Here's how I build Hybrids torch-addon:

# Base setup
* Create an empty Vapoursynth folder.
* Download portable Python (3.12)
https://www.python.org/ftp/python/3.12.8/python-3.12.8-embed-amd64.zip
* Download portable Vapoursynth
https://github.com/vapoursynth/vapoursynth/releases/download/R70/VapourSynth64-Portable-R70.zip
* Extract Python and then Vapoursynth into the Vapoursynth folder
* Change the content of the python312._pth to
  ```
  Scripts
  Lib\site-packages
  python312.zip
  .
  
  # Uncomment to run site.main() automatically
  #import site
  ```
* Install pip
 * Download the pip installer
   https://bootstrap.pypa.io/get-pip.py and move it into your Vapoursynth folder
 * Open a terminal inside the Vapoursynth and call  'python get-pip.py'
 
* Integrate Vapoursynth to the environment by calling 'python -m pip install wheel/VapourSynth-70-cp312-cp312-win_amd64.whl'

* Install vs-rife by calling:
  ```
  python -m pip install -U packaging setuptools wheel
  python -m pip install --pre -U torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu126
  python -m pip install --no-deps --pre -U torch_tensorrt --index-url https://download.pytorch.org/whl/nightly/cu126
  python -m pip install -U tensorrt-cu12 tensorrt-cu12_bindings tensorrt-cu12_libs --extra-index-url https://pypi.nvidia.com
  python -m pip install -U vsrife
  ```
* Install BasicVSR++
  `python -m pip install -U vsbasicvsrpp`
* Install DPIR
  ```
  python -m pip install -U vsdpir
  python -m vsdpir
  ```
* Install SCUNet
  ```
  python -m pip install -U vsscunet
  python -m vsscunet
  ```
* Install VSGAN
  ```
  python -m pip install -I vsgan
  ```
  (this downgrades numpy)
* Install REALEsrgan
  ```
  python -m pip install -U vsrealesrgan
  python -m vsrealesrgan
  ```
* Install HINet
  ```
  python -m pip install --upgrade vshinet
  ```
* Install AnimeSR
  ```
  python -m pip install -U vsanimesr
  ```
* Install FeMaSR
  ```
  python -m pip install -U vsfemasr
  ```
* Install CodeFormer
  ```
  python -m pip install -U vscodeformer
  python -m pip install https://github.com/eddiehe99/dlib-whl/raw/refs/heads/main/dlib-19.24.6-cp312-cp312-win_amd64.whl
  ```
* Install GRLIR
  ```
  python -m pip install -U vsgrlir
  ```   
* Install MFDIN
  ```
  python -m pip install -U vsmfdin
  ```   
* Install ProPainter
  ```
  python -m pip install https://github.com/dan64/vs-propainter/releases/download/v1.2.1/vspropainter-1.2.1-py3-none-any.whl
  ```   
* Install VSDDColor
  ```
  python -m pip install https://github.com/dan64/vs-deoldify/releases/download/v4.0.0/vsddcolor-1.0.1-py3-none-any.whl
  ```
* Install VSDDColor
  ```
  python -m pip install -U vsswinir
  ```
* Install GMFSS_Fortuna
  ```
  python -m pip install -U vsgmfss-fortuna
  ```
* Install DeOdify
  ```
  python -m pip install https://github.com/dan64/vs-deoldify/releases/download/v4.6.8/vsdeoldify-4.6.8-py3-none-any.whl
  ```
  * Download:
    * https://colorizers.s3.us-east-2.amazonaws.com/colorization_release_v2-9b330a0b.pth
    * https://colorizers.s3.us-east-2.amazonaws.com/siggraph17-df00044c.pth
    * https://data.deepai.org/deoldify/ColorizeArtistic_gen.pth
    * https://www.dropbox.com/s/axsd2g85uyixaho/ColorizeStable_gen.pth?dl=0
    * https://data.deepai.org/deoldify/ColorizeVideo_gen.pth
    and place them in the Vapoursynth/vsdeoldify/models-folder
    * https://github.com/zhangmozhe/Deep-Exemplar-based-Video-Colorization/releases/download/v1.0/colorization_checkpoint.zip
      and extract it into the Vapoursynth\Lib\site-packages\vsdeoldify\deepex
    * https://download.pytorch.org/models/resnet101-63fe2227.pth
    * https://download.pytorch.org/models/resnet50-19c8e357.pth
    * https://dl.fbaipublicfiles.com/dinov2/dinov2_vits14/dinov2_vits14_pretrain.pth
    and place them in the Vapoursynth\Lib\site-packages\vsdeoldify\deepex\checkpoints-folder
    * https://github.com/yyang181/colormnet/releases/download/v0.1/DINOv2FeatureV6_LocalAtten_s2_154000.pth 
    and place it into the Vapoursynth/Lib/site-packages/vsdeoldify/colormnet/weights-folder
  * install sparial_correlation_sampler (needs new build, see: https://forum.selur.net/thread-3595-post-25414.html#pid25414)
    extract content of spatial_correlation_sampler (open as an archive) into Vapoursynth\Lib\site-packages

* Download Models for the installed tools
  ```
  python -m vsrife
  python -m vsrealesrgan
  python -m vshinet
  python -m vsfemasr
  python -m vscodeformer
  python -m vsgrlir
  python -m vsddcolor
  python -m vsswinir
  ```


  
* Install DeepDeinterlace  (**fails due to openmim dependency**)
  Download https://github.com/pifroggi/vs_deepdeinterlace/archive/refs/heads/main.zip and place the vs_deepdeinterlace-folder (under vs_deepdeinterlace-main)  inside your Vapoursynth/Lib/site-packages folder
  ```
  python -m pip install positional_encodings
  python -m pip install -U openmim
  python -m mim install "mmcv>=2.0.0"
  ```