[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71128":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":29,"readmeContent":30,"aiSummary":31,"trendingCount":16,"starSnapshotCount":16,"syncStatus":32,"lastSyncTime":33,"discoverSource":34},71128,"lora-scripts","Akegarasu\u002Flora-scripts","Akegarasu","SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.","",null,"Python",6046,695,35,132,0,4,17,39.53,"GNU Affero General Public License v3.0",false,"main",true,[25,26,27,28],"dreambooth","finetune","lora","stable-diffusion","2026-06-12 02:02:48","\u003Cdiv align=\"center\">\n\n\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Fassets\u002F36563862\u002F3b177f4a-d92a-4da4-85c8-a0d163061a40\" width=\"200\" height=\"200\" alt=\"SD-Trainer\" style=\"border-radius: 25px\">\n\n# SD-Trainer\n\n_✨ Enjoy Stable Diffusion Train！ ✨_\n\n\u003C\u002Fdiv>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\" style=\"margin: 2px;\">\n    \u003Cimg alt=\"GitHub Repo stars\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FAkegarasu\u002Flora-scripts\">\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\" style=\"margin: 2px;\">\n    \u003Cimg alt=\"GitHub forks\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FAkegarasu\u002Flora-scripts\">\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fraw.githubusercontent.com\u002FAkegarasu\u002Flora-scripts\u002Fmaster\u002FLICENSE\" style=\"margin: 2px;\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002FAkegarasu\u002Flora-scripts\" alt=\"license\">\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Freleases\" style=\"margin: 2px;\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002FAkegarasu\u002Flora-scripts?color=blueviolet&include_prereleases\" alt=\"release\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Freleases\">Download\u003C\u002Fa>\n  ·\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Fblob\u002Fmain\u002FREADME.md\">Documents\u003C\u002Fa>\n  ·\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Fblob\u002Fmain\u002FREADME-zh.md\">中文README\u003C\u002Fa>\n\u003C\u002Fp>\n\nLoRA-scripts (a.k.a SD-Trainer)\n\nLoRA & Dreambooth training GUI & scripts preset & one key training environment for [kohya-ss\u002Fsd-scripts](https:\u002F\u002Fgithub.com\u002Fkohya-ss\u002Fsd-scripts.git)\n\n## ✨NEW: Train WebUI\n\nThe **REAL** Stable Diffusion Training Studio. Everything in one WebUI.\n\nFollow the installation guide below to install the GUI, then run `run_gui.ps1`(windows) or `run_gui.sh`(linux) to start the GUI.\n\n![image](https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Fassets\u002F36563862\u002Fd3fcf5ad-fb8f-4e1d-81f9-c903376c19c6)\n\n| Tensorboard | WD 1.4 Tagger | Tag Editor |\n| ------------ | ------------ | ------------ |\n| ![image](https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Fassets\u002F36563862\u002Fb2ac5c36-3edf-43a6-9719-cb00b757fc76) | ![image](https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Fassets\u002F36563862\u002F9504fad1-7d77-46a7-a68f-91fbbdbc7407) | ![image](https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\u002Fassets\u002F36563862\u002F4597917b-caa8-4e90-b950-8b01738996f2) |\n\n\n# Usage\n\n### Required Dependencies\n\nPython 3.10 and Git\n\n### Clone repo with submodules\n\n```sh\ngit clone --recurse-submodules https:\u002F\u002Fgithub.com\u002FAkegarasu\u002Flora-scripts\n```\n\n## ✨ SD-Trainer GUI\n\n### Windows\n\n#### Installation\n\nRun `install.ps1` will automatically create a venv for you and install necessary deps. \nIf you are in China mainland, please use `install-cn.ps1`\n\n#### Train\n\nrun `run_gui.ps1`, then program will open [http:\u002F\u002F127.0.0.1:28000](http:\u002F\u002F127.0.0.1:28000) automanticlly\n\n### Linux\n\n#### Installation\n\nRun `install.bash` will create a venv and install necessary deps. \n\n#### Train\n\nrun `bash run_gui.sh`, then program will open [http:\u002F\u002F127.0.0.1:28000](http:\u002F\u002F127.0.0.1:28000) automanticlly\n\n## Legacy training through run script manually\n\n### Windows\n\n#### Installation\n\nRun `install.ps1` will automatically create a venv for you and install necessary deps.\n\n#### Train\n\nEdit `train.ps1`, and run it.\n\n### Linux\n\n#### Installation\n\nRun `install.bash` will create a venv and install necessary deps.\n\n#### Train\n\nTraining script `train.sh` **will not** activate venv for you. You should activate venv first.\n\n```sh\nsource venv\u002Fbin\u002Factivate\n```\n\nEdit `train.sh`, and run it.\n\n#### TensorBoard\n\nRun `tensorboard.ps1` will start TensorBoard at http:\u002F\u002Flocalhost:6006\u002F\n\n## Program arguments\n\n| Parameter Name                | Type  | Default Value | Description                                      |\n|-------------------------------|-------|---------------|--------------------------------------------------|\n| `--host`                      | str   | \"127.0.0.1\"   | Hostname for the server                          |\n| `--port`                      | int   | 28000         | Port to run the server                           |\n| `--listen`                    | bool  | false         | Enable listening mode for the server             |\n| `--skip-prepare-environment`  | bool  | false         | Skip the environment preparation step            |\n| `--disable-tensorboard`       | bool  | false         | Disable TensorBoard                              |\n| `--disable-tageditor`         | bool  | false         | Disable tag editor                               |\n| `--tensorboard-host`          | str   | \"127.0.0.1\"   | Host to run TensorBoard                          |\n| `--tensorboard-port`          | int   | 6006          | Port to run TensorBoard                          |\n| `--localization`              | str   |               | Localization settings for the interface          |\n| `--dev`                       | bool  | false         | Developer mode to disale some checks             |\n","SD-Trainer 是一个用于训练LoRA和Dreambooth模型的图形界面及脚本工具，基于kohya-ss的训练器，适用于扩散模型。项目提供了用户友好的GUI，简化了从环境搭建到模型训练的全过程，并支持通过WebUI进行操作，集成有Tensorboard、WD 1.4 Tagger和Tag Editor等实用功能。该工具适合需要对Stable Diffusion模型进行微调或个性化定制的研究人员与开发者使用，尤其对于希望在不深入了解底层代码的情况下快速上手模型训练的用户非常友好。",2,"2026-06-11 03:36:00","high_star"]