NNFlowVector is free to use for producing regular motion vectors, and no license is required to run it (just download and install it using the included instructions). To be able to use the smart vector output feature, you have to obtain a license (either buy one or request a trial license first).
Please do try the software on your own system before ordering a license using the shop.
If you do wish to test out any of the softwares without limitations, you can request a free trial license using this page.
By downloading our software you are accepting our end user license agreement.
If you are unsure of what version to download, here is a short explanation. You have three different options of CUDA version that the plugins have been compiled against, and you got to pick one. There are pros and cons with both options:
– CUDA11.2: This is a more modern version of CUDA which does natively support the modern GPUs with compute capability 8.0 and 8.6 (i.e. Ampere cards, such as a RTX3080). This version will run directly and possibly even faster on the modern GPUs. The downside is that you will run into a CUDA/cuDNN version clash when using Foundry’s AIR nodes in Nuke13.x. If you need to use our plugins alongside those, you have to use the CUDA10.1 build instead.
– CUDA10.1: This is an older version of CUDA/cuDNN, but is matching exactly to the versions Nuke13.x are built against. You need to use this version if you want our plugins to run alongside Foundry’s AIR nodes (for example the CopyCat node). The downside is that if you got a modern GPU with compute capability 8.0 or 8.6 (i.e. Ampere cards, such as a RTX3080), you will have to wait 20-30 minutes the first time you run our plugins because it will have to JIT compile the PTX code to support your modern GPU. Please see the documentation of how to increase the value for the CUDA_CACHE_MAXSIZE environment variable to do this successfully.
– CUDA11.1: This is what the Nuke14 builds of the plugins have been compiled against, to match exactly to the versions that Nuke itself is built against. Since the compute capability 8.0 and 8.6 cards are natively supported here, we can rely on only one version of CUDA/cuDNN for Nuke14 which make it much simpler.
NNFlowVector – v2.0.0
| CUDA11.1.1** | CPU only | |
| NVIDIA cuDNN | v8.4.1 | – |
| NVIDIA driver | 455.32+ on Linux 456.81+ on Windows | – |
| Nuke14.0 |   |   |
| CUDA11.2.0 | CUDA10.1.243* | CPU only | |
| NVIDIA cuDNN | v8.1.0 | v8.0.5* | – |
| NVIDIA driver | 460.27+ on Linux 460.89+ on Windows | 418.87+ on Linux 426.00+ on Windows | – |
| Nuke13.2 | |   | |
| Nuke13.1 | | | |
| Nuke13.0 | | | |
| Nuke12.2 | | | |
| Nuke12.1 | | | |
| Nuke12.0 | | | |
* This combination of CUDA & cuDNN matches what Nuke 13.x is built against. This means that if you do need NNFlowVector to work well together with Foundry AIR nodes (such as CopyCat) in the same Nuke scripts, you have to use this version. If you got a compute capability 8.0 or 8.6 GPU (i.e. Ampere architecture, for example RTX3080), you will then need to wait for the plugin to auto-compile the kernels for that GPU the first time it’s used. Please see the section about “environment variables” in the documentation to read about how to increase the CUDA_CACHE_MAXSIZE to successfully use this version with modern GPUs.
Important! If you are downloading the Windows versions of the plugin, you have to add the full path to the chosen plugin installation folder to the PATH environment variable on your system (in addition to the NUKE_PATH environment variable). This is needed for the plugin to be able to find additional included libraries that it is dependent on. Please refer to the “Plugin Installation” section in the included Documentation for more details. (This is handled automatically by the system when you are using the Linux versions.)