6 posts tagged with "workflow"

This is an exploration of a VFX shot creation workflow that uses AI.

A Novel Approach​

The Visual Effects Society chapter in New York City did a deep dive on AI about a year ago. One of the panelists was there to showcase a workflow that involved feeding a model with what were essentially previs renders to then create a final shot. Leading up to the panel, I had been incredibly skeptical about AI's utility in the realm of video generation (I still am, but more on that later). However, seeing the ways in which a low polygon pass at a scene could be turned into a final shot was intriguing (mainly for that workflow's potential for granular control, something so rare in AI.)

This article breaks down a fun workflow I put together using Griptape.

Intro​

It was during my first ever meeting with the machine learning working group at the Academy Software Foundation that I met Jason Schleifer, Chief Creative Officer at Griptape and a Wētā FX alum. He was there to showcase Griptape and breakdown the progress they had made in what was described as the connective tissue for AI in modern day VFX. Fast forward a year and The Foundry purchased Griptape to signal their focus on tomorrow's compositing ecosystem. It's exciting to see, and I've been planning a chance to meaningfully test out the project for some time.

What is Griptape?​

Griptape is a few things. First and foremost, it's an AI orchestration tool that allows you to set up multiple agents using a graphical node-based interface. With The Foundry's acquisition, it's becoming increasingly integrated into the Nuke Family suite of tools. It's also a framework, meaning Griptape is an open-source, Python-based library for building AI applications — crucially it's the layer underneath the node UI you see when you set up the installable application. The UI, called Griptape Nodes, is the visual front-end; while the framework is the code-level foundation that the same workflows compile down to (or can be authored in directly). It's a robust, highly extensible Python architecture designed for scale, workflow longevity, and integration with existing infrastructure.

This post is an update on the work on Dailies Notes Assistant, and a reflection on my brother's article: Quality in the Age of Slop.

My brother Sinclair recently wrote an article that's been getting some traction on the internet. Yes, he blogs too, or rather, I blog too, he was very much first. If you're familiar with Hank and John Green from the vlog brothers, well, we've turned into the blog brothers! In his post, he explores the idea of 'Quality' from the book Zen and The Art of Motorcycle Maintenance (1974) and how it relates to programming in the age of AI. Robert Pirsig, in his book, refuses to really define what he means by Quality, but eventually distinguishes between:

Romantic Quality — the immediate, felt, aesthetic surface of things. The beauty you see at a glance. How something feels.

Classic Quality — the underlying structure, function, and reason. How something works.

Reading Sinclair's article, I couldn't help but think about my work with the Academy Software Foundation sandbox project Dailies Notes Assistant, and specifically, what Classic Quality looks like in dailies note taking.

This post covers show-side production tracking in the visual effects industry - looking specifically at tools used to maintain and communicate a database of work on film and television projects. I'm including a simple python script that I set up to quickly A/B dailies against previous versions in Nuke.

I've worked for a studio, I've worked for a vendor, but for the longest time, show-side work has been this big mystery to me. I always figured it was vastly different to anything I'd done before. I've been working show-side on a large project for the last couple months; it's early days but I've learned a few things, so here goes.

In this post, I showcase a fun integration with Pro-Tools and take a look at what makes MASV a great tool for large file sending.

Meet MASV​

MASV is a cloud-native Managed File Transfer service with a long list of multi-industry use-cases. The idea is, rather than trying to manage your own transfer setup, you give that responsibility to MASV who has built out the infrastructure to safely and speedily transfer your files. It's important to note, most MFT companies are not reinventing protocols, they're wrapping them with security and reliability enhancements, a job that would be a headache to do in-house. MASV's specific approach is to provide users with a store and forward model, primarily utilizing Amazon Web Services as their backbone. What this means is users have the flexibility to upload their files, and grab them whenever they want, including while they're still uploading: see MASV Express. With this model, the transfer has a middle man, that for most intents and purposes, is secure and compliant, but that's a consideration some users have to make.

Production Workflow Manager: A liaison who designs, manages, and optimizes production workflows and tool configurations, allowing for fluid collaboration between creative, production, and technical teams.

Introduction​

Most of us accept that the primary role of a VFX vendor-side production team is to facilitate the activities of artists working on a project. The tangible goal-posts then, can be summed up as: keeping an artist's main focus on what's happening between their read and write nodes — not tracking creative look approvals, change orders, linking assets, scheduling, relaying notes, and so on...

A good producer needs to have a set of tools at their disposal to enlist, support, and deliver the work of these artists. These tools should also help make sure producers and coordinators can utilize all available data tracked in whatever production resources available. Enter the Production Workflow Manager. Some put this under Production Manager, others Production Pipeline Lead, at some shops coordinators do this, or TDs, but this person's role is to facilitate the facilitators — and it's my opinion that this should be a dedicated role as the envoy to pipeline from production. Essentially someone who works to build, teach, and support workflows that bolster the work of production professionals.