You can check the performance of model with models/my_model/noise1_best.png. Conversely speaking, there is no effect unless it is expanded to a considerable size), Fixed a bug that input path might not be recognized when launching by passing command line option in GUI, Update Caffe (corresponds to cuDNN v5 RC), Corresponds to command line options with GUI, Separate option settings in separate windows with GUI, Added behavior setting when file is specified as argument in GUI, Add output file overwrite prohibition setting by GUI, Added initial directory setting when pressing reference button in GUI, Improved so that you can select files and folders at the same time in the window when input reference button is pressed in GUI, Fixed a bug that forced termination occurred with 16 bit output, Added check on whether GUI is Compute Capability 2.0 or higher device, If the size of the enlarged image exceeds 3 GB, data is written to a temporary file so as to take measures against memory shortage, Update model of anime_style_art (Y direction), Added ability to change the size of the dialog displayed by GUI reference button, Fixed a bug that CUI did not start (change the shortcut option for help display to "-? If you insert dll while software is running, please restart the software. Watch 271 Star 5.3k Fork 641 Code; Issues 69; Pull requests 0; ... waifu2x was closed when i dropped the file in, i also logged out and back in. Add noise reduction level 0 and make it the default level. GUI supports English, Japanese, Simplified Chinese, Traditional Chinese, Korean, Turkish, Spanish, Russian, and French. You can try another waifu2x converter that supports OpenCL and SIMD optimization. Waifu2x Caffe rewrites only the conversion function of the image conversion software "waifu2x" using Caffe and is software developed for Windows. You should use noise free images. The program will run on most modern PCs, although it will perform better if you have a speedy processor and/or video card (also called a GPU). You can check the performance of model with models/my_model/scale2.0x_best.png. 2.25x scaling would be perfect for 480p -> 1080p. You can read more for yourself here: Hopefully on Nvidia’s side they decide to bring full driver support backported to at least Pascal and at most Maxwell. what am i doing wrong this time??? Update waifu2x-caffe library to 1.1.6. cuDNN is a library for high-speed machine learning which can be used only with NVIDIA GPUs. The whole entire DirectML and DXR framework are a thing that isn’t really locked to hardware. Press question mark to learn the rest of the keyboard shortcuts.