LONDON – Foundry has released Nuke 13, which introduces a flexible machine learning toolset, a new Hydra 3D viewport renderer and extended monitor out functionality, enhanced workflows for collaborative review, Python 3 support, and much more.
The Machine Learning Toolset allows artists to harness the power of machine learning directly in Nuke 13. Developed by Foundry’s A.I. Research team, it enables artists to create bespoke effects with a high-quality result in relatively little time. Applications of this toolset include upres, removing motion blur, tracker marker removal, beauty work, garbage matting, and more.
Key components of the machine learning toolset include:
CopyCat – An artist can create an effect on a small number of frames in a sequence and train a network to replicate this effect with the CopyCat node. This artist-focused shot-specific approach enables the creation of high-quality, bespoke models relatively quickly within Nuke without custom training environments, complex network permissions, or sending data to the cloud.
Inference – Is the node that runs the neural networks produced by Copy Cat, applying the model to your image sequence or another sequence.
Upscale and Deblur – Two new tools for common compositing tasks were developed using the ML methodology behind CopyCat and open-source MLServer. The ML networks for these nodes can be refined using CopyCat to create even higher-quality shots or studio-specific versions in addition to their primary use for resizing footage and removing motion blur.
Nuke 13.0 also includes the introduction of Hydra support within Nuke’s 3D viewport, offering a higher quality image much closer to Scanline Renderer’s output, enabling artists to work closer to their final image. Using hdStorm for rendering also provides a more consistent experience to other applications using Hydra.
Introduced in Nuke 12.2, Sync Review has been extended to support syncing of editorial actions as well as playback and annotations. Now fully supported in Nuke Studio, Hiero, and HieroPlayer, Sync Review offers a new way to collaborate on review remotely and share the vision of the final image.