chaiNNerΒΆ

  1. Get chaiNNer-windows-x64-**.zip from Releases.

  2. Decompress .zip to chaiNNer\.

  3. Download cpython-3.11.5+20230826-x86_64-pc-windows-msvc-shared-install_only.tar.gz from integratedPython.ts[1].

  4. Decompress .tar.gz to python\.

  5. Put python\ into chaiNNer\python\.

Enable model architecture supportΒΆ

cd chaiNNer\python\python
# pytorch
python -m pip install torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu121
python -m pip install facexlib==0.3.0 einops==0.6.1 safetensors==0.4.0 spandrel==0.3.4 spandrel-extra-arches==0.1.1
# ncnn
python -m pip install ncnn==2023.6.18
# onnx
python -m pip install onnx==1.16.0 onnxoptimizer==0.3.13 onnxruntime-gpu==1.17.1 protobuf==4.24.2

  1. Get PyTorch models from Model Architecture Support or get ONNX model from Model Architecture Support. Or find models in multiple formats on OpenModelDB.

  2. Or you can convert PyTorch model to ONNX, NCNN model in chaiNNer.

  3. chaiNNer β†’ Manage Dependencies β†’ Packages β†’ PyTorch, ONNX, NCNN β†’ Install

  4. Restart chaiNNer.

  5. Usage with LOAD MODEL node and corresponding node for PROCESSING.

ReferenceΒΆ