the-database

Here is the image I was using, zipped to make sure the image file is untouched by github. [GAvGRBhaUAApWr3.zip](https://github.com/chaiNNer-org/chaiNNer/files/14354952/GAvGRBhaUAApWr3.zip) If I load this image into chaiNNer and then save it...

I wrote a plugin to help with this, but it's still a work in progress and doesn't work perfectly yet. This Lua script disables upscaling with the model during seek...

Thanks to everyone who has been sharing benchmarks, please keep them coming. Based on some of those results it seems like it might be useful to have another model with...

Thanks for sharing. I pushed some updates to the v2 branch based on your previous comments to increase its flexibility. The format of the conf file has been completely redone...

> Tried to benchmark but failed. (I still lack knowledge of coding. I tried pressing "all.bat" but there was no response and I didn't understand where to fix the 'video_path'...

I see what you're saying. Maybe this can be handled using a new `resize_resolution_before_upscale` option, which would behave similarly to some of your suggestions. I'm not sure about the name...

Thanks for sharing this. With V2 I have been working on making everything more easily configurable, but this demonstrates a use case I didn't consider. I'll see if I can...

Update your NVIDIA driver to the latest version and try again.

If you have Intel, change the Upscaling Backend from TensorRT to DirectML or NCNN. Also update the ONNX Model Path and select a model which is fp32.

Good idea, this is worth exploring. If we can convert pth to fp32 ONNX on the fly with PyTorch CPU, and vs-mlrt can further convert fp32 to fp16 on the...