If you do not agree, click on the “I Disagree” button below and exit the Website. I acknowledge that the Website’s Terms-of-Service Agreement governs my use of the Website, and I have reviewed and agreed to be bound by those terms.By logging on and viewing any part of the Website, I will not hold the Website’s owners or its employees responsible for any materials located on the Website.I understand and will abide by the standards and laws of my community.I will leave this Website promptly if I am in any way offended by the sexual nature of any material.I do not find images of nude adults, adults engaged in sexual acts, or other sexual material to be offensive or objectionable.I am voluntarily choosing to access this Website because I want to view, read, or hear the various available materials.I will not allow any person under 18-years old to have access to any of the materials contained within this Website.I am an adult, at least 18-years old, and the age of consent in my jurisdiction, and I have the right to access and possess adult material in my community.By clicking “I Agree” below, you state that the following statements are accurate: Visiting this Website if you are under 18-years old and the age of consent might be prohibited by the law of your jurisdiction. The materials that are available on this Website include graphic visual depictions and descriptions of nudity and sexual activity and must not be accessed by anyone who is under 18-years old and the age of consent. If you find that your GPU is hungry, try increasing thread count to achieve faster processing.This Website is for use solely by individuals at least 18-years old (or the age of consent in the jurisdiction from which you are accessing the Website). The default setting usually works fine for most situations. You can tune this configuration with "4:4:4" for many small-size images, and "2:2:2" for large-size images. load:proc:save = thread count for the three stages (image decoding + waifu2x upscaling + image encoding), using larger values may increase GPU usage and consume more GPU memory. tile-size = tile size, use smaller value to reduce GPU memory usage, default selects automatically.scale = scale level, 1 = no scaling, 2 = upscale 2x.noise-level = noise level, large value means strong denoise effect, -1 = no effect.input-path and output-path accept either file path or directory path. h show this help -v verbose output -i input-path input image path (jpg/png/webp) or directory -o output-path output image path (jpg/png/webp) or directory -n noise-level denoise level (-1/0/1/2/3, default=0) -s scale upscale ratio (1/2/4/8/16/32, default=2) -t tile-size tile size (>=32/0=auto, default=0) can be 0,0,0 for multi-gpu -m model-path waifu2x model path (default=models-cunet) -g gpu-id gpu device to use (-1=cpu, default=auto) can be 0,1,2 for multi-gpu -j load:proc:save thread count for load/proc/save (default=1:2:2) can be 1:2,2,2:2 for multi-gpu -x enable tta mode -f format output image format (jpg/png/webp, default=ext/png) Usage: waifu2x-ncnn-vulkan -i infile -o outfile.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |