[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72242":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":17,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":29,"readmeContent":30,"aiSummary":31,"trendingCount":16,"starSnapshotCount":16,"syncStatus":18,"lastSyncTime":32,"discoverSource":33},72242,"MagicQuill","ant-research\u002FMagicQuill","ant-research","[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System","https:\u002F\u002Fmagicquill.art",null,"Python",3681,389,46,44,0,1,2,3,29.77,"Other",false,"main",[25,26,27,28],"aigc","gradio","image-editing","mllm","2026-06-12 02:03:00","# 🪶 MagicQuill: An Intelligent Interactive Image Editing System (*CVPR 2025*)\n\u003Ca href=\"https:\u002F\u002Fmagicquill.art\u002Fdemo\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Project&message=magicquill.art&color=blue\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2411.09703\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2411.09703-b31b1b.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FAI4Editing\u002FMagicQuill\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-sa\u002F4.0\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-CC%20BY--SA%204.0-lightgrey.svg\">\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fmagicquill.art\u002Fv2\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Project&message=MagicQuillV2&color=red\">\u003C\u002Fa>\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8ee9663a-fef2-484a-a0b7-8427ab590424\n\nThere is an HD video on [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=5DiKfONMnE4).\n\n[Zichen Liu](https:\u002F\u002Fzliucz.github.io)\u003Csup>\\*,1,2\u003C\u002Fsup>, [Yue Yu](https:\u002F\u002Fbruceyyu.github.io\u002F)\u003Csup>\\*,1,2\u003C\u002Fsup>, [Hao Ouyang](https:\u002F\u002Fken-ouyang.github.io\u002F)\u003Csup>2\u003C\u002Fsup>, [Qiuyu Wang](https:\u002F\u002Fgithub.com\u002Fqiuyu96)\u003Csup>2\u003C\u002Fsup>, [Ka Leong Cheng](https:\u002F\u002Ffelixcheng97.github.io\u002F)\u003Csup>1,2\u003C\u002Fsup>, [Wen Wang](https:\u002F\u002Fgithub.com\u002Fencounter1997)\u003Csup>3,2\u003C\u002Fsup>, [Zhiheng Liu](https:\u002F\u002Fjohanan528.github.io\u002F)\u003Csup>4\u003C\u002Fsup>, [Qifeng Chen](https:\u002F\u002Fcqf.io\u002F)\u003Csup>†,1\u003C\u002Fsup>, [Yujun Shen](https:\u002F\u002Fshenyujun.github.io\u002F)\u003Csup>†,2\u003C\u002Fsup>\u003Cbr>\n\u003Csup>1\u003C\u002Fsup>HKUST \u003Csup>2\u003C\u002Fsup>Ant Group \u003Csup>3\u003C\u002Fsup>ZJU \u003Csup>4\u003C\u002Fsup>HKU \u003Csup>\\*\u003C\u002Fsup>equal contribution \u003Csup>†\u003C\u002Fsup>corresponding author\n\n> TLDR: MagicQuill is an intelligent and interactive system achieving precise image editing.\n>\n> Key Features: 😎 User-friendly interface \u002F 🤖 AI-powered suggestions \u002F 🎨 Precise local editing\n\n- [🪶 MagicQuill: An Intelligent Interactive Image Editing System](#-magicquill-an-intelligent-interactive-image-editing-system)\n  - [TODO List](#todo-list)\n  - [Update Log](#update-log)\n  - [Hardware Requirements](#hardware-requirements)\n  - [Docker Container](#docker-container)\n  - [Setup](#setup)\n  - [Tutorial](#tutorial)\n  - [Citation](#citation)\n  - [Acknowledgement](#acknowledgement)\n  - [Note](#note)\n\n## [MagicQuillV2](https:\u002F\u002Fmagicquill.art\u002Fv2\u002F) has been released!!! Check it out ;)\n\n## TODO List\n\n- [x] Release the paper and demo page. Visit [magicquill.art](https:\u002F\u002Fmagicquill.art) 🪩\n- [x] Release the code and checkpoints.\n- [x] Release gradio demo.\n- [x] Release ComfyUI MagicQuill custom node.\n\n\u003Cimg src=\"docs\u002Fcomfyui.png\" width=\"100%\" >\n\n## Update Log\n\n- [2024.11.21] 📢 Update the save button; Fix path bug on Windows; Add `.bat` and `.sh` files for convenient environment install on Windows and Linux. Thanks [lior007](https:\u002F\u002Fgithub.com\u002Flior007) and [JamesIV4](https:\u002F\u002Fgithub.com\u002FJamesIV4).\n- [2024.11.25] 📢 New UI Updates: Drag & Drop Images + Download Button: We've enhanced our interface with two exciting features! Now you can easily upload images with drag & drop functionality, and quickly save your work using our new download button. Try it out and let us know what you think!\n- [2024.12.06] 📢 New Feature Updates: Auto-save and Resolution Adjustment are now enabled in the parameter settings. Thanks [Furkan Gözükara](https:\u002F\u002Fgithub.com\u002FFurkanGozukara) for his brilliant suggestions.\n- [2024.12.07] 🎉 Exciting News: ComfyUI MagicQuill Node has been released! Check the repository https:\u002F\u002Fgithub.com\u002Fmagic-quill\u002FComfyUI_MagicQuill for more details.\n- [2024.12.16] 🎉 Exciting News: MagicQuill is also available at [Modelscope](https:\u002F\u002Fmodelscope.cn\u002Fstudios\u002Fant-research\u002FMagicQuill_demo). Thanks for their amazing support and infrastructure.\n- [2025.01.02] 🎉 Exciting News: MagicQuill docker container is now available. You can now build & run your own image in a cleaner, isolated environment. Thanks [gbudge](https:\u002F\u002Fgithub.com\u002Fgbudge) for his contribution.\n- [2025.02.27] 🎉 Exciting News: MagicQuill has been accepted to CVPR 2025! Looking forward to meeting everyone in Tennessee!\n- [2025.12.03] 🎉 Exciting News: [MagicQuillV2](https:\u002F\u002Fmagicquill.art\u002Fv2\u002F) has been released! Check it out ;), give us a [star](https:\u002F\u002Fgithub.com\u002Fzliucz\u002FMagicQuillV2) if you are interested.\n\nTo update the latest features, pull the latest code and re-install the gradio_magicquill:\n```\npip uninstall -y gradio_magicquill-0.0.1-py3-none-any.whl\npip install gradio_magicquill-0.0.1-py3-none-any.whl\n```\n\n## Hardware Requirements\n\n- GPU is required to run MagicQuill. **Through our testing, we have confirmed that the model can run on GPUs with 8GB VRAM (RTX4070 Laptop).**\n\nFor users with limited GPU resources, please try our [Huggingface Demo](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FAI4Editing\u002FMagicQuill) and [Modelscope Demo](https:\u002F\u002Fmodelscope.cn\u002Fstudios\u002Fant-research\u002FMagicQuill_demo). Also, consider disabling the DrawNGuess automatic prompt filling by clicking the wand icon above if it takes too long time on your machine.\n\n##  Setup\nFollow the following guide to set up the environment.\n\n1. git clone repo. **Please don't forget the `--recursive` flag.** Otherwise, you will find `LLaVA` submodule missing.\n    ```\n    git clone --recursive https:\u002F\u002Fgithub.com\u002Fmagic-quill\u002FMagicQuill.git\n    cd MagicQuill\n    ```\n2. download and unzip checkpoints\n    ```\n    wget -O models.zip \"https:\u002F\u002Fhkustconnect-my.sharepoint.com\u002F:u:\u002Fg\u002Fpersonal\u002Fzliucz_connect_ust_hk\u002FEWlGF0WfawJIrJ1Hn85_-3gB0MtwImAnYeWXuleVQcukMg?e=Gcjugg&download=1\"\n    unzip models.zip\n    ```\n    If the .zip file is not accessible, download it via browser. All checkpoints are about 25 GB in total. It may take some time to download. Alternatively, check our checkpoints at [huggingface](https:\u002F\u002Fhuggingface.co\u002FLiuZichen\u002FMagicQuill-models).\n\n---\n\nIf you are a Windows user, you may try to use `windows_setup.bat` to conveniently install environments, just enter `windows_setup.bat` in your Python shell. For Linux user, check `linux_setup.sh`.\n\nAlternatively, follow the step-by-step installation guide.\n\n3. create environment\n    ```\n    conda create -n MagicQuill python=3.10 -y\n    conda activate MagicQuill\n    ```\n\n4. install torch with GPU support\n    ```\n    pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\n    ```\n\n5. install the interface\n    ```\n    pip install gradio_magicquill-0.0.1-py3-none-any.whl\n    ```\n    \n6. install llava environment\n    ```\n    (For Linux)\n    cp -f pyproject.toml MagicQuill\u002FLLaVA\u002F\n    pip install -e MagicQuill\u002FLLaVA\u002F\n    ```\n    or\n    ```\n    (For Windows)\n    copy \u002FY pyproject.toml MagicQuill\\LLaVA\\\n    pip install -e MagicQuill\\LLaVA\\\n    ```\n    (For Windows PowerShell, the first line should be `Copy-Item -Path pyproject.toml -Destination \"MagicQuill\\LLaVA\" -Force`)\n    \n\n7. install the remaining environment\n    ```\n    pip install -r requirements.txt\n    ```\n\n8. run magicquill\n    ```\n    python gradio_run.py\n    ```\n    If you are mainland user, you may try `export HF_ENDPOINT=https:\u002F\u002Fhf-mirror.com` to use huggingface mirror to facilitate the download of some necessary checkpoints to run our system.\n\n\n## Docker Container\n\nYou can build a docker container with MagicQuill as follows:\n\n1. git clone repo. **Please don't forget the `--recursive` flag.** Otherwise, you will find `LLaVA` submodule missing.\n    ```\n    git clone --recursive https:\u002F\u002Fgithub.com\u002Fmagic-quill\u002FMagicQuill.git\n    cd MagicQuill\n    ```\n\n2. download and unzip checkpoints\n    ```\n    wget -O models.zip \"https:\u002F\u002Fhkustconnect-my.sharepoint.com\u002F:u:\u002Fg\u002Fpersonal\u002Fzliucz_connect_ust_hk\u002FEWlGF0WfawJIrJ1Hn85_-3gB0MtwImAnYeWXuleVQcukMg?e=Gcjugg&download=1\"\n    unzip models.zip\n    ```\n    If the .zip file is not accessible, download it via browser. All checkpoints are about 25 GB in total. It may take some time to download. Alternatively, check our checkpoints at [huggingface](https:\u002F\u002Fhuggingface.co\u002FLiuZichen\u002FMagicQuill-models).\n    \n    Note: these can be located anywhere on the host computer, but Docker Compose expects them to be in `\u002Fdata\u002Fmagicquill\u002Fmodels` by default. Update `docker-compose.yaml` if you unzip them to another location.\n\n3. build the image\n   ```\n   docker compose build\n   ```\n\n4. run the image\n   ```\n   docker compose up -d\n   ```\n\n## Tutorial\n\nPlease read before you try!\n\n\u003C!DOCTYPE html>\n\u003Chtml>\n\u003Cbody>\n\u003Cdiv class=\"tutorial\">\u003Cdiv>\u003Ch3 align=\"center\" class=\"heading\">I. Three type of magic quills\u003C\u002Fh3>\u003Cdiv align=\"center\">\u003Cimg fill=\"white\" src=\"docs\u002Ficons\u002Fbrush_edge_add.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>Use the \u003Cb>add brush\u003C\u002Fb> to add details and elements guided by prompts - express your ideas with your own lively strokes!\u003Cbr>\u003C\u002Fdiv>\u003Cdiv class=\"ant-row css-1kuana8\">\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fdeer.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall>\"With just a few strokes, a vivid little deer comes to life\"\u003C\u002Fsmall>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fnecklace.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall> \"Adorn the beautiful lady with a necklace\"\u003C\u002Fsmall>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Fbrush_edge_remove.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>The \u003Cb>subtract brush\u003C\u002Fb> can remove excess details or redraw areas based on prompts. If there's anything you're not satisfied with, just subtract it away!\u003Cbr>\u003C\u002Fdiv>\u003Cdiv class=\"ant-row css-1kuana8\">\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fdolphin.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall> \"A dolphin with two tail fins? Let's give it a quick 'treatment'!\"\u003C\u002Fsmall>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fskeleton cowboy.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall> \"Let's take off Mr. Skeleton's hat and help him cool down.\"\u003C\u002Fsmall>\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv align=\"center\" style=\"display: flex; justify-content: center; align-items: center; gap: 10px;\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Fbrush_edge_add.svg\" alt=\"add brush\" class=\"icon\" width=\"100\">\u003Cspan>&\u003C\u002Fspan>\u003Cimg src=\"docs\u002Ficons\u002Fbrush_edge_remove.svg\" alt=\"minus brush\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>Combine the \u003Cb>add and subtract brushes\u003C\u002Fb> to create amazing combo effects!\u003Cbr>\u003C\u002Fdiv>\u003Cdiv class=\"ant-row css-1kuana8\">\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fmona lisa cat.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall> \"Let's give Mona Lisa a pet cat~\"\u003C\u002Fsmall>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fhandsome bowtie.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall> \"Let's give this handsome fellow a new tie!\"\u003C\u002Fsmall>\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cimg src=\"docs\u002Ficons\u002Fbrush.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>The \u003Cb>color brush\u003C\u002Fb> can precisely color the image, matching the color of your brush~\u003Cbr>\u003C\u002Fdiv>\u003Cdiv class=\"ant-row css-1kuana8\">\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fbeautiful hair.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall>\"Precise color highlighting - paint exactly where you want to color\"\u003C\u002Fsmall>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fcake flowers.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall> \"Don't you think the blue flowers look more dreamy than the pink ones?\"\u003C\u002Fsmall>\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Cdiv align=\"center\">*Please note the color brush and add&subtract brush are mutually exclusive - you can only use one at a time!\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003Chr>\u003Ch3 align=\"center\" class=\"heading\">II. Draw and Guess\u003C\u002Fh3>\u003Cdiv align=\"center\">\u003Cimg src=\"docs\u002Ficons\u002Fwand.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">Our brush is super smart! Look at the examples above - as soon as you finish drawing, it quickly guesses what you want to create and fills in the prompts for you~ Sometimes it might guess wrong though, so feel free to tell it what you actually want to draw~\u003Cbr>\u003C\u002Fdiv>\u003Cdiv class=\"ant-row ant-row-center css-1kuana8\">\u003Cdiv class=\"ant-col ant-col-xs-24 ant-col-md-12 css-1kuana8\">\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg width=\"300\" src=\"docs\u002Fgifs\u002Fpath.gif\" alt=\"gif description\" class=\"gif\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Csmall> \"Oops! I don't want to draw a vine, I want to create a path!\"\u003C\u002Fsmall>\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003C\u002Fdiv>\u003Chr>\u003Ch3 align=\"center\" class=\"heading\">III. Super useful canvas tools!\u003C\u002Fh3>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Fupload.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">Click this button to upload the photo you want to edit~\u003Cbr>\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Feraser.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">Made a mistake with the brush? Just erase it with the rubber tool!\u003Cbr>\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Fcursor.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">Drag, rotate, and resize your strokes with the cursor - just like when you're working in PowerPoint!\u003Cbr>\u003C\u002Fdiv>\u003Cbr>\u003Cdiv align=\"center\" style=\"display: flex; justify-content: center; align-items: center; gap: 10px;\">\u003Cimg src=\"docs\u002Ficons\u002Fundo.svg\" alt=\"add brush\" class=\"icon\" width=\"100\">\u003Cspan>&\u003C\u002Fspan>\u003Cimg src=\"docs\u002Ficons\u002Fredo.svg\" alt=\"minus brush\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">Left is ctrl+z, right is ctrl+y - you know what that means! 😊\u003Cbr>And for Mac users, left is command+z, right is command+shift+z! 😝\u003Cbr>\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Fdelete.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">Oops! That doesn't look right 😵 - click this trash bin to delete the stroke\u003Cbr>\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Feye.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">The brush strokes are in my way, how can I see the image😡?! Try clicking this button to temporarily hide your strokes\u003Cbr>\u003C\u002Fdiv>\u003Cbr>\u003Cdiv align=\"center\" style=\"display: flex; justify-content: center; align-items: center; gap: 10px;\">\u003Cimg src=\"docs\u002Ficons\u002Faccept.svg\" alt=\"add brush\" class=\"icon\" width=\"100\">\u003Cspan>&\u003C\u002Fspan>\u003Cimg src=\"docs\u002Ficons\u002Fdiscard.svg\" alt=\"minus brush\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">These two icons will appear after the image is generated...\u003Cbr>I love this generated image 😍, I want to keep editing! ➡️ Click ✅ to continue editing\u003Cbr>What is this thing 😡, I don't want to see it! ➡️ Click ❎ to discard the result\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003Chr>\u003Ch3 align=\"center\" class=\"heading\">IV. Notes\u003C\u002Fh3>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Floading.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">When you see the spinning icon in the bottom left corner, it means the magicquill is still charging up 💪 Wait for it to disappear before clicking the Run button!\u003Cbr>\u003C\u002Fdiv>\u003Cdiv align=\"center\">\u003Cbr>\u003Cimg src=\"docs\u002Ficons\u002Fwand.svg\" alt=\"SVG image\" class=\"icon\" width=\"100\">\u003C\u002Fdiv>\u003Cdiv align=\"center\">When the magic wand is flashing, our brush is working hard to guess what you're trying to draw 🤔 Please be patient! 🙏\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003Chr>\u003Ch3 align=\"center\" class=\"heading\">V. Parameters\u003C\u002Fh3>\u003Cdiv align=\"center\">If you've made it here, you must really love our work! 😍\u003Cbr>If you want to learn how to better control the generation results, don't miss this section! 😘\u003Cbr>Next to the Run button, you can select parameters to modify advanced settings 🧐\u003Cbr>\u003Cbr>\u003C\u002Fdiv>\u003Cdiv>\u003Cul>\u003Cli>\u003Cu>Base Model Name\u003C\u002Fu>: Users can adjust this to select appropriate base models for different editing styles\u003Cul>\u003Cli>\u003Ca href=\"https:\u002F\u002Fcivitai.com\u002Fmodels\u002F4201\u002Frealistic-vision-v60-b1\">SD1.5\u002FrealisticVisionV60B1_v51VAE.safetensors\u003C\u002Fa>: This generates realistic style images! Use this most of the time.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fcivitai.com\u002Fmodels\u002F4384?modelVersionId=128713\">SD1.5\u002FDreamShaper.safetensors\u003C\u002Fa>: This one is for generating fantasy style images\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fcivitai.com\u002Fmodels\u002F43331\u002Fmajicmix-realistic\">SD1.5\u002FmajicMIX_realistic\u003C\u002Fa>: This one is good at generating portraits 👩\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fcivitai.com\u002Fmodels\u002F7240?modelVersionId=948574\">SD1.5\u002FMeinaMix.safetensors\u003C\u002Fa>: This one is good at generating anime images.\u003C\u002Fli>\u003Cli>\u003Ca href=\"https:\u002F\u002Fcivitai.com\u002Fmodels\u002F36520\u002Fghostmix\">SD1.5\u002Fghostmix_v20Bakedvae.safetensors\u003C\u002Fa>: Another model for anime image generation.\u003C\u002Fli>\u003Cli>If there are any models you'd like to add, contact us!\u003C\u002Fli>\u003C\u002Ful>\u003C\u002Fli>\u003Cli>\u003Cu>Negative Prompt\u003C\u002Fu>: Users can input content they want the model to avoid generating. Whatever you don't want to generate, put it here.\u003C\u002Fli>\u003Cli>\u003Cu>Fine Edge\u003C\u002Fu>: Users can enable this option to activate fine edge control.\u003C\u002Fli>\u003Cli>\u003Cu>Grow Size\u003C\u002Fu>: Adjust this parameter to set the pixel range affected around brush strokes when editing images, to expand\u002Freduce the brush stroke influence area.\u003C\u002Fli>\u003Cli>\u003Cu>Edge Strength\u003C\u002Fu>: Parameter for adjusting the add\u002Fsubtract brush control strength. Simply put, if you're confident in your drawing skills, you can increase strength. If you're a bad drawer like us 🤦, please keep the parameter as is, or reduce the strength a bit.\u003C\u002Fli>\u003Cli>\u003Cu>Color Strength\u003C\u002Fu>: Parameter for adjusting the color brush control strength, can adjust the image's coloring effects.\u003C\u002Fli>\u003Cli>The remaining parameters are just some common parameters for diffusion models! You basically don't need to manage these, but if you're in the industry\u002FAI art expert, feel free to try adjusting them.\u003C\u002Fli>\u003C\u002Ful>\u003C\u002Fdiv>\n\u003C\u002Fbody>\n\u003C\u002Fhtml>\n\n## Citation\nDon't forget to cite this source if it proves useful in your research!\n```bibtex\n@article{liu2024magicquill, \n\ttitle={MagicQuill: An Intelligent Interactive Image Editing System}, \n\tauthor={Zichen Liu and Yue Yu and Hao Ouyang and Qiuyu Wang and Ka Leong Cheng and Wen Wang and Zhiheng Liu and Qifeng Chen and Yujun Shen}, \n\tyear={2024}, \n\teprint={2411.09703}, \n\tarchivePrefix={arXiv}, \n\tprimaryClass={cs.CV}}\n```\n\n## Acknowledgement\nOur implementation is based on \n- [ComfyUI-BrushNet](https:\u002F\u002Fgithub.com\u002Fnullquant\u002FComfyUI-BrushNet)\n- [ComfyUI](https:\u002F\u002Fgithub.com\u002Fcomfyanonymous\u002FComfyUI)\n- [LLaVA](https:\u002F\u002Fgithub.com\u002Fhaotian-liu\u002FLLaVA)\n- [comfyui_controlnet_aux](https:\u002F\u002Fgithub.com\u002FFannovel16\u002Fcomfyui_controlnet_aux)\n- [ComfyUI_Custom_Nodes_AlekPet](https:\u002F\u002Fgithub.com\u002FAlekPet\u002FComfyUI_Custom_Nodes_AlekPet)\n- [fabric.js](https:\u002F\u002Fgithub.com\u002Ffabricjs\u002Ffabric.js)\n\nThanks for their remarkable contribution and released code!\n\n## Note\nNote: This repo is governed by the license of CC BY-NC 4.0 We strongly advise users not to knowingly generate or allow others to knowingly generate harmful content, including hate speech, violence, pornography, deception, etc. \n\n(注：本仓库受CC BY-NC的许可协议限制。我们强烈建议，用户不应传播及不应允许他人传播以下内容，包括但不限于仇恨言论、暴力、色情、欺诈相关的有害信息。)\n","MagicQuill 是一个智能交互式图像编辑系统，旨在实现精确的图像编辑。其核心功能包括用户友好的界面、AI 驱动的建议以及精准的局部编辑能力。项目使用 Python 语言开发，并通过 Gradio 提供了易于使用的 Web 界面。MagicQuill 适用于需要高质量图像编辑的应用场景，如专业设计、创意内容制作和个人照片处理等。此外，该项目还提供了 Docker 容器和详细的设置教程，方便开发者快速上手和部署。","2026-06-11 03:40:59","high_star"]