This is the version history, or change log, for all the released versions of NNCleanup (latest official release at the top).

v1.4.1 – November 2023

  • Corrected a bug that made the node crash when a GPU build was used to process on a machine without an installed GPU. Now it automatically falls back to using the CPU instead, as intended.

v1.4.0 – November 2023

  • Added four new variants called “AA”, “BB”, “CC” and “DD”. These new variants are similar to the already existing ones (A-D), but feature improvements in terms of details and color stability (due to better tuned hyper parameters in new training runs from scratch).
  • More efficient releasing of used GPU memory while using the node in a live Nuke GUI session, i.e. you don’t have to restart Nuke anymore to get some of the GPU memory back. Also doing a more thorough GPU memory cleanup when the node is fully deleted (usually when you run “File/Clear” in the Nuke GUI).
  • Added native support for the NVIDIA RTX40xx series of GPUs, i.e. compute capability 8.9 (also supporting 9.0), with a version built against CUDA 11.8 and cuDNN 8.4.1.
  • Added support for Nuke14.1 (which also is natively built against CUDA 11.8 and cuDNN 8.4.1)
  • Added a check for GPU compatibility, i.e. disable the GPU processing options if the current GPU is not supported (instead of crashing).
  • Improved the error logging. It’s now much more clear if the node errors because you are running out of GPU memory.
  • Added text information knobs to the “About” tab that prints out what CUDA/cuDNN versions the current build is against. Also what compute capability that is natively supported and what compute capability your current GPU supports and info about if you will or will not use JIT-compiled kernels. We’ve also added info about compatibility against Nuke’s own AIR tools in relation to the current build configuration.
  • Added a warning to the terminal during node creation if you are relying on JIT-compiled kernels. Just so you get some kind of heads up the first time the JIT-compilation kicks in (which usually takes just above half an hour). There are also warnings about the CUDA_CACHE_MAXSIZE environment variable if it’s not set correctly. These warning can be suppressed with a new environment variable PIXELMANIA_SUPPRESS_KERNEL_WARNINGS if you want.

v1.3.0 – March 2023

  • Added support for dedicated render licenses.
  • Added support for Nuke Indie.

v1.2.1 – March 2023

  • Fixed a bug related to processing on other GPU devices than “CUDA device ID” 0 on multi-GPU workstations.

v1.2.0 – March 2023

  • Implemented NNSuperResolution as an improved way of internally upscaling inpainted results processed in lower resolution than original res, i.e. when using “processing scale” set lower than 1.0. If you turn the option “enhanced upscaling using NNSuperResolution” off, the plugin will instead use a standard bilinear filter to bring the processed patch back to the original resolution (this was the standard behaviour in v1.1.x).
  • Added an option for outputting the internally generated keymix matte into an artist customizable channel. Also added the option to make this output matte binary or not.
  • Made sure to pass through additional layers other than “rgba” correctly and unaltered.
  • Added progress bars when processing.
  • Fixed the default knob values of the “process region”.
  • Fixed so the plugin doesn’t error when specifying a too small “process region” (now it
  • caps at the minimum region possible instead).
  • Minor additional updates to the UI for better user experience.
  • Added support for Nuke11.3 on Linux.

v1.1.1 – February 2023

  • Bug fix release; fixing a processing region issue when not processing “full frame” and the
  • image has a bounding box larger or smaller than the image format.

v1.1.0 – February 2023

  • Addition of the knobs “process”, “process region”, “bbox padding” and “process
  • scale”. All these knobs are relevant to be able to better control the size of the image the plugin is processing, and hence how much GPU memory that is required to be able to run the process GPU accelerated.

v1.0.0 – February 2023

  • Initial release