CivArchive
    ← All articles
    Published August 11, 2024by SECourses

    BiRefNet State Of The Art Newest Very Best Background Batch Remover APP

    563 views5 reactions2 comments on CivitAI9 collected
    tool guide

    BiRefNet State Of The Art Newest Very Best Background Batch Remover APP. BiRefNet is the very best state of the art newest published background removal open source model. It is way better than BRIA RMBG V1.4 that we knew as best.

    Official repo : https://github.com/ZhengPeng7/BiRefNet

    -

    Download APP and installers from : https://www.patreon.com/posts/109913645

    -

    Hugging Face Demo : https://huggingface.co/spaces/ZhengPeng7/BiRefNet_demo

    I have developed a very advanced Gradio APP for this with full proper file saving and batch processing. Also my version removes BG and saves as transparent background.

    The APP uses huge VRAM for high resolution images. However it is still working uber fast even though using shared VRAM. So make sure that you have high RAM or set virtual RAM.

    Click below to see how to set virtual RAM on Windows.

    https://www.windowscentral.com/how-change-virtual-memory-size-windows-10

    On Massed Compute A6000 GPU (31 cents per hour) you can very fast remove even very high res images backgrounds.

    Currently we have 1 click installers for RunPod, Massed Compute, Kaggle and Windows.

    Windows Requirements

    Python 3.10, FFmpeg, Cuda 11.8, C++ tools and Git

    If it doesn’t work make sure to below tutorial and install everything exactly as shown in this below tutorial

    How To Use On Windows

    Just extract files into like c:/BiRefNet_v1

    Double click Windows_Install.bat file and it will generate a isolated virtual environment and install requirements

    It will automatically download models into your Hugging Face cache (best model under 1 GB)

    Then start and use the Gradio APP with Windows_Start_App.bat

    Cloud How To Use

    Massed Compute, RunPod has instructions txt files. Follow them

    Kaggle has all the instructions 1 by 1

    On Kaggle set resolution 1024x1024 or you will get out of memory error