rwfsmith
rwfsmith
I follow the steps on here and it works for me https://github.com/casper-hansen/AutoAWQ/issues/704
I get the same issue with my Ayn Thor with Rune Factory 4 (the only game I've tried so far), changing this setting doesn't seem to help.
I'm getting the same thing on Windows, so I did this: pip install onnx pip install onnx_tool pip install flask then it worked.
Yeah, I'm not sure which file it can't find.
Yeah, there does not seem to be any pre-built wheels for torch 2.8.0, so you might need to build it from scratch. You can update the dependencies in "custom_nodes\ComfyUI-3D-Pack\_Pre_Builds\_Build_Scripts\build_config.yaml" with...
You generally want to train in the original accuracy then quantize it later. That being said, the Nunchaku quantization doesn't seem to perform well below 80GB of VRAM without a...
I hit the same problem during VAE decode on my 5090 if I try to run the native 1080p upscale workflow from the default templates.