Pedro Coelho

@CrazyWolf13 I think it should be a simple change in `inference_gfpgan.py` from : ```python if args.bg_upsampler == 'realesrgan': if not torch.cuda.is_available(): # CPU import warnings warnings.warn('The unoptimized RealESRGAN is slow...

@hollowaykeanho For me this happens with videos and only on `-scale 2` but not on `-scale 4`. @cherrynoize Try calling the script with `-scale 4` as a parameter. Upscaling model...

Hey, David (@moufmouf). From The print I could tell when this happened (although I triggered this error several times before). I think it says 23:32:53 (UTC-3), so in UTC it...

Concordo em gênero, número e grau com a necessidade levantada pelo @PedroHenrique1s .