Skip to content

Releases: nihui/waifu2x-ncnn-vulkan

Release 20250915

15 Sep 11:32
a86cfb0
Compare
Choose a tag to compare

update ncnn libjpeg-turbo zlib-ng

Release 20250802

02 Aug 13:45
d0dda96
Compare
Choose a tag to compare
Release 20250802 Pre-release
Pre-release

update ncnn and pre/post precess

  • insanely faster on amd rdna3+
  • faster on intel / amd integrated graphics
  • slightly faster on nvidia
  • less VRAM on old graphics without fp16 ssbo capability

image decoder / encoder with libjpeg-turbo / libpng / zlib-ng

  • faster image loading and saving with simd optimization
  • support very large resolution

linux package build for manylinux_2_28

expected to be compatible with other distros using glibc 2.28 or later, including:

  • Debian 10+
  • Ubuntu 18.10+
  • Fedora 29+
  • CentOS/RHEL 8+

Release 20250504

04 May 09:22
e129fac
Compare
Choose a tag to compare
fix cpu mode with tilesize smaller than image size (#187)

It was only tested on Linux platform. So, please check if it works on Windows. :)

Signed-off-by: ArchieMeng <[email protected]>

Release 20220728

28 Jul 14:25
Compare
Choose a tag to compare
update ncnn

Release 20220419

19 Apr 14:18
Compare
Choose a tag to compare

fix macos model directory
fix palette png loading in windows
update ncnn library for faster inference

Release 20210521

21 May 14:41
Compare
Choose a tag to compare
build smaller binary size

Release 20210210

10 Feb 08:07
Compare
Choose a tag to compare
update scale implementation

version 20210102

02 Jan 10:12
Compare
Choose a tag to compare

support Apple M1
support running on cpu, which can be parallelized with gpu, via -g -1

version 20200818

18 Aug 14:20
Compare
Choose a tag to compare

fix grayscale image decoding
save to jpg format
try looking for model files from executable directory
add cmake option to build with system libncnn and libwebp
update ncnn for faster gpu loading
multi-gpu support

version 20200606

06 Jun 12:47
cd12dff
Compare
Choose a tag to compare

webp encoding
fix color on windows