[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1571":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":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":28,"readmeContent":29,"aiSummary":30,"trendingCount":16,"starSnapshotCount":16,"syncStatus":31,"lastSyncTime":32,"discoverSource":33},1571,"DragGAN","XingangPan\u002FDragGAN","XingangPan","Official Code for DragGAN (SIGGRAPH 2023)","https:\u002F\u002Fvcai.mpi-inf.mpg.de\u002Fprojects\u002FDragGAN\u002F",null,"Python",35825,3421,966,145,0,5,70.5,"Other",false,"main",true,[24,25,26,27],"artificial-intelligence","generative-adversarial-network","generative-models","image-manipulation","2026-06-12 04:00:10","\u003Cp align=\"center\">\n\n  \u003Ch1 align=\"center\">Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold\u003C\u002Fh1>\n  \u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fxingangpan.github.io\u002F\">\u003Cstrong>Xingang Pan\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fayushtewari.com\u002F\">\u003Cstrong>Ayush Tewari\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fpeople.mpi-inf.mpg.de\u002F~tleimkue\u002F\">\u003Cstrong>Thomas Leimkühler\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Flingjie0206.github.io\u002F\">\u003Cstrong>Lingjie Liu\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fwww.meka.page\u002F\">\u003Cstrong>Abhimitra Meka\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"http:\u002F\u002Fwww.mpi-inf.mpg.de\u002F~theobalt\u002F\">\u003Cstrong>Christian Theobalt\u003C\u002Fstrong>\u003C\u002Fa>\n  \u003C\u002Fp>\n  \u003Ch2 align=\"center\">SIGGRAPH 2023 Conference Proceedings\u003C\u002Fh2>\n  \u003Cdiv align=\"center\">\n    \u003Cimg src=\"DragGAN.gif\", width=\"600\">\n  \u003C\u002Fdiv>\n\n  \u003Cp align=\"center\">\n  \u003Cbr>\n    \u003Ca href=\"https:\u002F\u002Fpytorch.org\u002Fget-started\u002Flocally\u002F\">\u003Cimg alt=\"PyTorch\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPyTorch-ee4c2c?logo=pytorch&logoColor=white\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Ftwitter.com\u002FXingangP\">\u003Cimg alt='Twitter' src=\"https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FXingangP?label=%40XingangP\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2305.10973\">\n      \u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPaper-PDF-green?style=for-the-badge&logo=adobeacrobatreader&logoWidth=20&logoColor=white&labelColor=66cc00&color=94DD15' alt='Paper PDF'>\n    \u003C\u002Fa>\n    \u003Ca href='https:\u002F\u002Fvcai.mpi-inf.mpg.de\u002Fprojects\u002FDragGAN\u002F'>\n      \u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDragGAN-Page-orange?style=for-the-badge&logo=Google%20chrome&logoColor=white&labelColor=D35400' alt='Project Page'>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1mey-IXPwQC_qSthI5hO-LTX7QL4ivtPh?usp=sharing\">\u003Cimg src=\"https:\u002F\u002Fcolab.research.google.com\u002Fassets\u002Fcolab-badge.svg\" alt=\"Open In Colab\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fp>\n\n## Web Demos\n\n[![Open in OpenXLab](https:\u002F\u002Fcdn-static.openxlab.org.cn\u002Fapp-center\u002Fopenxlab_app.svg)](https:\u002F\u002Fopenxlab.org.cn\u002Fapps\u002Fdetail\u002FXingangPan\u002FDragGAN)\n\n\u003Cp align=\"left\">\n  \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fradames\u002FDragGan\">\u003Cimg alt=\"Huggingface\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Hugging%20Face-DragGAN-orange\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n## Requirements\n\nIf you have CUDA graphic card, please follow the requirements of [NVlabs\u002Fstylegan3](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fstylegan3#requirements).  \n\nThe usual installation steps involve the following commands, they should set up the correct CUDA version and all the python packages\n\n```\nconda env create -f environment.yml\nconda activate stylegan3\n```\n\nThen install the additional requirements\n\n```\npip install -r requirements.txt\n```\n\nOtherwise (for GPU acceleration on MacOS with Silicon Mac M1\u002FM2, or just CPU) try the following:\n\n```sh\ncat environment.yml | \\\n  grep -v -E 'nvidia|cuda' > environment-no-nvidia.yml && \\\n    conda env create -f environment-no-nvidia.yml\nconda activate stylegan3\n\n# On MacOS\nexport PYTORCH_ENABLE_MPS_FALLBACK=1\n```\n\n## Run Gradio visualizer in Docker \n\nProvided docker image is based on NGC PyTorch repository. To quickly try out visualizer in Docker, run the following:  \n\n```sh\n# before you build the docker container, make sure you have cloned this repo, and downloaded the pretrained model by `python scripts\u002Fdownload_model.py`.\ndocker build . -t draggan:latest  \ndocker run -p 7860:7860 -v \"$PWD\":\u002Fworkspace\u002Fsrc -it draggan:latest bash\n# (Use GPU)if you want to utilize your Nvidia gpu to accelerate in docker, please add command tag `--gpus all`, like:\n#   docker run --gpus all  -p 7860:7860 -v \"$PWD\":\u002Fworkspace\u002Fsrc -it draggan:latest bash\n\ncd src && python visualizer_drag_gradio.py --listen\n```\nNow you can open a shared link from Gradio (printed in the terminal console).   \nBeware the Docker image takes about 25GB of disk space!\n\n## Download pre-trained StyleGAN2 weights\n\nTo download pre-trained weights, simply run:\n\n```\npython scripts\u002Fdownload_model.py\n```\nIf you want to try StyleGAN-Human and the Landscapes HQ (LHQ) dataset, please download weights from these links: [StyleGAN-Human](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F1dlFEHbu-WzQWJl7nBBZYcTyo000H9hVm\u002Fview?usp=sharing), [LHQ](https:\u002F\u002Fdrive.google.com\u002Ffile\u002Fd\u002F16twEf0T9QINAEoMsWefoWiyhcTd-aiWc\u002Fview?usp=sharing), and put them under `.\u002Fcheckpoints`.\n\nFeel free to try other pretrained StyleGAN.\n\n## Run DragGAN GUI\n\nTo start the DragGAN GUI, simply run:\n```sh\nsh scripts\u002Fgui.sh\n```\nIf you are using windows, you can run:\n```\n.\\scripts\\gui.bat\n```\n\nThis GUI supports editing GAN-generated images. To edit a real image, you need to first perform GAN inversion using tools like [PTI](https:\u002F\u002Fgithub.com\u002Fdanielroich\u002FPTI). Then load the new latent code and model weights to the GUI.\n\nYou can run DragGAN Gradio demo as well, this is universal for both windows and linux:\n```sh\npython visualizer_drag_gradio.py\n```\n\n## Acknowledgement\n\nThis code is developed based on [StyleGAN3](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fstylegan3). Part of the code is borrowed from [StyleGAN-Human](https:\u002F\u002Fgithub.com\u002Fstylegan-human\u002FStyleGAN-Human).\n\n(cheers to the community as well)\n## License\n\nThe code related to the DragGAN algorithm is licensed under [CC-BY-NC](https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-nc\u002F4.0\u002F).\nHowever, most of this project are available under a separate license terms: all codes used or modified from [StyleGAN3](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fstylegan3) is under the [Nvidia Source Code License](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fstylegan3\u002Fblob\u002Fmain\u002FLICENSE.txt).\n\nAny form of use and derivative of this code must preserve the watermarking functionality showing \"AI Generated\".\n\n## BibTeX\n\n```bibtex\n@inproceedings{pan2023draggan,\n    title={Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold},\n    author={Pan, Xingang and Tewari, Ayush, and Leimk{\\\"u}hler, Thomas and Liu, Lingjie and Meka, Abhimitra and Theobalt, Christian},\n    booktitle = {ACM SIGGRAPH 2023 Conference Proceedings},\n    year={2023}\n}\n```\n","DragGAN 是一个基于生成对抗网络（GAN）的图像交互式编辑工具，允许用户通过拖拽点来直接操控生成图像。该项目利用了 StyleGAN3 作为基础模型，并结合了 PyTorch 框架实现对图像的精细化控制，包括调整物体位置、姿态和形状等。其核心功能在于提供了一个直观且强大的界面，使得非专业用户也能轻松地进行高质量图像编辑。适用于需要灵活修改合成图像内容的各种场景，如数字艺术创作、设计原型快速迭代以及科研实验中的数据增强等。",2,"2026-06-11 02:44:43","top_all"]