{"id":13399969,"url":"https://github.com/danielgatis/rembg","last_synced_at":"2025-05-12T18:28:36.011Z","repository":{"id":37357181,"uuid":"286500101","full_name":"danielgatis/rembg","owner":"danielgatis","description":"Rembg is a tool to remove images background","archived":false,"fork":false,"pushed_at":"2025-04-25T11:49:49.000Z","size":73032,"stargazers_count":18817,"open_issues_count":10,"forks_count":1998,"subscribers_count":154,"default_branch":"main","last_synced_at":"2025-05-05T11:18:32.688Z","etag":null,"topics":["background-removal","image-processing","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/danielgatis.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null},"funding":{"github":["danielgatis"],"custom":["https://www.buymeacoffee.com/danielgatis"]}},"created_at":"2020-08-10T14:38:24.000Z","updated_at":"2025-05-05T07:34:19.000Z","dependencies_parsed_at":"2023-01-31T06:00:40.917Z","dependency_job_id":"2104a665-1466-4454-979c-85179418ccf6","html_url":"https://github.com/danielgatis/rembg","commit_stats":{"total_commits":337,"total_committers":56,"mean_commits":6.017857142857143,"dds":0.3115727002967359,"last_synced_commit":"95b81143c9a1d760c892ffa7f406f055fc244b81"},"previous_names":[],"tags_count":68,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgatis%2Frembg","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgatis%2Frembg/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgatis%2Frembg/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgatis%2Frembg/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/danielgatis","download_url":"https://codeload.github.com/danielgatis/rembg/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252524783,"owners_count":21762165,"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":["background-removal","image-processing","python"],"created_at":"2024-07-30T19:00:45.813Z","updated_at":"2025-05-12T18:28:35.985Z","avatar_url":"https://github.com/danielgatis.png","language":"Python","readme":"# Rembg\n\n[![Downloads](https://img.shields.io/pypi/dm/rembg.svg)](https://img.shields.io/pypi/dm/rembg.svg)\n[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://img.shields.io/badge/License-MIT-blue.svg)\n[![Hugging Face Spaces](https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/KenjieDec/RemBG)\n[![Streamlit App](https://img.shields.io/badge/🎈%20Streamlit%20Community-Cloud-blue)](https://bgremoval.streamlit.app/)\n\nRembg is a tool to remove images background.\n\n\u003cp style=\"display: flex;align-items: center;justify-content: center;\"\u003e\n  \u003cimg alt=\"example car-1\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/car-1.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example car-1.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/car-1.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example car-2\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/car-2.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example car-2.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/car-2.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example car-3\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/car-3.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example car-3.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/car-3.out.png\" width=\"100\" /\u003e\n\u003c/p\u003e\n\n\u003cp style=\"display: flex;align-items: center;justify-content: center;\"\u003e\n  \u003cimg alt=\"example animal-1\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/animal-1.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example animal-1.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/animal-1.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example animal-2\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/animal-2.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example animal-2.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/animal-2.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example animal-3\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/animal-3.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example animal-3.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/animal-3.out.png\" width=\"100\" /\u003e\n\u003c/p\u003e\n\n\u003cp style=\"display: flex;align-items: center;justify-content: center;\"\u003e\n  \u003cimg alt=\"example girl-1\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/girl-1.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example girl-1.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/girl-1.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example girl-2\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/girl-2.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example girl-2.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/girl-2.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example girl-3\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/girl-3.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example girl-3.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/girl-3.out.png\" width=\"100\" /\u003e\n\u003c/p\u003e\n\n\u003cp style=\"display: flex;align-items: center;justify-content: center;\"\u003e\n  \u003cimg alt=\"example anime-girl-1\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/anime-girl-1.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example anime-girl-1.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/anime-girl-1.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example anime-girl-2\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/anime-girl-2.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example anime-girl-2.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/anime-girl-2.out.png\" width=\"100\" /\u003e\n  \u003cimg alt=\"example anime-girl-3\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/anime-girl-3.jpg\" width=\"100\" /\u003e\n  \u003cimg alt=\"example anime-girl-3.out\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/examples/anime-girl-3.out.png\" width=\"100\" /\u003e\n\u003c/p\u003e\n\n**If this project has helped you, please consider making a [donation](https://www.buymeacoffee.com/danielgatis).**\n\n## Sponsors\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd align=\"center\" vertical-align=\"center\"\u003e\n      \u003ca href=\"https://withoutbg.com/?utm_source=rembg\u0026utm_medium=github_readme\u0026utm_campaign=sponsorship\" \u003e\n        \u003cimg src=\"https://withoutbg.com/images/logo-social.png\" width=\"120px;\" alt=\"withoutBG API Logo\" /\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd align=\"center\" vertical-align=\"center\"\u003e\n      \u003cb\u003ewithoutBG API\u003c/b\u003e\n      \u003cbr /\u003e\n      \u003ca href=\"https://withoutbg.com/?utm_source=rembg\u0026utm_medium=github_readme\u0026utm_campaign=sponsorship\"\u003ehttps://withoutbg.com\u003c/a\u003e\n      \u003cbr /\u003e\n      \u003cp width=\"200px\"\u003e\n      High-quality background removal API at affordable rates\n        \u003cbr/\u003e\n      \u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n \u003ctr\u003e\n    \u003ctd align=\"center\" vertical-align=\"center\"\u003e\n      \u003ca href=\"https://photoroom.com/api/remove-background?utm_source=rembg\u0026utm_medium=github_webpage\u0026utm_campaign=sponsor\" \u003e\n        \u003cimg src=\"https://font-cdn.photoroom.com/media/api-logo.png\" width=\"120px;\" alt=\"Unsplash\" /\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd align=\"center\" vertical-align=\"center\"\u003e\n      \u003cb\u003ePhotoRoom Remove Background API\u003c/b\u003e\n      \u003cbr /\u003e\n      \u003ca href=\"https://photoroom.com/api/remove-background?utm_source=rembg\u0026utm_medium=github_webpage\u0026utm_campaign=sponsor\"\u003ehttps://photoroom.com/api\u003c/a\u003e\n      \u003cbr /\u003e\n      \u003cp width=\"200px\"\u003e\n        Fast and accurate background remover API\u003cbr/\u003e\n      \u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n## Requirements\n\n```text\npython: \u003e=3.10, \u003c3.14\n```\n\n## Installation\n\nIf you have `onnxruntime` already installed, just install `rembg`:\n\n```bash\npip install rembg # for library\npip install \"rembg[cli]\" # for library + cli\n```\n\nOtherwise, install `rembg` with explicit CPU/GPU support.\n\n### CPU support:\n\n```bash\npip install rembg[cpu] # for library\npip install \"rembg[cpu,cli]\" # for library + cli\n```\n\n### GPU support:\n\nFirst of all, you need to check if your system supports the `onnxruntime-gpu`.\n\nGo to [onnxruntime.ai](\u003chttps://onnxruntime.ai/getting-started\u003e) and check the installation matrix.\n\n\u003cp style=\"display: flex;align-items: center;justify-content: center;\"\u003e\n  \u003cimg alt=\"onnxruntime-installation-matrix\" src=\"https://raw.githubusercontent.com/danielgatis/rembg/master/onnxruntime-installation-matrix.png\" width=\"400\" /\u003e\n\u003c/p\u003e\n\nIf yes, just run:\n\n```bash\npip install \"rembg[gpu]\" # for library\npip install \"rembg[gpu,cli]\" # for library + cli\n```\n\nNvidia GPU may require onnxruntime-gpu, cuda, and cudnn-devel. [#668](https://github.com/danielgatis/rembg/issues/668#issuecomment-2689830314) . If rembg[gpu] doesn't work and you can't install cuda or cudnn-devel, use rembg[cpu] and onnxruntime instead.\n\n## Usage as a cli\n\nAfter the installation step you can use rembg just typing `rembg` in your terminal window.\n\nThe `rembg` command has 4 subcommands, one for each input type:\n\n- `i` for files\n- `p` for folders\n- `s` for http server\n- `b` for RGB24 pixel binary stream\n\nYou can get help about the main command using:\n\n```shell\nrembg --help\n```\n\nAs well, about all the subcommands using:\n\n```shell\nrembg \u003cCOMMAND\u003e --help\n```\n\n### rembg `i`\n\nUsed when input and output are files.\n\nRemove the background from a remote image\n\n```shell\ncurl -s http://input.png | rembg i \u003e output.png\n```\n\nRemove the background from a local file\n\n```shell\nrembg i path/to/input.png path/to/output.png\n```\n\nRemove the background specifying a model\n\n```shell\nrembg i -m u2netp path/to/input.png path/to/output.png\n```\n\nRemove the background returning only the mask\n\n```shell\nrembg i -om path/to/input.png path/to/output.png\n```\n\nRemove the background applying an alpha matting\n\n```shell\nrembg i -a path/to/input.png path/to/output.png\n```\n\nPassing extras parameters\n\n```shell\nSAM example\n\nrembg i -m sam -x '{ \"sam_prompt\": [{\"type\": \"point\", \"data\": [724, 740], \"label\": 1}] }' examples/plants-1.jpg examples/plants-1.out.png\n```\n\n```shell\nCustom model example\n\nrembg i -m u2net_custom -x '{\"model_path\": \"~/.u2net/u2net.onnx\"}' path/to/input.png path/to/output.png\n```\n\n### rembg `p`\n\nUsed when input and output are folders.\n\nRemove the background from all images in a folder\n\n```shell\nrembg p path/to/input path/to/output\n```\n\nSame as before, but watching for new/changed files to process\n\n```shell\nrembg p -w path/to/input path/to/output\n```\n\n### rembg `s`\n\nUsed to start http server.\n\n```shell\nrembg s --host 0.0.0.0 --port 7000 --log_level info\n```\n\nTo see the complete endpoints documentation, go to: `http://localhost:7000/api`.\n\nRemove the background from an image url\n\n```shell\ncurl -s \"http://localhost:7000/api/remove?url=http://input.png\" -o output.png\n```\n\nRemove the background from an uploaded image\n\n```shell\ncurl -s -F file=@/path/to/input.jpg \"http://localhost:7000/api/remove\"  -o output.png\n```\n\n### rembg `b`\n\nProcess a sequence of RGB24 images from stdin. This is intended to be used with another program, such as FFMPEG, that outputs RGB24 pixel data to stdout, which is piped into the stdin of this program, although nothing prevents you from manually typing in images at stdin.\n\n```shell\nrembg b image_width image_height -o output_specifier\n```\n\nArguments:\n\n- image_width : width of input image(s)\n- image_height : height of input image(s)\n- output_specifier: printf-style specifier for output filenames, for example if `output-%03u.png`, then output files will be named `output-000.png`, `output-001.png`, `output-002.png`, etc. Output files will be saved in PNG format regardless of the extension specified. You can omit it to write results to stdout.\n\nExample usage with FFMPEG:\n\n```shell\nffmpeg -i input.mp4 -ss 10 -an -f rawvideo -pix_fmt rgb24 pipe:1 | rembg b 1280 720 -o folder/output-%03u.png\n```\n\nThe width and height values must match the dimension of output images from FFMPEG. Note for FFMPEG, the \"`-an -f rawvideo -pix_fmt rgb24 pipe:1`\" part is required for the whole thing to work.\n\n## Usage as a library\n\nInput and output as bytes\n\n```python\nfrom rembg import remove\n\ninput_path = 'input.png'\noutput_path = 'output.png'\n\nwith open(input_path, 'rb') as i:\n    with open(output_path, 'wb') as o:\n        input = i.read()\n        output = remove(input)\n        o.write(output)\n```\n\nInput and output as a PIL image\n\n```python\nfrom rembg import remove\nfrom PIL import Image\n\ninput_path = 'input.png'\noutput_path = 'output.png'\n\ninput = Image.open(input_path)\noutput = remove(input)\noutput.save(output_path)\n```\n\nInput and output as a numpy array\n\n```python\nfrom rembg import remove\nimport cv2\n\ninput_path = 'input.png'\noutput_path = 'output.png'\n\ninput = cv2.imread(input_path)\noutput = remove(input)\ncv2.imwrite(output_path, output)\n```\n\nForce output as bytes\n\n```python\nfrom rembg import remove\n\ninput_path = 'input.png'\noutput_path = 'output.png'\n\nwith open(input_path, 'rb') as i:\n    with open(output_path, 'wb') as o:\n        input = i.read()\n        output = remove(input, force_return_bytes=True)\n        o.write(output)\n```\n\nHow to iterate over files in a performatic way\n\n```python\nfrom pathlib import Path\nfrom rembg import remove, new_session\n\nsession = new_session()\n\nfor file in Path('path/to/folder').glob('*.png'):\n    input_path = str(file)\n    output_path = str(file.parent / (file.stem + \".out.png\"))\n\n    with open(input_path, 'rb') as i:\n        with open(output_path, 'wb') as o:\n            input = i.read()\n            output = remove(input, session=session)\n            o.write(output)\n```\n\nTo see a full list of examples on how to use rembg, go to the [examples](USAGE.md) page.\n\n## Usage as a docker\n\n### Only CPU\n\nJust replace the `rembg` command for `docker run danielgatis/rembg`.\n\nTry this:\n\n```shell\ndocker run -v path/to/input:/rembg danielgatis/rembg i input.png path/to/output/output.png\n```\n\n### Nvidia CUDA Hardware Acceleration\n\nRequirement: using CUDA in docker needs your **host** has **NVIDIA Container Toolkit** installed. [NVIDIA Container Toolkit Install Guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)\n\n**Nvidia CUDA Hardware Acceleration** needs cudnn-devel so you need to build the docker image by yourself. [#668](https://github.com/danielgatis/rembg/issues/668#issuecomment-2689914205)\n\nHere is a example shows you how to build an image and name it *rembg-nvidia-cuda-cudnn-gpu*\n```shell\ndocker build -t rembg-nvidia-cuda-cudnn-gpu -f Dockerfile_nvidia_cuda_cudnn_gpu .\n```\nBe aware: It would take 11GB of your disk space. (The cpu version only takes about 1.6GB). Models didn't included.\n\nAfter you build the image, run it like this as a cli\n```shell\nsudo docker run --rm -it --gpus all -v /dev/dri:/dev/dri -v $PWD:/rembg rembg-nvidia-cuda-cudnn-gpu i -m birefnet-general input.png output.png\n```\n\n- Trick 1: Actually you can also make up a nvidia-cuda-cudnn-gpu image and install rembg[gpu, cli] in it.\n- Trick 2: Try param `-v /somewhereYouStoresModelFiles/:/root/.u2net` so to download/store model files out of docker images. You can even comment the line `RUN rembg d u2net` so when builing the image, it download will no models, so you can download the specific model you want even without the default u2net model.\n\n## Models\n\nAll models are downloaded and saved in the user home folder in the `.u2net` directory.\n\nThe available models are:\n\n- u2net ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net.onnx), [source](https://github.com/xuebinqin/U-2-Net)): A pre-trained model for general use cases.\n- u2netp ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2netp.onnx), [source](https://github.com/xuebinqin/U-2-Net)): A lightweight version of u2net model.\n- u2net_human_seg ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net_human_seg.onnx), [source](https://github.com/xuebinqin/U-2-Net)): A pre-trained model for human segmentation.\n- u2net_cloth_seg ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net_cloth_seg.onnx), [source](https://github.com/levindabhi/cloth-segmentation)): A pre-trained model for Cloths Parsing from human portrait. Here clothes are parsed into 3 category: Upper body, Lower body and Full body.\n- silueta ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/silueta.onnx), [source](https://github.com/xuebinqin/U-2-Net/issues/295)): Same as u2net but the size is reduced to 43Mb.\n- isnet-general-use ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/isnet-general-use.onnx), [source](https://github.com/xuebinqin/DIS)): A new pre-trained model for general use cases.\n- isnet-anime ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/isnet-anime.onnx), [source](https://github.com/SkyTNT/anime-segmentation)): A high-accuracy segmentation for anime character.\n- sam ([download encoder](https://github.com/danielgatis/rembg/releases/download/v0.0.0/vit_b-encoder-quant.onnx), [download decoder](https://github.com/danielgatis/rembg/releases/download/v0.0.0/vit_b-decoder-quant.onnx), [source](https://github.com/facebookresearch/segment-anything)): A pre-trained model for any use cases.\n- birefnet-general ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/BiRefNet-general-epoch_244.onnx), [source](https://github.com/ZhengPeng7/BiRefNet)): A pre-trained model for general use cases.\n- birefnet-general-lite ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/BiRefNet-general-bb_swin_v1_tiny-epoch_232.onnx), [source](https://github.com/ZhengPeng7/BiRefNet)): A light pre-trained model for general use cases.\n- birefnet-portrait ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/BiRefNet-portrait-epoch_150.onnx), [source](https://github.com/ZhengPeng7/BiRefNet)): A pre-trained model for human portraits.\n- birefnet-dis ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/BiRefNet-DIS-epoch_590.onnx), [source](https://github.com/ZhengPeng7/BiRefNet)): A pre-trained model for dichotomous image segmentation (DIS).\n- birefnet-hrsod ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/BiRefNet-HRSOD_DHU-epoch_115.onnx), [source](https://github.com/ZhengPeng7/BiRefNet)): A pre-trained model for high-resolution salient object detection (HRSOD).\n- birefnet-cod ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/BiRefNet-COD-epoch_125.onnx), [source](https://github.com/ZhengPeng7/BiRefNet)): A pre-trained model for concealed object detection (COD).\n- birefnet-massive ([download](https://github.com/danielgatis/rembg/releases/download/v0.0.0/BiRefNet-massive-TR_DIS5K_TR_TEs-epoch_420.onnx), [source](https://github.com/ZhengPeng7/BiRefNet)): A pre-trained model with massive dataset.\n\n### How to train your own model\n\nIf You need more fine tuned models try this:\n\u003chttps://github.com/danielgatis/rembg/issues/193#issuecomment-1055534289\u003e\n\n## Some video tutorials\n\n- \u003chttps://www.youtube.com/watch?v=3xqwpXjxyMQ\u003e\n- \u003chttps://www.youtube.com/watch?v=dFKRGXdkGJU\u003e\n- \u003chttps://www.youtube.com/watch?v=Ai-BS_T7yjE\u003e\n- \u003chttps://www.youtube.com/watch?v=D7W-C0urVcQ\u003e\n\n## References\n\n- \u003chttps://arxiv.org/pdf/2005.09007.pdf\u003e\n- \u003chttps://github.com/NathanUA/U-2-Net\u003e\n- \u003chttps://github.com/pymatting/pymatting\u003e\n\n## FAQ\n\n### When will this library provide support for Python version 3.xx?\n\nThis library directly depends on the [onnxruntime](https://pypi.org/project/onnxruntime) library. Therefore, we can only update the Python version when [onnxruntime](https://pypi.org/project/onnxruntime) provides support for that specific version.\n\n## Buy me a coffee\n\nLiked some of my work? Buy me a coffee (or more likely a beer)\n\n\u003ca href=\"https://www.buymeacoffee.com/danielgatis\" target=\"_blank\"\u003e\u003cimg src=\"https://bmc-cdn.nyc3.digitaloceanspaces.com/BMC-button-images/custom_images/orange_img.png\" alt=\"Buy Me A Coffee\" style=\"height: auto !important;width: auto !important;\"\u003e\u003c/a\u003e\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=danielgatis/rembg\u0026type=Date)](https://star-history.com/#danielgatis/rembg\u0026Date)\n\n## License\n\nCopyright (c) 2020-present [Daniel Gatis](https://github.com/danielgatis)\n\nLicensed under [MIT License](./LICENSE.txt)\n","funding_links":["https://github.com/sponsors/danielgatis","https://www.buymeacoffee.com/danielgatis","https://www.buymeacoffee.com/danielgatis)."],"categories":["Background Removal","Python","✂️ Image segmentation","抠图/补图","HarmonyOS","其他_机器视觉","语言资源库","Uncategorized","Zeichnen"],"sub_categories":["Software tools","特效/实用工具","Windows Manager","网络服务_其他","python","Uncategorized"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielgatis%2Frembg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdanielgatis%2Frembg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielgatis%2Frembg/lists"}