` 或 `yolain`。\n4.  点击安装并重启 ComfyUI。\n\n## 基本使用\n\n安装完成后，启动 ComfyUI，您将在节点菜单中看到大量以 `easy` 开头的节点。以下是构建一个最基础工作流的简要步骤：\n\n### 1. 界面美化与主题切换\n首次安装后，为了获得最佳视觉体验：\n*   进入 `Settings` (设置) -> `Color Palette` (配色方案)。\n*   选择一个喜欢的主题并刷新页面。\n\n### 2. 构建简易生成流程\nComfyUI-Easy-Use 提供了简化的加载器和采样器，大幅减少连线复杂度。\n\n*   **加载模型与提示词**：\n    *   添加节点：`easy fullLoader`。\n    *   功能：一站式加载 Checkpoint、VAE、CLIP 等，并支持 A1111 风格的提示词输入模式。\n    *   连接：将模型输出连接到后续采样节点。\n\n*   **预设参数配置**：\n    *   添加节点：`easy preSamplingAdvanced` 或 `easy preSamplingCustom`。\n    *   功能：独立配置采样参数（步数、CFG、种子等），支持预览和噪声注入 (`easy latentNoisy`)。\n\n*   **风格与提示词增强**：\n    *   添加节点：`easy stylesSelector`。\n    *   功能：多选风格提示词（默认支持 Fooocus 风格 JSON），可自定义放入 `styles` 文件夹。\n    *   添加节点：`easy prompt`。\n    *   功能：提供主体和光影预设，快速构建高质量提示词。\n\n*   **采样与输出**：\n    *   添加节点：`easy kSampler`。\n    *   功能：集成预览与选择功能 (`Preview&Choose`)，简化图像输出流程。\n    *   连接：将 `fullLoader` 的模型、`preSampling` 的参数、`stylesSelector` 的正负提示词连接至此。\n\n### 3. 高级功能速览\n*   **循环与逻辑**：使用 `easy forLoopStart` \u002F `easy forLoopEnd` 和 `easy ifElse` 实现复杂的批量处理逻辑。\n*   **图像处理**：使用 `easy imageRemBg` (支持 RMBG-1.4\u002FBriaAI) 一键移除背景，或使用 `easy humanSegmentation` 进行人体部位分割。\n*   **模型支持**：原生支持 SD1.x, SDXL, SD3, Flux, Kolors (可图), Stable Cascade 等模型的简化加载节点（如 `easy fluxLoader`, `easy kolorsLoader`）。\n\n通过以上步骤，您可以快速利用 ComfyUI-Easy-Use 搭建高效的工作流，无需再为繁琐的连线而困扰。更多详细工作流示例请参考官方 [Workflow Collection](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows)。","一位电商设计师需要在 ComfyUI 中快速批量生成多套不同风格的商品海报，并反复调整提示词与模型参数以寻找最佳效果。\n\n### 没有 ComfyUI-Easy-Use 时\n- **节点连接繁琐**：构建基础工作流需手动连接数十个原生节点，每次切换 SDXL 或 Flux 模型都要重新搭建链路，耗时且易出错。\n- **参数调试低效**：修改采样器或步数等参数必须深入采样节点内部，无法在不改变生成逻辑的情况下快速预览不同配置的效果。\n- **风格尝试单一**：缺乏内置的风格提示词选择器，想测试\"Fooocus\"等多种风格需手动复制粘贴复杂的 JSON 提示词，难以进行多方案对比。\n- **兼容性问题多**：集成 InstantID 换脸或 RMBG 抠图功能时，需额外安装多个独立插件包并处理依赖冲突，环境配置极其痛苦。\n\n### 使用 ComfyUI-Easy-Use 后\n- **一键加载模型**：利用简化的 Loader 节点，仅需一个节点即可兼容 SD1.5、SDXL 及 Flux 等多种架构，瞬间完成模型切换与基础链路搭建。\n- **前置参数配置**：通过独立的预采样配置节点，将参数设置与生成过程分离，设计师可随意调整步数或 CFG 值并实时预览，无需改动核心流程。\n- **多选风格测试**：内置多可选风格提示词选择器，直接调用预设的 Fooocus 风格库或自定义 JSON，轻松实现“一次点击，多种风格”的批量对比。\n- **功能高度集成**：原生集成了 InstantID、背景移除及逻辑控制节点，无需额外折腾依赖包，复杂功能如换脸抠图可直接拖拽使用，稳定流畅。\n\nComfyUI-Easy-Use 通过将碎片化的复杂操作封装为直观的标准化节点，让创作者从繁琐的技术连线中解放，真正专注于创意内容的生产。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fyolain_ComfyUI-Easy-Use_0ec8423f.jpg","yolain","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fyolain_7aed5225.png","Thank you for visiting.",null,"https:\u002F\u002Fgithub.com\u002Fyolain",[78,82,86,90,94],{"name":79,"color":80,"percentage":81},"Python","#3572A5",82.2,{"name":83,"color":84,"percentage":85},"JavaScript","#f1e05a",16.5,{"name":87,"color":88,"percentage":89},"CSS","#663399",1.3,{"name":91,"color":92,"percentage":93},"Shell","#89e051",0,{"name":95,"color":96,"percentage":93},"Batchfile","#C1F12E",2456,189,"2026-04-12T00:19:12","GPL-3.0","Windows, Linux, macOS","未说明（作为 ComfyUI 插件，依赖宿主环境；支持 SDXL\u002FFlux\u002FSD3 等模型通常建议 NVIDIA GPU 8GB+ 显存）","未说明（建议 16GB+ 以运行大型模型如 Flux 或 SDXL）",{"notes":105,"python":106,"dependencies":107},"1. 本工具是 ComfyUI 的自定义节点集成包，必须安装在 ComfyUI 的 custom_nodes 目录下。2. 部分功能（如 Layer Diffuse）首次使用时需运行 `pip install -r requirements.txt` 安装额外依赖。3. 支持多种模型架构（SD1.x, SD2.x, SDXL, SVD, Zero123, Stable Cascade, InstantID, SD3, Kolors, Flux），具体硬件需求取决于所选用的模型。4. Windows 用户可双击 `install.bat` 安装依赖。5. 使用 Fooocus 风格提示词或特定功能时需确保对应的外部自定义节点包已安装。","未说明（需与 ComfyUI 环境一致，通常为 3.10+）",[28,108,109,110,111],"ComfyUI-Inspire-Pack (可选，用于 Lora Block Weight)","ComfyUI_InstantID (可选，用于 InstantID)","ComfyUI-BrushNet (可选，用于 BrushNet)","BriaAI RMBG-1.4\u002F2.0 (可选，用于背景移除)",[15,43],"2026-03-27T02:49:30.150509","2026-04-12T16:43:05.529742",[116,121,126,131,136,141,146,151],{"id":117,"question_zh":118,"answer_zh":119,"source_url":120},30843,"更新后模型缩略图（LoRA 预览）不再显示怎么办？","这通常是由于浏览器缓存或加载速度问题导致的。解决方案包括：1. 尝试开启缓存功能（如果有相关设置）；2. 在列表中快速滚动时图片可能来不及加载，稍作等待即可显示；3. 检查文件路径是否正确，确保预览图文件存在于对应的模型文件夹中。维护者表示开启缓存后通常能解决问题。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F409",{"id":122,"question_zh":123,"answer_zh":124,"source_url":125},30844,"更新特定版本后所有节点失效，界面变成黑红色如何解决？","这是由于某个依赖包判断逻辑不严谨导致的兼容性问题。维护者已调整代码修复了该问题。如果遇到此情况，请确保更新到最新的 ComfyUI-Easy-Use 插件版本，或者暂时回退到 3 月 3 日及之前的稳定版本，直到官方发布修复补丁。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F76",{"id":127,"question_zh":128,"answer_zh":129,"source_url":130},30845,"使用 layer_diffusion 时报错 'InpaintWorker.calculate_weight_patched() takes 4 positional arguments but 5 were given' 怎么办？","该错误是因为加载 Inpaint 模型时直接覆盖了原模型，而 ComfyUI 缓存了模型且变更了计算权重的方法。解决方法是不要直接将 Inpaint 模型覆盖到原本 model 上，或者尝试不使用 LoRA 进行测试（虽然不加 LoRA 也可能晚些出现该问题，但有助于排查）。建议等待插件更新以修复此权重计算冲突。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F74",{"id":132,"question_zh":133,"answer_zh":134,"source_url":135},30846,"使用循环节点批量处理图像时出现 OOM（内存溢出）有解决办法吗？","目前这是一个已知难题，即使在新版中有所改进，内存占用仍会随着处理数量增加而逐渐累积，最终导致耗尽。对于大规模批量处理（如放大数百张图片），目前没有完美的实时清理内存方案。建议减少单次循环处理的图片数量，分批次执行，或增加物理内存配置。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F651",{"id":137,"question_zh":138,"answer_zh":139,"source_url":140},30847,"提示词中包含英文冒号（:）导致采样报错或无法正常工作如何解决？","当提示词格式如 [dog:cow:4] 中使用英文字符冒号且开启 A1111 兼容模式时会报错。解决方法是将提示词中的英文冒号切换为中文字符下的冒号输入，或者关闭 A1111 兼容模式。此外，ComfyUI 原生的 'clip 文本' 节点目前已支持提示词分步和交替功能，可替代部分兼容性需求。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F198",{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},30848,"cleanGpuUsed 节点无法释放 GPU 资源怎么办？","cleanGpuUsed 节点旨在释放显存，但如果使用后无反应，可能是因为 ComfyUI 本身有预留的内存管理方法。维护者指出该功能早已集成在 easyuse 插件中，且新版 ComfyUI Manager 也具备此功能。请确保插件和 Manager 均为最新版本，并检查是否正确连接了该节点到工作流末端。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F124",{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},30849,"如何正确查看或调试 XL 模型的 Conditioning（条件生成）数据？","如果需要查看 XL 模型的条件生成数据，推荐使用 rgthree 的 ComfyUI Nodes 插件中的 'Display Any' 节点。该节点可以直观地显示任何类型的数据结构，帮助确认 Conditioning 是否正确。可以在 ComfyUI Manager 中搜索 ID 153 或名称 'rgthree-comfy' 进行安装。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F46",{"id":152,"question_zh":153,"answer_zh":154,"source_url":155},30850,"手动添加的 easyLoader 节点缺少正负提示词输入点怎么办？","如果在 C 站下载的压缩包工作流中正常，但手动右键添加的 easyLoader 缺少正负提示词（positive\u002Fnegative）输入点，可能是节点定义加载不完整或版本差异导致。建议检查插件是否为最新版，或者尝试重启 ComfyUI 刷新节点列表。如果问题依旧，可直接使用工作流文件中保存的节点配置来覆盖手动添加的节点。","https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fissues\u002F231",[157,162,167,172,177,182,187,192,197,202,207,212,217,222,227,232,237,242,247,252],{"id":158,"version":159,"summary_zh":160,"released_at":161},222641,"v1.3.6","## 变更内容\n- 恢复了 `easy showAnything` 对列表类型的支持（但在某些情况下显示大量数据仍可能导致 ComfyUI 崩溃）\n- 修复自定义组件，使其支持子图和 Nodes 2.0 #942\n- 添加 `easy multiAngle` 节点\n- 将 `prompt.py` 转换为 V3 Schema\n- 修复 `easy humanSegmentation` 错误\n- 添加 `easy stringJoinLines`、`easy stringToIntList`、`easy simpleMath`\n- 修复 `easy ifElse` 和 `easy anythingIndexSwitch` 在特定环境中无法正常工作的问题\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.3.5...v1.3.6","2026-01-23T06:21:32",{"id":163,"version":164,"summary_zh":165,"released_at":166},222642,"v1.3.5","## 变更内容\n- 修复 `isNone`\n- 在 `easy imageChooser` 中添加 `preview_rescale`\n- 修复小部件隐藏问题 #910\n* 修复：在 `wildcardsPromptMatrix` 中添加 `max` 参数，由 @facok 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F909 中完成\n- 修复子图节点上的标题框样式\n- 在 `easy promptLine` 中添加 `remove_empty_lines`\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.3.4...v1.3.5","2025-12-19T04:16:19",{"id":168,"version":169,"summary_zh":170,"released_at":171},222643,"v1.3.4","## 变更内容\n- 修复 `easy seedList` 的 `max_num` 问题 #879\n- 由 @Mr-Quin 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F877 中为 xyplot 添加 ControlNet 输入\n- 为 `easy indexAnything` 支持“负索引”\n\n## 新贡献者\n* @Mr-Quin 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F877 中完成了首次贡献\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.3.3...v1.3.4","2025-10-15T13:41:50",{"id":173,"version":174,"summary_zh":175,"released_at":176},222644,"v1.3.3","- 移除了 CSS 类名 `gird-cols-1` 的定义 #859\n- 修复 `easy promptAwait` 中锁种子功能失效的问题\n- 重命名节点映射\n- 修复 `easy imageChooser` 输出类型错误 #845\n\n**完整更新日志**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.3.2...v1.3.3","2025-08-29T07:28:30",{"id":178,"version":179,"summary_zh":180,"released_at":181},222645,"v1.3.2","## 变更内容\n\n- 重构 `easy imageChooser` 节点，以适配前端版本≥v1.24.2，解决方案参考自 [Comfyui_LG_Tools](https:\u002F\u002Fgithub.com\u002FLAOGOU-666\u002FComfyui_LG_Tools)。\n- 重构 `easy stylesSelector` 节点，您可以将[其他风格文件](https:\u002F\u002Fgithub.com\u002Fyolain\u002FEasyUse-Styles-Templates)下载到 `styles` 文件夹中。\n- 重构 `easy humanSegmentation` 节点。\n- 修复 `easy makeImageForICLora` 节点的问题：当进行图像拼接时，若两张图像的高度相同，会出现该问题。\n- 新增 `easy joycaption3API` 节点。\n- 由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F8 中新增 `easy promptAwait` 节点。\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.3.1...v1.3.2","2025-08-08T11:03:56",{"id":183,"version":184,"summary_zh":185,"released_at":186},222646,"v1.3.1","## 变更内容\n* 使用之前生成的模型\u002F剪辑作为下次加载 LoRA 的基础，由 @mekinney 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F766 中实现\n* 更新 XY 图表标签，由 @mekinney 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F792 中实现\n* 本地化文本中的拼写错误，由 @harukaxxxx 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F797 中修复\n* 更新 logic.py：正确处理覆盖模式，由 @teward 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F807 中实现\n* 更新 util.py，由 @WathomeBo 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F809 中完成\n* 在 ImageChooser 中存储元数据，由 @Laegel 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F813 中实现\n\n## 新贡献者\n* @mekinney 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F766 中完成了首次贡献\n* @harukaxxxx 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F797 中完成了首次贡献\n* @teward 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F807 中完成了首次贡献\n* @WathomeBo 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F809 中完成了首次贡献\n* @Laegel 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F813 中完成了首次贡献\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.3.0...v1.3.1","2025-06-29T03:44:56",{"id":188,"version":189,"summary_zh":190,"released_at":191},222647,"v1.3.0","## 变更内容\n* 由 @Hapseleg 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F746 中修复了缺失的变量问题。\n* 添加 `wildcardsPromptMatrix` 节点：由 @Rosmeowtis 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F743 中完成。\n* 合并 `wildcardsPromptMatrix` 节点：由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F751 中完成。\n* 为 `easy wildcardsMatrix` 添加 `output_limit` 参数：由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F752 中完成。\n\n## 新贡献者\n* @Hapseleg 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F746 中完成了首次贡献。\n* @Rosmeowtis 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F743 中完成了首次贡献。\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.9...v1.3.0","2025-05-09T16:25:07",{"id":193,"version":194,"summary_zh":195,"released_at":196},222648,"v1.2.9","## 变更内容\n- 修复 ImageChooser 导致工作流处理被取消的问题\n- 修复 brushnet tensor(640) 错误\n- 修复 v1.6.0 前端更新后控件未隐藏的问题\n- 修复图像选择器无法选择图像的问题\n- 修复 contextMenu 的猴子补丁影响自定义脚本 (pysssss) 节点的问题\n* 由 @robinjhuang 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F693 中更新了用于发布到 Comfy Registry 的 GitHub Action\n* 由 @Naix2012 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F697 中更新了 prompt.py\n\n## 新贡献者\n* @robinjhuang 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F693 中完成了首次贡献\n* @Naix2012 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F697 中完成了首次贡献\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.8...v1.2.9","2025-04-15T06:22:37",{"id":198,"version":199,"summary_zh":200,"released_at":201},222649,"v1.2.8","## 变更内容\n* 添加语言环境目录\n* 由 @newideas99 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F657 中修复 CLIP 视觉模型的 URL，并改进下载错误处理\n* 修复：通配符，改进文本编码处理以防止中文字符乱码……由 @facok 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F685 中完成\n\n## 新贡献者\n* @newideas99 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F657 中完成了首次贡献\n* @facok 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F685 中完成了首次贡献\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.7...v1.2.8","2025-03-10T03:12:11",{"id":203,"version":204,"summary_zh":205,"released_at":206},222650,"v1.2.7","## 变更内容\n* HumanParsing 添加了 'CUDAExecutionProvider'，由 @t00350320 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F611 中完成\n* 新增模型缩略图的显示方式，由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F622 中完成\n* 文件结构的调整，由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F632 中完成\n* 修复因 IDE 自动修补部分路径而导致的问题 #635，由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F636 中完成\n* 修复人体分割错误，由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F639 中完成\n* 修正：requirements.txt 文件，由 @anton-averich 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F638 中完成\n* 更新节点映射表，由 @yolain 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F648 中完成\n\n## 新贡献者\n* @anton-averich 在 https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F638 中完成了首次贡献\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv.1.2.6...v1.2.7","2025-02-10T09:58:48",{"id":208,"version":209,"summary_zh":210,"released_at":211},222651,"v.1.2.6","## What's Changed\r\n- Fix missing the \"Red Rect\" styles when you are missing custom nodes.\r\n- Adjust the default value of `clip_skip` from `-1` to `-2` in some easy loaders.\r\n- Fix the issue due to set nodes missing custom nodes which their connected, causing canvas to be messed up.\r\n- Fix the `easy imageChooser` can not using in a loop.\r\n* Fix SyntaxWarning in python 3.12 by @BobDu in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F590\r\n\r\n## New Contributors\r\n* @BobDu made their first contribution in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F590\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.5...v.1.2.6","2025-01-10T04:53:39",{"id":213,"version":214,"summary_zh":215,"released_at":216},222652,"v1.2.5","\r\n\r\n## What's Changed\r\n\r\n- Added `enable (GPU=A1111)` noise mode on `easy preSamplingCustom` and `easy preSamplingAdvanced` \r\n- Added `easy makeImageForICLora`\r\n- Added `FLUX.1-dev` preset for InstantX Flux ipadapter on `easy ipadapterApply`\r\n- Fix brushnet can not be used with startup arg `--fast` mode\r\n- Support briaai RMBG-2.0\r\n- Support mochi \r\n- Implement reuse of end nodes output in the loop body (e.g: previewImage and showAnything and sth.) \r\n\r\n### pull requests\r\n* Loops do repeat execution for leaf nodes by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F515\r\n* Support mochi by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F519\r\n* Support New flux model by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F543\r\n* Add noise generate mode (GPU=A1111) on easy preSamlingCustom by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F561\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.4...v1.2.5","2024-12-09T07:54:25",{"id":218,"version":219,"summary_zh":220,"released_at":221},222653,"v1.2.4","- Added `easy imageSplitTiles` and `easy imageTilesFromBatch`\r\n- Support `model_override`,`vae_override`,`clip_override` can be input separately to `easy fullLoader`\r\n- Added `easy saveImageLazy`\r\n- Added `easy loadImageForLoop`\r\n- Added `easy isFileExist`\r\n- Added `easy saveText`\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.3...v1.2.4","2024-11-06T10:22:21",{"id":223,"version":224,"summary_zh":225,"released_at":226},222654,"v1.2.3","## What's Changed\r\n- `easy showAnything` and `easy cleanGPUUsed` added slot of output\r\n- Added human parts segmentation to `easy humanSegmentation` - Code based on (ComfyUI_Human_Parts)[https:\u002F\u002Fgithub.com\u002Fmetal3d\u002FComfyUI_Human_Parts]\r\n- Using FluxGuidance when you are using a flux model and choose basicGuider and set the cfg>0 on `easy preSamplingCustom`\r\n- Added `easy loraStackApply` and `easy controlnetStackApply` - Apply loraStack and controlnetStack\r\n- Support Execution blocker by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F385\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.2...v1.2.3","2024-10-06T02:46:07",{"id":228,"version":229,"summary_zh":230,"released_at":231},222655,"v1.2.2","## What's Changed\r\n* Fix filtering embedding carries chinese #299 by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F302\r\n* Add easy fluxLoader to support the nf4 flux checkpoint by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F303\r\n* Update Readme by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F307\r\n* Update the web v2 version to work more seamlessly with Comfy's new front-end by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F310\r\n* Fix get comfyui revision more add int type conversion by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F313\r\n* Update v2 frontend to 0.0.4 by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F318\r\n* Fix unable display model thumbnail image on node of pyssss's settings.  by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F320\r\n* Set setting auto nest subdirectories to false by default by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F324\r\n* Fix fluxLoader ckpt can not load all-in-one ckpt beyond nf4 by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F326\r\n* Fix preSamplingCustom seed not working by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F328\r\n* Support Execution inversion by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F329\r\n* Fix whileloop nodes bug and add outputToList node by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F346\r\n* Fix can not get total when convert it to input on loops nodes by @yolain in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F352\r\n\r\n## New Contributors\r\n* @yolain made their first contribution in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F302\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.1...v1.2.2","2024-09-04T04:12:59",{"id":233,"version":234,"summary_zh":235,"released_at":236},222656,"v1.2.1","[cn]\r\n- 增加 `easy ipadapterApplyFaceIDKolors`\r\n- `easy ipadapterApply` 和 `easy ipadapterApplyADV` 增加 **PLUS (kolors genernal)** 和 **FACEID PLUS KOLORS** 预置项\r\n- `easy imageRemBg` 增加 **inspyrenet** 选项\r\n- 增加 `easy controlnetLoader++`\r\n- 去除 `easy positive` `easy negative` 等prompt节点的自动将中文翻译功能，自动翻译仅在 `easy a1111Loader` 等不支持中文TE的加载器中生效\r\n- 增加 `easy kolorsLoader` - 可灵加载器，参考了 [MinusZoneAI](https:\u002F\u002Fgithub.com\u002FMinusZoneAI\u002FComfyUI-Kolors-MZ) 和 [kijai](https:\u002F\u002Fgithub.com\u002Fkijai\u002FComfyUI-KwaiKolorsWrapper) 的代码。\r\n\r\n[en]\r\n- Added `easy ipadapterApplyFaceIDKolors`\r\n- Added **inspyrenet** to `easy imageRemBg` \r\n- Added `easy controlnetLoader++`\r\n- Added **PLUS (kolors genernal)** and **FACEID PLUS KOLORS** preset to `easy ipadapterApply` and `easy ipadapterApplyADV` (Supported kolors ipadapter）\r\n- Added `easy kolorsLoader` - Code based on [MinusZoneAI](https:\u002F\u002Fgithub.com\u002FMinusZoneAI\u002FComfyUI-Kolors-MZ)'s and [kijai](https:\u002F\u002Fgithub.com\u002Fkijai\u002FComfyUI-KwaiKolorsWrapper)'s repo, thanks for their contribution.\r\n\r\n\r\n## What's Changed\r\n* Add OpenCV to avoid error No module named 'cv2' by @alexisrolland in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F252\r\n* Fix extra input spec dict on ipadapterApplyFromParams by @huchenlei in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F258\r\n* Fix `XYplot_Negative_Cond` input types by @christian-byrne in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F270\r\n* fix sd2_clip moved in ComfyUi, #272 by @AlUlkesh in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F273\r\n* Update PyProject Toml - License by @haohaocreates in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F279\r\n\r\n## New Contributors\r\n* @alexisrolland made their first contribution in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F252\r\n* @huchenlei made their first contribution in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F258\r\n* @christian-byrne made their first contribution in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F270\r\n* @AlUlkesh made their first contribution in https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fpull\u002F273\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.2.0...v1.2.1","2024-08-04T02:07:51",{"id":238,"version":239,"summary_zh":240,"released_at":241},222657,"v1.2.0","[cn]\r\n\r\n- 增加 faceid portrait unnorm\r\n- 增加 `easy pulIDApply` 和 `easy pulIDApplyADV`\r\n- 增加 `easy huanyuanDiTLoader` 和 `easy pixArtLoader`\r\n- 当新菜单的位置在上或者下时增加上 crystools 的显示，推荐开两个就好（如果后续crystools有更新UI适配我可能会删除掉）\r\n- 增加 **easy sliderControl** - 滑块控制节点，当前可用于控制ipadapterMS的参数 (双击滑块可重置为默认值)\r\n- 增加 **layer_weights** 属性在 `easy ipadapterApplyADV` 节点\r\n\r\n[en]\r\n\r\n- Added `easy pulIDApply` and `easy pulIDApplyADV`\r\n- Added `easy huanyuanDiTLoader` and `easy pixArtLoader`\r\n- Added **easy sliderControl** - Slider control node, which can currently be used to control the parameters of ipadapterMS (double-click the slider to reset to default)\r\n- Added **layer_weights** in `easy ipadapterApplyADV`\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.1.9...v1.2.0","2024-07-08T09:35:38",{"id":243,"version":244,"summary_zh":245,"released_at":246},222658,"v1.1.9","[cn]\r\n- 增加 新的调度器 **gitsScheduler**\r\n- 增加 `easy imageBatchToImageList` 和 `easy imageListToImageBatch`\r\n- 递归模型子目录嵌套\r\n- 支持 sd3 模型 \r\n- 增加 `easy applyInpaint` - 局部重绘全模式节点 (相比与之前的kSamplerInpating节点逻辑会更合理些)\r\n\r\n[en]\r\n- Added **gitsScheduler**\r\n- Added `easy imageBatchToImageList` and `easy imageListToImageBatch` \r\n- Recursive subcategories nested for models\r\n- Support for Stable Diffusion 3 model\r\n- Added `easy applyInpaint` - All inpainting mode in this node\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.1.8...v1.1.9","2024-06-25T11:18:53",{"id":248,"version":249,"summary_zh":250,"released_at":251},222659,"v1.1.8","[cn]\r\n- 增加中文提示词自动翻译，使用[opus-mt-zh-en模型](https:\u002F\u002Fhuggingface.co\u002FHelsinki-NLP\u002Fopus-mt-zh-en), 默认已对wildcard、lora正则处理, 其他需要保留的中文，可使用`@你的提示词@`包裹 (若依赖安装完成后报错, 请重启)，测算大约会占0.3GB显存\r\n- 增加 `easy controlnetStack` - controlnet堆\r\n- 增加 `easy applyBrushNet` - [示例参考](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4brushnet_1.1.8.json)\r\n- 增加 `easy applyPowerPaint` - [示例参考](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4powerpaint_outpaint_1.1.8.json)\r\n\r\n[en]\r\n- Added `easy controlnetStack`\r\n- Added `easy applyBrushNet` - [Workflow Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4brushnet_1.1.8.json)\r\n- Added `easy applyPowerPaint` - [Workflow Example](https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Yolain-Workflows\u002Fblob\u002Fmain\u002Fworkflows\u002F2_advanced\u002F2-4inpainting\u002F2-4powerpaint_outpaint_1.1.8.json)\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.1.7...v1.1.8","2024-06-04T15:38:11",{"id":253,"version":254,"summary_zh":255,"released_at":256},222660,"v1.1.7","- Added `easy prompt` - Subject and light presets, maybe adjusted later\r\n- Added `easy icLightApply` - Light and shadow migration, Code based on [ComfyUI-IC-Light](https:\u002F\u002Fgithub.com\u002Fhuchenlei\u002FComfyUI-IC-Light)\r\n- Added `easy imageSplitGrid`\r\n- `easy kSamplerInpainting` added options such as different diffusion and brushnet in **additional** widget\r\n- Support for brushnet model loading - [ComfyUI-BrushNet](https:\u002F\u002Fgithub.com\u002Fnullquant\u002FComfyUI-BrushNet)\r\n- Added `easy applyFooocusInpaint` - Replace FooocusInpaintLoader\r\n- Removed `easy fooocusInpaintLoader`\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fyolain\u002FComfyUI-Easy-Use\u002Fcompare\u002Fv1.1.6...v1.1.7","2024-05-23T05:53:33"]