Dowon
https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/964 forge has changed the import policy for checkpoints, so changing checkpoints during generation no longer works.
It's not uncommon for machine learning models to fail to predict. Try sending them to the img2img tab and inpainting them yourself.
The YOLO model's filename shows what it predicts. If we support selecting certain classes, how does the user know which class names are supported by their YOLO model? I tried...
Windowsで、pytorch 2.4.0バージョンを使っていて、cpuで推論するときにこの問題が発生します。 pytorchのバージョンを変更してください。 https://github.com/Bing-su/adetailer/issues/693
현재 최신버전인 v8.3.221에서도 정상 동작함을 확인했습니다.
Try reinstalling venv.
Your idea is awesome, let's just review a few things and merge it.
Before merge it, could you write a paragraph describing each features? I'm not a very good writer.
First, this is an issue that should be reported to https://github.com/Gourieff/sd-webui-reactor. Second, according to onnxruntime's [documentation](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), the onnxruntime-gpu package that you install with pip expects CUDA version 11.8. Please follow...