diff --git a/Model-Conversion-Guide.md b/Model-Conversion-Guide.md index 48c3bca..3806898 100644 --- a/Model-Conversion-Guide.md +++ b/Model-Conversion-Guide.md @@ -4,7 +4,7 @@ This guide explains how you can convert PyTorch models to NCNN models for Upscay > Only PyTorch models for ESRGAN are guaranteed to work. You can use a similar process for ONNX models (use onnxsim to simplify the model, install ONNX in dependencies and replace the orange blocks with their cyan equivalents), but it can often fail. ## Prerequisites -- [chaiNNer](https://github.com/chaiNNer-org/chaiNNer) (note that versions >= 0.21.1 may not be compatible for now) +- [chaiNNer](https://github.com/chaiNNer-org/chaiNNer/releases/tag/v0.21.0) (Versions after v0.21.0 seem to not work) - [This .chn file](https://gist.github.com/aaronliu0130/38b996f360dfee86d71130f129920f3a/raw/f06e711e03a4a239e6dc041fadf890a26fdd979a/pth2bin.chn). Right click the link, click "Save link as" and save it wherever you want. - A model in PyTorch (.pth) format. This guide is for converting PyTorch to NCNN (Upscayl's format) only. - You can get models from .