{"id":13487814,"url":"https://github.com/MC-E/DragonDiffusion","last_synced_at":"2025-03-27T23:31:47.373Z","repository":{"id":179021193,"uuid":"657057334","full_name":"MC-E/DragonDiffusion","owner":"MC-E","description":"ICLR 2024 (Spotlight)","archived":false,"fork":false,"pushed_at":"2024-03-02T01:26:51.000Z","size":10964,"stargazers_count":721,"open_issues_count":21,"forks_count":22,"subscribers_count":41,"default_branch":"master","last_synced_at":"2024-10-30T23:35:53.310Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/MC-E.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":"2023-06-22T08:15:41.000Z","updated_at":"2024-10-28T21:53:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"1f0f8982-b83e-4a08-9950-d5299b786f47","html_url":"https://github.com/MC-E/DragonDiffusion","commit_stats":null,"previous_names":["mc-e/dragondiffusion"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MC-E%2FDragonDiffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MC-E%2FDragonDiffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MC-E%2FDragonDiffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MC-E%2FDragonDiffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MC-E","download_url":"https://codeload.github.com/MC-E/DragonDiffusion/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245944020,"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":[],"created_at":"2024-07-31T18:01:04.409Z","updated_at":"2025-03-27T23:31:44.645Z","avatar_url":"https://github.com/MC-E.png","language":"Python","readme":"# [DragonDiffusion](https://arxiv.org/abs/2307.02421) + [DiffEditor](https://arxiv.org/abs/2402.02583)\n[Chong Mou](https://scholar.google.com/citations?user=SYQoDk0AAAAJ\u0026hl=zh-CN),\n[Xintao Wang](https://xinntao.github.io/),\n[Jiechong Song](),\n[Ying Shan](https://scholar.google.com/citations?user=4oXBp9UAAAAJ),\n[Jian Zhang](https://jianzhang.tech/)\n\n[![Project page](https://img.shields.io/badge/Project-Page-brightgreen)](https://mc-e.github.io/project/DragonDiffusion/)\n[![arXiv](https://img.shields.io/badge/ArXiv-2304.08465-brightgreen)](https://arxiv.org/abs/2307.02421)\n[![arXiv](https://img.shields.io/badge/ArXiv-2402.02583-brightgreen)](https://arxiv.org/abs/2402.02583)\n\n---\nhttps://user-images.githubusercontent.com/54032224/302051504-dac634f3-85ef-4ff1-80a2-bd2805e067ea.mp4\n\n## 🚩 **New Features/Updates**\n- [2024/02/26] **DiffEditor** is accepted by CVPR 2024.\n- [2024/02/05] Releasing the paper of **DiffEditor**.\n- [2024/02/04] Releasing the code of **DragonDiffusion** and **DiffEditor**.\n- [2024/01/15] **DragonDiffusion** is accepted by ICLR 2024 (**Spotlight**).\n- [2023/07/06] Paper of **DragonDiffusion** is available [here](https://arxiv.org/abs/2307.02421).\n\n---\n\n# Introduction\n**DragonDiffusion** is a turning-free method for fine-grained image editing. The core idea of DragonDiffusion comes from [score-based diffusion](https://arxiv.org/abs/2011.13456). It can perform various editing tasks, including object moving, object resizing, object appearance replacement, content dragging, and object pasting. **DiffEditor** further improves the editing accuracy and flexibility of DragonDiffusion.\n\n# 🔥🔥🔥 Main Features  \n### **Appearance Modulation**  \nAppearance Modulation can change the appearance of an object in an image. The final appearance can be specified by a reference image.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://huggingface.co/Adapter/DragonDiffusion/resolve/main/asserts/appearance.PNG\" height=240\u003e\n\u003c/p\u003e\n\n### **Object Moving \u0026 Resizing**  \nObject Moving can move an object in the image to a specified location.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://huggingface.co/Adapter/DragonDiffusion/resolve/main/asserts/move.PNG\" height=220\u003e\n\u003c/p\u003e\n\n### **Face Modulation**  \nFace Modulation can transform the outline of one face into the outline of another reference face.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://huggingface.co/Adapter/DragonDiffusion/resolve/main/asserts/face.PNG\" height=250\u003e\n\u003c/p\u003e\n\n### **Content Dragging**  \nContent Dragging can perform image editing through point-to-point dragging.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://huggingface.co/Adapter/DragonDiffusion/resolve/main/asserts/drag.PNG\" height=230\u003e\n\u003c/p\u003e\n\n### **Object Pasting**  \nObject Pasting can paste a given object onto a background image.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://huggingface.co/Adapter/DragonDiffusion/resolve/main/asserts/paste.PNG\" height=250\u003e\n\u003c/p\u003e\n\n# 🔧 Dependencies and Installation\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= 2.0.1](https://pytorch.org/)\n```bash\npip install -r requirements.txt\npip install dlib==19.14.0\n```\n\n# ⏬ Download Models \nAll models will be automatically downloaded. You can also choose to download manually from this [url](https://huggingface.co/Adapter/DragonDiffusion).\n\n# 💻 How to Test\nInference requires at least `16GB` of GPU memory for editing a `768x768` image.  \nWe provide a quick start on gradio demo.\n```bash\npython app.py\n```\n\n# Related Works\n[1] \u003ca href=\"https://github.com/XingangPan/DragGAN\"\u003eDrag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold\u003c/a\u003e\n\u003c/p\u003e\n\u003cp\u003e\n[2] \u003ca href=\"https://yujun-shi.github.io/projects/dragdiffusion.html\"\u003eDragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing\u003c/a\u003e\n\u003c/p\u003e\n\u003cp\u003e\n[3] \u003ca href=\"https://arxiv.org/abs/2306.03881\"\u003e\nEmergent Correspondence from Image Diffusion\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\n[4] \u003ca href=\"https://dave.ml/selfguidance/\"\u003eDiffusion Self-Guidance for Controllable Image Generation\u003c/a\u003e\n\u003c/p\u003e\n\u003cp\u003e\n[5] \u003ca href=\"https://browse.arxiv.org/abs/2308.06721\"\u003eIP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models\u003c/a\u003e\n\u003c/p\u003e\n\n# 🤗 Acknowledgements\nWe appreciate the foundational work done by [score-based diffusion](https://arxiv.org/abs/2011.13456) and [DragGAN](https://arxiv.org/abs/2305.10973).\n\n# BibTeX\n\n    @article{mou2023dragondiffusion,\n      title={Dragondiffusion: Enabling drag-style manipulation on diffusion models},\n      author={Mou, Chong and Wang, Xintao and Song, Jiechong and Shan, Ying and Zhang, Jian},\n      journal={arXiv preprint arXiv:2307.02421},\n      year={2023}\n    }\n    @article{mou2023diffeditor,\n      title={DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing},\n      author={Mou, Chong and Wang, Xintao and Song, Jiechong and Shan, Ying and Zhang, Jian},\n      journal={arXiv preprint arXiv:2402.02583},\n      year={2023}\n    }\n","funding_links":[],"categories":["Personalized Restoration","Papers"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMC-E%2FDragonDiffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMC-E%2FDragonDiffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMC-E%2FDragonDiffusion/lists"}