Repository files navigation

Rembg is a tool to remove images background.

If this project has helped you, please consider making adonation.

PhotoRoom Remove Background API https://photoroom.com/api Fast and accurate background remover API

python: >=3.10, <3.14

If you haveonnxruntime already installed, just installrembg:

pip install rembg# for librarypip install"rembg[cli]"# for library + cli

Otherwise, installrembg with explicit CPU/GPU support.

pip install rembg[cpu]# for librarypip install"rembg[cpu,cli]"# for library + cli

First of all, you need to check if your system supports theonnxruntime-gpu.

Go toonnxruntime.ai and check the installation matrix.

If yes, just run:

pip install"rembg[gpu]"# for librarypip install"rembg[gpu,cli]"# for library + cli

Nvidia GPU may require onnxruntime-gpu, cuda, and cudnn-devel.#668 . If rembg[gpu] doesn't work and you can't install cuda or cudnn-devel, use rembg[cpu] and onnxruntime instead.

ROCM support requires theonnxruntime-rocm package. Install it followingAMD's documentation.

Ifonnxruntime-rocm is installed and working, install therembg[rocm]version of rembg:

pip install"rembg[rocm]"# for librarypip install"rembg[rocm,cli]"# for library + cli

After the installation step you can use rembg just typingrembg in your terminal window.

Therembg command has 4 subcommands, one for each input type:

• i for files
• p for folders
• s for http server
• b for RGB24 pixel binary stream

You can get help about the main command using:

rembg --help

As well, about all the subcommands using:

rembg<COMMAND> --help

Used when input and output are files.

Remove the background from a remote image

curl -s http://input.png| rembg i> output.png

Remove the background from a local file

rembg i path/to/input.png path/to/output.png

Remove the background specifying a model

rembg i -m u2netp path/to/input.png path/to/output.png

Remove the background returning only the mask

rembg i -om path/to/input.png path/to/output.png

Remove the background applying an alpha matting

rembg i -a path/to/input.png path/to/output.png

Passing extras parameters

SAM examplerembg i -m sam -x'{ "sam_prompt": [{"type": "point", "data": [724, 740], "label": 1}] }' examples/plants-1.jpg examples/plants-1.out.png

Custom model examplerembg i -m u2net_custom -x'{"model_path": "~/.u2net/u2net.onnx"}' path/to/input.png path/to/output.png

Used when input and output are folders.

Remove the background from all images in a folder

rembg p path/to/input path/to/output

Same as before, but watching for new/changed files to process

rembg p -w path/to/input path/to/output

Used to start http server.

rembg s --host 0.0.0.0 --port 7000 --log_level info

To see the complete endpoints documentation, go to:http://localhost:7000/api.

Remove the background from an image url

curl -s"http://localhost:7000/api/remove?url=http://input.png" -o output.png

Remove the background from an uploaded image

curl -s -F file=@/path/to/input.jpg"http://localhost:7000/api/remove"  -o output.png

Process 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.

rembg b image_width image_height -o output_specifier

Arguments:

• image_width : width of input image(s)
• image_height : height of input image(s)
• output_specifier: printf-style specifier for output filenames, for example ifoutput-%03u.png, then output files will be namedoutput-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.

Example usage with FFMPEG:

ffmpeg -i input.mp4 -ss 10 -an -f rawvideo -pix_fmt rgb24 pipe:1| rembg b 1280 720 -o folder/output-%03u.png

The 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.

Input and output as bytes

fromrembgimportremoveinput_path='input.png'output_path='output.png'withopen(input_path,'rb')asi:withopen(output_path,'wb')aso:input=i.read()output=remove(input)o.write(output)

Input and output as a PIL image

fromrembgimportremovefromPILimportImageinput_path='input.png'output_path='output.png'input=Image.open(input_path)output=remove(input)output.save(output_path)

Input and output as a numpy array

fromrembgimportremoveimportcv2input_path='input.png'output_path='output.png'input=cv2.imread(input_path)output=remove(input)cv2.imwrite(output_path,output)

Force output as bytes

fromrembgimportremoveinput_path='input.png'output_path='output.png'withopen(input_path,'rb')asi:withopen(output_path,'wb')aso:input=i.read()output=remove(input,force_return_bytes=True)o.write(output)

How to iterate over files in a performatic way

frompathlibimportPathfromrembgimportremove,new_sessionsession=new_session()forfileinPath('path/to/folder').glob('*.png'):input_path=str(file)output_path=str(file.parent/ (file.stem+".out.png"))withopen(input_path,'rb')asi:withopen(output_path,'wb')aso:input=i.read()output=remove(input,session=session)o.write(output)

To see a full list of examples on how to use rembg, go to theexamples page.

Just replace therembg command fordocker run danielgatis/rembg.

Try this:

docker run -v path/to/input:/rembg danielgatis/rembg i input.png path/to/output/output.png

Requirement: using CUDA in docker needs yourhost hasNVIDIA Container Toolkit installed.NVIDIA Container Toolkit Install Guide

Nvidia CUDA Hardware Acceleration needs cudnn-devel so you need to build the docker image by yourself.#668

Here is a example shows you how to build an image and name itrembg-nvidia-cuda-cudnn-gpu

docker build -t rembg-nvidia-cuda-cudnn-gpu -f Dockerfile_nvidia_cuda_cudnn_gpu.

Be aware: It would take 11GB of your disk space. (The cpu version only takes about 1.6GB). Models didn't included.

After you build the image, run it like this as a cli

sudo 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

• Trick 1: Actually you can also make up a nvidia-cuda-cudnn-gpu image and install rembg[gpu, cli] in it.
• Trick 2: Try param-v /somewhereYouStoresModelFiles/:/root/.u2net so to download/store model files out of docker images. You can even comment the lineRUN rembg d u2net so when building the image, it download will no models, so you can download the specific model you want even without the default u2net model.

All models are downloaded and saved in the user home folder in the.u2net directory.

The available models are:

• u2net (download,source): A pre-trained model for general use cases.
• u2netp (download,source): A lightweight version of u2net model.
• u2net_human_seg (download,source): A pre-trained model for human segmentation.
• u2net_cloth_seg (download,source): A pre-trained model for Cloths Parsing from human portrait. Here clothes are parsed into 3 category: Upper body, Lower body and Full body.
• silueta (download,source): Same as u2net but the size is reduced to 43Mb.
• isnet-general-use (download,source): A new pre-trained model for general use cases.
• isnet-anime (download,source): A high-accuracy segmentation for anime character.
• sam (download encoder,download decoder,source): A pre-trained model for any use cases.
• birefnet-general (download,source): A pre-trained model for general use cases.
• birefnet-general-lite (download,source): A light pre-trained model for general use cases.
• birefnet-portrait (download,source): A pre-trained model for human portraits.
• birefnet-dis (download,source): A pre-trained model for dichotomous image segmentation (DIS).
• birefnet-hrsod (download,source): A pre-trained model for high-resolution salient object detection (HRSOD).
• birefnet-cod (download,source): A pre-trained model for concealed object detection (COD).
• birefnet-massive (download,source): A pre-trained model with massive dataset.

If You need more fine tuned models try this:#193 (comment)

• https://www.youtube.com/watch?v=3xqwpXjxyMQ
• https://www.youtube.com/watch?v=dFKRGXdkGJU
• https://www.youtube.com/watch?v=Ai-BS_T7yjE
• https://www.youtube.com/watch?v=D7W-C0urVcQ

• https://arxiv.org/pdf/2005.09007.pdf
• https://github.com/NathanUA/U-2-Net
• https://github.com/pymatting/pymatting

This library directly depends on theonnxruntime library. Therefore, we can only update the Python version whenonnxruntime provides support for that specific version.

Liked some of my work? Buy me a coffee (or more likely a beer)

Copyright (c) 2020-presentDaniel Gatis

Licensed underMIT License