{"id":13487763,"url":"https://github.com/muzishen/IMAGDressing","last_synced_at":"2025-03-27T23:31:41.786Z","repository":{"id":244199033,"uuid":"809060646","full_name":"muzishen/IMAGDressing","owner":"muzishen","description":"[AAAI 2025]👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing. It enables customizable human image generation with flexible garment, pose, and scene control, ensuring high fidelity and garment consistency for virtual dressing.","archived":false,"fork":false,"pushed_at":"2025-03-18T03:26:41.000Z","size":48617,"stargazers_count":1188,"open_issues_count":12,"forks_count":103,"subscribers_count":14,"default_branch":"main","last_synced_at":"2025-03-18T04:29:06.296Z","etag":null,"topics":["datasets","diffusion-models","text-to-image-generation","try-on"],"latest_commit_sha":null,"homepage":"https://imagdressing.github.io/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/muzishen.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-01T15:18:27.000Z","updated_at":"2025-03-18T03:26:44.000Z","dependencies_parsed_at":"2024-06-13T11:35:31.499Z","dependency_job_id":"285d0dc5-1390-48db-b9f7-730cda00fe40","html_url":"https://github.com/muzishen/IMAGDressing","commit_stats":null,"previous_names":["muzishen/imagdressing"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muzishen%2FIMAGDressing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muzishen%2FIMAGDressing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muzishen%2FIMAGDressing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/muzishen%2FIMAGDressing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/muzishen","download_url":"https://codeload.github.com/muzishen/IMAGDressing/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245944019,"owners_count":20697945,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["datasets","diffusion-models","text-to-image-generation","try-on"],"created_at":"2024-07-31T18:01:03.467Z","updated_at":"2025-03-27T23:31:36.755Z","avatar_url":"https://github.com/muzishen.png","language":"Python","funding_links":[],"categories":["Python","Personalized Restoration","Projekte"],"sub_categories":["🌄 Image"],"readme":"# **👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing**\n\n\n## 📦️ Release\n- [2024/08/24] 🔥 We add the [train code](https://github.com/muzishen/IMAGDressing/blob/main/train.py), feel free to give it a try!\n- [2024/08/23] 🔥 We release the [IGPair dataset](https://huggingface.co/datasets/IMAGDressing/IGPair) publicly available for download.\n- [2024/07/30] 🔥 We release the [WebUI Code](https://github.com/muzishen/IMAGDressing/blob/main/app.py) for gradio interface.\n- [2024/07/26] 🔥 We release the [online webui]( https://huggingface.co/spaces/feishen29/IMAGDressing-v1)，thanks to [ZeroGPU](https://huggingface.co/zero-gpu-explorers) for providing free A100 GPUs. And the original [Gradio_demo](https://sf.dictdoc.site/)  is soon to be deprecated. \n- [2024/07/19] 🔥 We release the [code](https://github.com/muzishen/IMAGDressing/blob/main/inference_IMAGdressing_cartoon_style.py) and [examples](https://github.com/muzishen/IMAGDressing/blob/main/assets/cartoon.png) for cartoon-style virtual dressing.\n- [2024/07/18] 🔥 We release the [technical report of IMAGDressing-v1](http://arxiv.org/abs/2407.12705) and [CAMI metric code](https://github.com/muzishen/IMAGDressing/tree/main/metric).\n- [2024/07/16] 🔥 We add the batch inference for [full VD](https://github.com/muzishen/IMAGDressing/blob/main/inference_IMAGdressing_controlnetinpainting_folder.py) and [VTON](https://github.com/muzishen/IMAGDressing/blob/main/inference_IMAGdressing_ipa_controlnetpose_folder.py). Thanks @ZhaoChaoqun for the contribution.\n- [2024/07/01] 🔥 We release the test cases in the assets/images directory.\n- [2024/06/21] 🔥 We release the inpainting feature to enable outfit changing. **[Experimental Feature](assets/inpainting.png)**.\n- [2024/06/13] 🔥 We release the [Gradio_demo](https://sf.dictdoc.site/) of IMAGDressing-v1 (**Service deprecation imminent**).\n- [2024/05/28] 🔥 We release the inference code of SD1.5 that is compatible with [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter) and [ControlNet](https://github.com/lllyasviel/ControlNet).\n- [2024/05/08]  🔥 We launch the [project page](https://imagdressing.github.io/) of IMAGDressing-v1.\n\n---\n\n## IMAGDressing-v1: Customizable Virtual Dressing\n\u003ca href='https://imagdressing.github.io/'\u003e\u003cimg src='https://img.shields.io/badge/Project-Page-green'\u003e\u003c/a\u003e\n\u003ca href='http://arxiv.org/abs/2407.12705'\u003e\u003cimg src='https://img.shields.io/badge/Technique-Report-red'\u003e\u003c/a\u003e\n\u003ca href='https://huggingface.co/feishen29/IMAGDressing'\u003e\u003cimg src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-blue'\u003e\u003c/a\u003e\n\u003ca href='https://huggingface.co/datasets/IMAGDressing/IGPair'\u003e\u003cimg src='https://img.shields.io/badge/Dataset-IGPair-orange'\u003e\u003c/a\u003e\n[![GitHub stars](https://img.shields.io/github/stars/muzishen/IMAGDressing?style=social)](https://github.com/muzishen/IMAGDressing)\n\n\n\n### 🚀 **Key Features:**\n1. **Simple Architecture**: IMAGDressing-v1 generates lifelike garments and facilitates easy user-driven scene editing.\n2. **New Task, Metric, and Dataset**: Introduces the virtual dressing (VD) task, designs a comprehensive affinity metric index (CAMI), and releases the IGPair dataset.\n3. **Flexible Plugin Compatibility**: Seamlessly integrates with extension plugins such as [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter), [ControlNet](https://github.com/lllyasviel/ControlNet), [T2I-Adapter](https://github.com/TencentARC/T2I-Adapter), and [AnimateDiff](https://github.com/guoyww/AnimateDiff).\n4. **Rapid Customization**: Allows for rapid customization within seconds without the need for additional LoRA training.\n\n\n\n## 🔥 **Dataset Demo**\nYou can download the dataset from [Baidu Cloud](https://pan.baidu.com/s/1y-VnKWgHHCPV5M4zQUmn7g?pwd=IMAG) or [Huggingface Dataset](https://huggingface.co/datasets/IMAGDressing/IGPair). By requesting access, you agree to use the data only for academic and personal purposes and not for commercial use.\n\n![Dataset Demo](assets/dataset_demo.png)\n\n## 🔥 **Examples**\n\n\u003cdiv style=\"display: flex; justify-content: space-around;\"\u003e\n  \u003cimg src=\"assets/scrolling_images1.gif\" alt=\"GIF 1\" width=\"200\" /\u003e\n  \u003cimg src=\"assets/scrolling_images2.gif\" alt=\"GIF 2\" width=\"200\" /\u003e\n  \u003cimg src=\"assets/scrolling_images3.gif\" alt=\"GIF 3\" width=\"200\" /\u003e\n    \u003cimg src=\"assets/scrolling_images4.gif\" alt=\"GIF 4\" width=\"200\" /\u003e\n\u003c/div\u003e\n\n\n![compare](assets/compare_magic2.png)\n\n### \u003cspan style=\"color:red\"\u003eConbined with IP-Adapter and Controlnet-Pose\u003c/span\u003e\n\n![compare](assets/pose.png)\n\n![compare](assets/person.png)\n\n### \u003cspan style=\"color:red\"\u003eSupport text prompts for different scenes\u003c/span\u003e\n![different scenes](assets/different_scenes.png)\n\n### \u003cspan style=\"color:red\"\u003eSupports outfit changing in specified areas (Experimental Feature)\u003c/span\u003e\n![inpainting](assets/inpainting.png)\n\n### \u003cspan style=\"color:red\"\u003eSupports generating cartoon-style images (Experimental Feature)\u003c/span\u003e\n![cartoon](assets/cartoon.png)\n\n\n## 🏷️  Introduction\n\nTo address the need for flexible and controllable customizations in virtual try-on systems, we propose IMAGDressing-v1. Specifically, we introduce a garment UNet that captures semantic features from CLIP and texture features from VAE. Our hybrid attention module includes a frozen self-attention and a trainable cross-attention, integrating these features into a frozen denoising UNet to ensure user-controlled editing. We will release a comprehensive dataset, IGPair, with over 300,000 pairs of clothing and dressed images, and establish a standard data assembly pipeline. Furthermore, IMAGDressing-v1 can be combined with extensions like ControlNet, IP-Adapter, T2I-Adapter, and AnimateDiff to enhance diversity and controllability. \n\n![framework](assets/pipeline.png)\n\n## 🔧 Requirements\n\n- Python \u003e= 3.8 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))\n- [PyTorch \u003e= 2.0.0](https://pytorch.org/)\n- cuda==11.8\n\n```bash\nconda create --name IMAGDressing python=3.8.10\nconda activate IMAGDressing\npip install -U pip\n\n# Install requirements\npip install -r requirements.txt\n```\n\n---\n\n\n## 🌐 Download Models\nYou can download our models from [HuggingFace](https://huggingface.co/feishen29/IMAGDressing) or [百度云](https://pan.baidu.com/s/1-69aFUjtrsGnD0OlU0dMzQ?pwd=imag).  You can download the other component models from the original repository, as follows.\n- [stabilityai/sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse).\n- [SG161222/Realistic_Vision_V4.0_noVAE](https://huggingface.co/SG161222/Realistic_Vision_V4.0_noVAE).\n- [h94/IP-Adapter-FaceID](https://huggingface.co/h94/IP-Adapter-FaceID).\n- [lllyasviel/control_v11p_sd15_openpose](https://huggingface.co/lllyasviel/control_v11p_sd15_openpose).\n\n## 🎉 How to Train\n```sh\n# Please download the IGPair data first and modify the path in run.sh\nsh run.sh\n```\n\n## 🎉 How to Test\n\n### \u003cspan style=\"color:red\"\u003eImportant Reminder\u003c/span\u003e\n\n\n### 1. Random faces and poses to dress the assigned clothes \n\n```sh\npython inference_IMAGdressing.py --cloth_path [your cloth path]\n```\n\n\n### 2. Random faces use a given pose to dress a given outfit \n\n```sh\npython inference_IMAGdressing_controlnetpose.py --cloth_path [your cloth path] --pose_path [your posture path]\n```\n\n### 3. Specify the face and posture to wear the specified clothes\n\n```sh\npython inference_IMAGdressing_ipa_controlnetpose.py --cloth_path [your cloth path] --face_path [your face path] --pose_path [your posture path]\n```\n\n### 4. Specify the model to wear the specified clothes (Experimental Feature)\n\u003cspan style=\"color:red\"\u003ePlease download the humanparsing and openpose model file from [IDM-VTON-Huggingface](https://huggingface.co/spaces/yisol/IDM-VTON/tree/main) to the ckpt folder first.\u003c/span\u003e\n```sh\npython inference_IMAGdressing_controlnetinpainting.py --cloth_path [your cloth path] --model_path [your model path]\n```\n### 5. Specify the carton style for generate images (Experimental Feature)\n```sh\npython inference_IMAGdressing_counterfeit-v30.py --cloth_path [your cloth path] --model_path [your model path]\n```\n\n\n## 🤗Gradio interface 🤗\n\nWe also provide a Gradio \u003ca href='https://github.com/gradio-app/gradio'\u003e\u003cimg src='https://img.shields.io/github/stars/gradio-app/gradio'\u003e\u003c/a\u003e interface for a better experience, just run by:\n\n\n```bash\npip install modelscope==1.15.0\npip install mmcv-full==1.7.2\npip install mmdet==2.26.0\n\npython app.py  --model_weight $MODEL PATH --server_port  7860\n```\n\nYou can specify the `--server_port` arguments to satisfy your needs!\n\n\n**Or, try it out effortlessly on [HuggingFace](https://huggingface.co/spaces/feishen29/IMAGDressing-v1) 🤗**\n\n\n## 📚 Get Involved\nJoin us on this exciting journey to transform virtual dressing systems. Star⭐️ our repository to stay updated with the latest advancements, and contribute to making **IMAGDressing** the leading solution for virtual dressing generation.\n### Third-party Implementations of IMAGDressing-v1:\n- [windows-webui](https://github.com/v3ucn/IMAGdressing_WebUi_For_Windows) by @v3ucn\n- [comfyUI](https://github.com/AIFSH/IMAGDressing-ComfyUI) by @AIFSH\n\n\n## Acknowledgement\nWe would like to thank the contributors to the [IDM-VTON](https://github.com/yisol/IDM-VTON), [MagicClothing](https://github.com/ShineChen1024/MagicClothing), [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter), [ControlNet](https://github.com/lllyasviel/ControlNet), [T2I-Adapter](https://github.com/TencentARC/T2I-Adapter), and [AnimateDiff](https://github.com/guoyww/AnimateDiff) repositories, for their open research and exploration.\n\nThe IMAGDressing code is available for both academic and commercial use. However, the models available for manual and automatic download from IMAGDressing are intended solely for non-commercial research purposes. Similarly, our released checkpoints are restricted to research use only. Users are free to create images using this tool, but they must adhere to local laws and use it responsibly. The developers disclaim any liability for potential misuse by users.\n\n## 📝 Citation\n\nIf you find IMAGDressing-v1 useful for your research and applications, please cite using this BibTeX:\n\n```bibtex\n@article{shen2024IMAGDressing-v1,\n  title={IMAGDressing-v1: Customizable Virtual Dressing},\n  author={Shen, Fei and Jiang, Xin and He, Xin and Ye, Hu and Wang, Cong, and Du, Xiaoyu, Li Zechao, and Tang, Jinhui},\n  booktitle={arXiv preprint arXiv:2407.12705},\n  year={2024}\n}\n```\n\n## 🕒 TODO List\n- [x] Gradio demo\n- [x] Inference code\n- [x] Model weights (512 sized version)\n- [x] Support inpaint\n- [ ] Model weights (More higher sized version)\n- [x] Paper\n- [x] Evaluate metric code\n- [x] IGPair dataset\n- [x] Training code\n- [ ] Video Dressing\n- [ ] Others, such as User-Needed Requirements\n\n## 📨 Contact\nIf you have any questions, please feel free to contact with me at shenfei140721@126.com.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmuzishen%2FIMAGDressing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmuzishen%2FIMAGDressing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmuzishen%2FIMAGDressing/lists"}