(Image from https://github.com/xinntao/Real-ESRGAN/tree/master/inputs/ADE_val_00000114.jpg)
(Image from https://github.com/xinntao/Real-ESRGAN/blob/master/inputs/0030.jpg)
Ailia input shape: (1, 3, 256, 256)
Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.
For the sample image,
$ python3 real_esrgan.py
You can also use an anime-specific super-resolution model by adding the -m RealESRGAN_anime or RealESRGAN_anime_v3 option.
$ python3 real_esrgan.py -m RealESRGAN_anime -i input_anime.jpg -s output_anime.jpg
If you want to specify the input image, put the image path after the --input
option.
You can use --savepath
option to change the name of the output file to save.
$ python3 real-esrgan.py --input IMAGE_PATH --savepath SAVE_IMAGE_PATH
By adding the --video
option, you can input the video.
If you pass 0
as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.
$ python3 real_esrgan.py --video VIDEO_PATH
Pytorch
ONNX opset = 12