AI in animation

This last week I’ve been at the Manchester Animation Festival - a week-long festival for industry, education, and public alike. The panels and short films lit my mind up with an inspiration and drive that I haven’t felt in a while.

On the Industry Day, one of the panels I’d most anticipated was about AI: the fears, the predictions, the ways we’re already using it to improve our work… I’m certainly using AI tools in my photo editing, and as a base for subtitling any fast turnaround work for YouTube etc

For my money, a lot of the practical uses will end up being based on personal/client preferences, past the obvious ethical and legal conversations that are already taking place.

Take voice acting. When we change a line / scene in a script, we usually scratch in the dialogue by getting someone in the studio to record it. The actor then records the line at their next session, or ADRs it if it has already been animated to the scratch.

The current ethical debate, prompted by existing “machine learning” in which AI systems have been “trained” on an actor’s voice and then prompted to generate new speech from a written prompt, is “we can replace that by training an AI on the actor’s voice” vs “actors should be paid, and given the chance to produce the most authentic work”.

Obviously I agree with the latter- audiences deserve the authenticity, and suggesting that AI can replace their training and talent is horrible. But. How about using the AI as a temporary placeholder, instead of the scratch of a completely different voice just jumping in?

+ you get a smoother viewing experience

- the output is misrepresenting what you actually have “in the can” (burn-ins are easily overlooked)

+ it joins up more neatly, and you can judge timing better with a more accurate placeholder

+ if animation for the shot must happen before the actor is next available, a smooth read in the correct cadence and pronunciation will help lipsync

- the actor may be unnerved by hearing their own voice at ADR/ sense the uncanny valley more readily

… all of this assumes that the technology allows for cadence, tone etc. But existing technology such as VocAlign/ Revoice Pro (where you can match an audio clip by the actor to a reading by anyone else) take us a long way towards that already. We can use a written “find” command to find words or syllables in an audio library in Avid’s PhraseFind or DaVinci Resolve Studio. I feel confident that I could get some way towards a useable voice performance… if given enough time. If AI can be used as a tool to cut out that time, and present options to a human, it could be very useful indeed. IF it is desired.

It’s going to be an interesting time. But whether people currently view it as the dawn of a new era or the opening of a new Pandora’s Box… AI is happening. It’s worth being part of the conversation.

Awards season

The BAFTA Film nominations were yesterday. Unfortunately, Pirates not only failed to win - they were not even amongst the three animated features nominated in the relevant category.

However, this was more or less righted by the nomination in the 85th Academy Awards - announced earlier today. Pirates is one of five films nominated for Best Animated Feature, and one of three stop motion films within the category! So, fingers crossed for the 24th of February.

Another recently announced set of nominations that I eagerly browsed were those of the Visual Effects Society Awards - having been the previs/ VFX editor on Pirates, I was rather hoping to see a few nods in that area. Indeed, there's an Outstanding Animated Character in an Animated Feature Motion Picture - competing against Brave, Hotel Transylvania, and Wreck-It Ralph - all of which are fully CG. I personally attribute a large part of this (corrrectly or not) the seamless overlap between stop-motion and CG to a fair amount of confusion over the nature of the film and its effects. Not only amongst lay-people (although I have had to clarify on a few occasions that the water was indeed generated and yes - CG CAN do that these days), but also amongst VFX pros - for whom I answered several questions on Twitter about the production and stop motion, previs, vfx, CG animation, etc. at the time the film came out.

Pirates also has a Best Animated Feature nomination in the 40th Annie Awards, as well as Outstanding Achievement nominations in four categories:Character Animation in a Feature Production,  Production Design in an Animated Feature Production, Voice Acting in an Animated Feature Production, Writing in an Animated Feature Production. So... exciting times.

Working on Pirates was an amazing experience in its own right, especially as it was the first feature I ever worked on - but it's certainly amazing and fulfilling to see it get some outside recognition too, from people who didn't actually work on it - or who don't feel they have to say nice things because they know me.

It's been almost exactly a year now since VFX finished on the film, and it's immensely gratifying to see it still making its way out there. I really hope that it continues to get the same level of love and commitment from the rest of the world as those of us involved in its production put in.

To be an editor

I've recently started an acting class (more on that soon), and as it's a beginners class the attendees generally aren't in the industry. One or two would like to write or direct, but generally people are within other careers.

I've been honest and told them what I do. Here's a conversation I had last week after class with a small group:

Them: so what do you edit?
Me: Animation, mostly, at the moment. I have a short film or two coming up on the side.
Them: So where do you go after that? What is it you want to be?
Me: An editor.
Them: No, I mean, would you like to direct?
Me: Nope. I love editing.
Them: But... you already edit. What do you do next?
Me: Edit more. Edit better.

I'm not denying that there are editors out there who have always had their hearts set on directing. After enough sets of bad dailies I have sometimes wanted to make a film under the impression I at least knew a lot of what not to do.... perhaps that's why I'm doing well in animation editing where I have input over the way the framing works, the timing of lines, and the way we actively expect lines to be re-recorded to change performance.

Perhaps it's the lack of perceived credit/ glamour in the eyes of the public that puts the job down? I'd imagine most people on the street would find it very difficult to name any editor. Ask them about directors, and the job becomes much easier. It's true, our sector of the industry does seem to get marginalised (I remember commenting on Twitter one time when I noticed the editorial department credits of a feature film listed below on-set catering) and ACE and MPEG are actively campaigning for greater festival recognition of editors (see editorspetition.com for more information). Editors are traditionally seen as the quiet workers behind the scenes, and that's how a lot like it. But the lack of recognition for the job as a craft, and to want to always learn how to do your job better, does sometimes grate.

A Common Problem

Just about anyone who's used Avid before will know that all support queries and error message searches lead back to the Avid Community forum.

This is sometimes all you need to be able to fix your problem (even if the answer usually involves hours of work attempting to find a single corrupted audio file). More often, however, this occurs:

from xkcd

For those of you unfamiliar with xkcd (why? how?!) a great feature is the image alt text, accessible by hovering over the image on their website - or via an app on iOS. And it was the alt text which really made me think of the Avid Community:

"All long help threads should have a sticky globally-editable post at the top saying 'DEAR PEOPLE FROM THE FUTURE: Here's what we've figured out so far ...'"

Beautiful advice, and also potentially circumnavigating the existing dilema of whether to dredge up a 3 year old thread, start a new thread even though nobody knew the answer last time, or just try to get on with it yourself since nobody knew last time - and if they did figure it out then they're not the sort of person to update the old thread in which nobody else seems to have had the same problem over the last 3 years.