Stable Diffusion on AMD RDNA™ 3 Architecture

• oneMKL

  2 564 8.5 C++

  oneAPI Math Kernel Library (oneMKL) Interfaces

  

I think there's already been work done to just use intel MKL on any device: https://github.com/oneapi-src/oneMKL

• waifu2x-ncnn-vulkan

  30 2,874 0.0 C

  waifu2x converter ncnn version, runs fast on intel / amd / nvidia / apple-silicon GPU with vulkan

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• realsr-ncnn-vulkan

  7 1,036 0.0 C

  RealSR super resolution implemented with ncnn library

• dain-ncnn-vulkan

  9 496 0.0 C

  DAIN, Depth-Aware Video Frame Interpolation implemented with ncnn library

• rife-ncnn-vulkan

  12 739 0.0 C

  RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library

• srmd-ncnn-vulkan

  2 319 0.0 C

  SRMD super resolution implemented with ncnn library

• waifu2x

  403 27,147 0.0 Lua

  Image Super-Resolution for Anime-Style Art

Waifu2x in particular, is one of the oldest and still one of the best AI upscalers for anime and drawings in general, and it has always heavily favored Nvidia. The most known port was not the original Waifu2x by nagadomi, but Waifu2x-caffe, which was much more feature rich, and supported CUDA and cuDNN, both Nvidia exclusive. There was an OpenCL alternative which worked on AMD, but it was only as fast as Waifu2x-caffe under CUDA, but with cuDNN it still blew the OpenCL out of the water.

• WorkOS

  workos.com sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

• waifu2x-caffe

  47 7,947 0.0 C++

  waifu2xのCaffe版

Waifu2x in particular, is one of the oldest and still one of the best AI upscalers for anime and drawings in general, and it has always heavily favored Nvidia. The most known port was not the original Waifu2x by nagadomi, but Waifu2x-caffe, which was much more feature rich, and supported CUDA and cuDNN, both Nvidia exclusive. There was an OpenCL alternative which worked on AMD, but it was only as fast as Waifu2x-caffe under CUDA, but with cuDNN it still blew the OpenCL out of the water.

• Orochi

  1 15 7.3 C++
  

HIP is supported on Windows. Blender runs its HIP backend on Windows for example. Orochi enables developers to use HIP on windows already https://github.com/amdadvtech/Orochi

Suggest a related project