GA666666

> --no-gradio-queue This works for me, thank you.

I'm waiting for this too.

> [非 fp16 模型的](https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128.onnx)性能更好（尽管仍然不稳定）[](https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128.onnx) There is indeed an improvement in the frame rate, but it still does not reach a smooth speed. For this model, why is version 32 faster...

Using a 32-bit ONNX model increases the inference speed to 15fps, primarily because onnxruntime doesn't yet fully support Apple's M-series chips. 1. You can refer to this repository: [Deep-Live-Cam](https://github.com/gongzhang/Deep-Live-Cam/blob/main/README.macos.md). 2....