Show HN: I made ComfyUI nodes for virtual try-on using IDM-VTON

{
  "by": "TemryL",
  "descendants": 0,
  "id": 40228981,
  "score": 5,
  "text": "Hey HN,<p>4 days ago I went through the impressive demo of IDM-VTON on HuggingFace. I found there was no ComfyUI adaptation of this new model.<p>So I’ve implemented custom nodes in ComfyUI that allow anyone to perform virtual try-ons using IDM-VTON. Simply load an image of a model and a garment, and the node will generate a new image with the garment worn by the model.<p>I would love to hear your thoughts and feedback!<p>Cheers,\nTom",
  "time": 1714595478,
  "title": "Show HN: I made ComfyUI nodes for virtual try-on using IDM-VTON",
  "type": "story",
  "url": "https://github.com/TemryL/ComfyUI-IDM-VTON"
}

{
  "author": "TemryL",
  "date": null,
  "description": "ComfyUI adaptation of IDM-VTON for virtual try-on. - TemryL/ComfyUI-IDM-VTON",
  "image": "https://opengraph.githubassets.com/e96abc52328545856c50a401d3abcc9f2db6cd42594a20e9eaf30f1e008afeba/TemryL/ComfyUI-IDM-VTON",
  "logo": "https://logo.clearbit.com/github.com",
  "publisher": "GitHub",
  "title": "GitHub - TemryL/ComfyUI-IDM-VTON: ComfyUI adaptation of IDM-VTON for virtual try-on.",
  "url": "https://github.com/TemryL/ComfyUI-IDM-VTON"
}

{
  "url": "https://github.com/TemryL/ComfyUI-IDM-VTON",
  "title": "GitHub - TemryL/ComfyUI-IDM-VTON: ComfyUI adaptation of IDM-VTON for virtual try-on.",
  "description": "ComfyUI-IDM-VTON ComfyUI adaptation of IDM-VTON.  Installation ⚠️ Current implementation requires GPU with at least 16GB of VRAM ⚠️ Using ComfyUI Manager:  In ComfyUI Manager, look for ComfyUI-IDM-VTON, and...",
  "links": [
    "https://github.com/TemryL/ComfyUI-IDM-VTON"
  ],
  "image": "https://opengraph.githubassets.com/e96abc52328545856c50a401d3abcc9f2db6cd42594a20e9eaf30f1e008afeba/TemryL/ComfyUI-IDM-VTON",
  "content": "<div><article><p></p><h2>ComfyUI-IDM-VTON</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#comfyui-idm-vton\"></a><p></p>\n<p>ComfyUI adaptation of <a target=\"_blank\" href=\"https://github.com/yisol/IDM-VTON\">IDM-VTON</a>.</p>\n<p><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON/blob/main/workflow.png\"><img src=\"https://github.com/TemryL/ComfyUI-IDM-VTON/raw/main/workflow.png\" alt=\"workflow\" /></a></p>\n<p></p><h2>Installation</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#installation\"></a><p></p>\n<p>⚠️ Current implementation requires GPU with at least 16GB of VRAM ⚠️</p>\n<p></p><h3>Using ComfyUI Manager:</h3><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#using-comfyui-manager\"></a><p></p>\n<ul>\n<li>In <a target=\"_blank\" href=\"https://github.com/ltdrdata/ComfyUI-Manager\">ComfyUI Manager</a>, look for <code>ComfyUI-IDM-VTON</code>, and be sure the author is <code>TemryL</code>. Install it.</li>\n</ul>\n<p></p><h3>Manually:</h3><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#manually\"></a><p></p>\n<ul>\n<li>Clone this repo into <code>custom_nodes</code> folder in ComfyUI and install the dependencies.</li>\n</ul>\n<div><pre><span>cd</span> custom_nodes\ngit clone https://github.com/TemryL/ComfyUI-IDM-VTON.git\n<span>cd</span> ComfyUI-IDM-VTON\npython install.py</pre></div>\n<p>Models weights from <a target=\"_blank\" href=\"https://huggingface.co/yisol/IDM-VTON\">yisol/IDM-VTON</a> in <a target=\"_blank\" href=\"https://huggingface.co/\">HuggingFace</a> will be downloaded in <a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON/blob/main/models\">models</a> folder of this repository.</p>\n<p></p><h2>Mask Generation</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#mask-generation\"></a><p></p>\n<p>The workflow provided above uses <a target=\"_blank\" href=\"https://github.com/storyicon/comfyui_segment_anything\">ComfyUI Segment Anything</a> to generate the image mask.</p>\n<p></p><h2>DensePose Estimation</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#densepose-estimation\"></a><p></p>\n<p>DensePose estimation is performed using <a target=\"_blank\" href=\"https://github.com/Fannovel16/comfyui_controlnet_aux\">ComfyUI's ControlNet Auxiliary Preprocessors</a>.</p>\n<p></p><h2>⭐ Star Us!</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#star-star-us\"></a><p></p>\n<p>If you find this project useful, please consider giving it a star on GitHub. This helps the project to gain visibility and encourages more contributors to join in. Thank you for your support!</p>\n<p></p><h2>Contribute</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#contribute\"></a><p></p>\n<p>Thanks for your interest in contributing to the source code! We welcome help from anyone and appreciate every contribution, no matter how small!</p>\n<p>If you're ready to contribute, please create a fork, make your changes, commit them, and then submit a pull request for review. We'll consider it for integration into the main code base.</p>\n<p></p><h2>Credits</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#credits\"></a><p></p>\n<ul>\n<li><a target=\"_blank\" href=\"https://github.com/comfyanonymous/ComfyUI\">ComfyUI</a></li>\n<li><a target=\"_blank\" href=\"https://github.com/yisol/IDM-VTON\">IDM-VTON</a></li>\n<li><a target=\"_blank\" href=\"https://github.com/storyicon/comfyui_segment_anything\">ComfyUI Segment Anything</a></li>\n<li><a target=\"_blank\" href=\"https://github.com/Fannovel16/comfyui_controlnet_aux\">ComfyUI's ControlNet Auxiliary Preprocessors</a></li>\n</ul>\n<p></p><h2>License</h2><a target=\"_blank\" href=\"https://github.com/TemryL/ComfyUI-IDM-VTON#license\"></a><p></p>\n<p>Original <a target=\"_blank\" href=\"https://github.com/yisol/IDM-VTON\">IDM-VTON</a> source code under <a target=\"_blank\" href=\"https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode\">CC BY-NC-SA 4.0 license</a>.</p>\n</article></div>",
  "author": "",
  "favicon": "https://github.githubassets.com/favicons/favicon.svg",
  "source": "github.com",
  "published": "",
  "ttr": 43,
  "type": "object"
}