nuke-cattery-inference

Version: 1.1.1 Last Updated: 2026-03-10 Dependencies: NukeX or Nuke Studio (not Nuke Indie/Non-Commercial), Python 3.10+, PyTorch 2.1.1+cpu Deep Reference: ClaudeCode/data/research/Nuke_ML_Inference_Research.md

Overview

NukeX's Cattery system lets you run PyTorch ML models inside Nuke via the Inference node. The workflow is:

1. Export PyTorch model to TorchScript (.pt) - via script() or trace()
2. Compile .pt -> .cat via CatFileCreator node (NukeX/Studio only)
3. Infer using the Inference node in any comp (base Nuke too)

Requires NukeX or Nuke Studio for authoring. Inference node works in any Nuke license. Nuke version -> PyTorch version mapping: