[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72811":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":17,"rankGlobal":9,"rankLanguage":9,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":19,"hasPages":19,"topics":21,"createdAt":9,"pushedAt":9,"updatedAt":22,"readmeContent":23,"aiSummary":24,"trendingCount":15,"starSnapshotCount":15,"syncStatus":25,"lastSyncTime":26,"discoverSource":27},72811,"gligen-gui","mut-ex\u002Fgligen-gui","mut-ex","An intuitive GUI for GLIGEN that uses ComfyUI in the backend",null,"JavaScript",2045,185,14,21,0,1,58.91,"Other",false,"main",[],"2026-06-12 04:01:07","\u003Cp align=\"center\">\nIf you would like to show your appreciation for this project,\u003Cbr>please consider a donation :)\u003Cbr>\u003Cbr>\n\u003Ca href=\"https:\u002F\u002Fwww.paypal.com\u002Fdonate\u002F?business=Y4Y75KP2JBNJW&currency_code=USD\">\n\u003Cimg src=\"https:\u002F\u002Fwww.paypalobjects.com\u002Fen_US\u002Fi\u002Fbtn\u002Fbtn_donateCC_LG.gif\" alt=\"PayPal donation link\"\u002F>\u003C\u002Fa>\n\u003Cp>\n\n# GLIGEN GUI\n\n[GLIGEN](https:\u002F\u002Fgligen.github.io\u002F) is a novel way to specify the precise location of objects in text-to-image models. I present here an intuitive GUI that makes it significantly easier to use GLIGEN with ComfyUI.\n\n[N.B. If you want more control over your workflow check out the ComfyUI node to accompany this GUI](https:\u002F\u002Fgithub.com\u002Fmut-ex\u002Fcomfyui-gligengui-node)\n\n![GLIGEN GUI screenshot](latest.png)\n\n![GLIGEN Example Image](example_boxes.png)\n![GLIGEN Example Image](example.png)\n\n## Newest Features:\n* You can now move and resize the boxes\n* Ability to save the session the session to file and load a session from file\n* The VAE and the sampler can now be specified as well\n* Improved support for differnt aspect ratios + presets\n\n## Getting Started\n\nFirst of all make sure you have [ComfyUI](https:\u002F\u002Fgithub.com\u002Fcomfyanonymous\u002FComfyUI) successfully installed and running.\n\nNext, download the [gligen_sd14_textbox_pruned.safetensors](https:\u002F\u002Fhuggingface.co\u002Fcomfyanonymous\u002FGLIGEN_pruned_safetensors\u002Fblob\u002Fmain\u002Fgligen_sd14_textbox_pruned.safetensors) GLIGEN model file and place it in the ComfyUI\u002Fmodels\u002Fgligen directory.\n\nMake sure you have [Flask](https:\u002F\u002Fflask.palletsprojects.com\u002Fen\u002F3.0.x\u002F) installed\n\n    pip install flask\n\nClone this repository\n\n    git clone https:\u002F\u002Fgithub.com\u002Fmut-ex\u002Fgligen-gui.git\n    cd gligen-gui\n\nThen to start the GUI, run the following command\n\n    flask --app 'gligen_gui:create_app(8188)' run --port 5000\n\nNote that this assumes your ComfyUI instance is using port 8188. If not, replace 8188 with the correct port number.\n\nFinally, open http:\u002F\u002F127.0.0.1:5000\u002Fport\u002F8188 in your browser to start using the GUI. However change 8188 in the URL to the port used by ComfyUI if it is different.\n\n## How To Use\n\nMake sure you have a Stable Diffusion 1.5 **checkpoint** selected. Usage is pretty simple and straightforward! Envision your image by drawing grounding boxes on the blank canvas with your mouse, and labeling them by entering your desired prompt in the corresponding text input in the table on the right.\n\nYou can further describe your image in the text input labelled **POSITIVE** but in my experience it works better if you only enter tags relating to the style and quality of your desired image.\n\nIf there are any LORAs you wish to use, press the **+** button in the LORA section. Then, select the name of the LORA and adjust its strength, You can add mulitple LORAs.\n\nFinally, press the Queue Prompt to submit the prompt to ComfyUI. Once the image is generated, it will appear on the canvas.\n","该项目是一个为GLIGEN设计的直观图形用户界面，后端基于ComfyUI。它通过提供一个易于使用的前端界面，使得在文本到图像模型中指定对象精确位置变得更加简单。核心功能包括移动和调整框大小、保存和加载会话、指定VAE和采样器等，并支持多种宽高比及预设设置。适用于需要精准控制生成图像中元素位置的场景，如艺术创作、设计原型制作等领域。使用时需先安装并运行ComfyUI，再通过Flask启动本项目提供的GUI，在浏览器中即可操作。",2,"2026-06-11 03:43:41","high_star"]