This week we share with you a couple of notable RTs (of the UnTwitter kind) and a Dynamo Dream or two. Enjoy!
Who can believe it but Rooster Teeth is now 20 years old. Its come a very long way from its RVB days, not all of it good, but its still rolling. Indeed, RT is now also in the same stable as the final remains of Machinima.com (RIP). Ben Grussi and I dedicated a chapter to the RT story in our book Pioneers in Machinima (2021) and one thing we noted was its resilience to change over the years, so here’s wishing them all the best for the next turn on their roundabout too –
Another long-time favorite on our podcast is the RT Music (formerly RT Machinima) team. This month, I’d like to share their Elden Ring Rap with you (released 12 Mar 2022). Its definitely worth watching the video, not only are these guys great at writing some toe-tappers but they also do a pretty good job of showing off their machinima skills too –
Finally this week, Ian Hubert has released two episodes of his Dynamo Dream live action/VFX series (our feature image for this post). We covered the first episode of this stunning series on the podcast back in August 2021 (audio only) but what’s quite incredible about the release of Eps 2 and 3 in such quick succession is frankly the speed at which he’s been able to release them… and of course they’re very good if ever so slightly absurdist.
A Single Point in Space – Dynamo Dream, Ep 2 (released 23 Mar 2023) –
A Pete Episode – Dynamo Dream, Ep 3 (released 6 Apr 2023) –
Next week, we have some more selections to share with you too but if you find something you’d like us to do a full review of on the podcast, do share it.
March was another astonishing month in the world of AI genies with the release of exponentially powerful updates (GPT4 released 14 March; Baidu released Ernie Bot on 16 March), new services and APIs. It is not surprising that by the end of the month, Musk-oil is being poured over the ‘troubling waters’ – will it work now the genie is out of the bottle? Its anyone’s guess and certainly it seems a bit of trickery is the only way to get it back into the bottle at this stage.
More importantly, and with immediate effect, the US Copyright Office issued a statement on 16 March in relation to the IP issues that have been hot on many lips for several months now: registrations pertaining to copyright are about the processes of human creativity, where the role of generative AI is simply seen as a toolset under current legal copyright registration guidance. Thus, for example, in the case of Zarya of the Dawn (refer our comments in the Feb 2023 Tech Update), whilst the graphic novel contains original concepts that are attributable to the author, the use of images generated by AI (in the case of Zarya, MidJourney) are not copyrightable. The statement also makes it clear that each copyright registration case will be viewed on its own merit which is surely going to make for a growing backlog of cases in the coming months. It requires detailed clarification of how generative AI is used by human creators in each copyright case to help with the evaluation processes.
The statement also highlights that an inquiry into copyright and generative AIs will be undertaken across agencies later in 2023, where it will seek general public and legal input to evaluate how the law should apply to the use of copyrighted works in “AI training and the resulting treatment of outputs”. Read the full statement here. So, for now at least, the main legal framework in the US remains one of human copyright, where it will be important to keep detailed notes about how creators generated (engineered) content from AIs, as well as adapted and used the outputs, irrespective of the tools used. This will no doubt be a very interesting debate to follow, quite possibly leading to new ways of classifying content generated by AIs… and through which some suggest AIs as autonomous entities with rights could become recognized. It is clear in the statement, for example, that the US Copyright Office recognizes that machines can create (and hallucinate).
The complex issues of the dataset creation and AI training processes will underpin much of the legal stances taken and a paper released at the beginning of Feb 2023 could become one of the defining pieces of research that undermines it all. The research extracted near exact copyrighted images of identified people from a diffusion model, suggesting that it can lead to privacy violations. See a review here and for the full paper go here.
In the meantime, more creative platforms used to showcase creative work are introducing tagging systems to help identify AI generated content – #NoAI, #CreatedWithAI. Sketchfab joined the list at the end of Feb with its update here, with updates relating to its own re-use of such content through its licensing system coming into effect on 23 March.
Nvidia’s progressive march with AI genies needs an AI to keep up with it! Here’s my attempt to review the last month of releases relevant to the world of machinima and virtual production.
In February, we highlighted ControlNet as a means to focus on specific aspects of image generation and this month, on 8 March, Nvidia released the opposite which takes the outline of an image and infills it, called Prismer. You can find the description and code on its NVlabs GitHub page here.
Alongside the portfolio of generative AI tools Nvidia has launched in recent months, with the advent of OpenAI’s GPT4 in March, Nvidia is expanding its tools for creating 3D content –
It is also providing an advanced means to search its already massive database of unclassified 3D objects, integrating with its previously launched Omniverse DeepSearch AI librarian –
It released its cloud-based Picasso generative AI service at GTC23 on 23 March, which is a means to create copyright cleared images, videos and 3D applications. A cloud service is of course a really great idea because who can afford to keep up with the graphics cards prices? The focus for this is enterprise level, however, which no doubt means its not targeting indies at this stage but then again, does it need to when indies are already using DALL-E, Stable Diffusion, MidJourney, etc. Here’s a link to the launch video and here is a link to the wait list –
A procedural content generator for creating alleyways has been released by Difffuse Studios in the Blender Marketplace, link here and see the video demo here –
We spotted a useful social thread that highlights how to create consistent characters in Midjourney, by Nick St Pierre, using seeds –
and you can see the result of the approach in his example of an aging girl here –
JSFilmz created an interesting character animation using MidJourney5 (which released on 17 March) with advanced character detail features. This really shows its potential alongside animation toolsets such as Character Creator and Metahumans –
Runway’s Gen-2 text-to-video platform launched on 20 March, with higher fidelity and consistency in the outputs than its previous version (which was actually video-to-video output). Here’s a link to the sign-up and website, which includes an outline of the workflow. Here’s the demo –
Gen-2 is also our feature image for this blog post, illustrating the stylization process stage which looks great.
Wonder Dynamics launched on 9 March as a new tool for automating CG animations from characters that you can upload to its cloud service, giving creators the ability to tell stories without all the technical paraphenalia (mmm?). The toolset is being heralded as a means to democratize VFX and it is impressive to see that Aaron Sims Creative are providing some free assets to use with this and even more so to see none other than Steven Spielberg on the Advisory Board. Here’s the demo reel, although so far we’ve not found anyone that’s given it a full trial (its in closed beta at the moment) and shared their overview –
Finally for this month, we close this post with Disney’s Aaron Blaise and his video response to Corridor Crew’s use of generative AI to create a ‘new’ anime workflow, which we commented on last month here. We love his open-minded response to their approach. Check out the video here –
This week, we highlight some time-saving examples for generating 3D models using – you guessed it – AIs, and we also take a look at some recent developments in motion tracking for creators.
All these examples highlight that generating a 3D model isn’t the end of the process and that once its in Blender, or another animation toolset, there’s definitely more work to do. These add-ons are intended to help you reach your end result more quickly, cutting out some of the more tedious aspects of the creative process using AIs.
Blender is one of those amazing animation tools that has a very active community of users, and of course, a whole heap of folks looking for quick ways to solve challenges in their creative pipeline. We found folks that have integrated OpenAI’s ChatGPT into using the toolset by developing add-ons. Check out this illustration by Olav3D, whose comments about using ChatGPT for attempting to write Python scripts sum it up nicely, “better than search alone” –
Dreamtextures by Carson Katri is a Blender add-on using Stable Diffusion which is so clever that it even projects textures onto 3D models (with our thanks to Krad Productions for sharing this one). In this video, Default Cube talks about how to get results with as few glitches as possible –
and this short tells you how to integrate Dreamtextures into Blender, by Vertex Rage –
To check out Dreamtextures for yourself, you can find the Katri’s application on Github here and should you wish to support his work, subscribe to his Patreon channel here too.
OpenAI also launched its Point-E 3D model generator this month, which can then be imported into Blender but, as CGMatter has highlighted, using the published APIs takes a very long time sitting in cues to access the downloads, whilst downloading the code to your own machine to run it locally, well that’s easy – and once you have it, you can create point-cloud models in seconds. However, he’s running the code from Google’s CoLab, which means you can run the code in the cloud. Here’s his tutorial on how to use Point-E without the wait giving you access to your own version of the code (on Github) in CoLab –
We also found another very interesting Blender add-on, this one lets you import models from Google Maps into the toolset. The video is a little old, but the latest update of the mod on Github, version 0.6.0 (for RenderDoc 1.25 and Blender 3.4) has just released, created by Elie Michel –
We were also interested to see NVIDIA’s update at CES (in January). It announced a release for the Omniverse Launcher that supports 3D animation in Blender, with generative AIs that enhance characters’ movement and gestures, a future update to Canvas that includes 360 surround images for panoramic environments and also an AI ToyBox, that enables you to create 3D meshes from 2D inputs. Ostensibly, these tools are for creators to develop work for the metaverse and web3 applications, but we already know NVIDIA’s USD-based tools are incredibly powerful for supporting collaborative workflows including machinima and virtual production. Check out the update here and this is a nice little promo video that sums up the integrated collaborative capabilities –
As fast as the 3D modelling scene is developing, so is motion tracking. Move.ai which launched late last year, announced its pricing strategy this month at $365 for 12 months of unlimited processing of recordings – this is markerless mocap at its very best, although not so much if you want to do live mocap (no pricing strategy announced yet). Move.ai (our feature image for this article) lets you record content using a mobile phone (a couple of old iPhones). You can find out more on its new website here and here’s a fun taster, called Gorillas in the mist, with ballet and 4 iPhones, released in December by the Move.ai team –
And another app although not 3D is Face 2D Live, released by Dayream Studios – Blueprints in January. This tool allows you to live link a Face app on your iPhone or iPad to make cartoons, including with your friends also using an iPhone app, out of just about anything. It costs just $14.99 and is available on the Unreal Marketplace here. Here’s a short video example to wet your appetite – we can see a lot of silliness ensuing with this for sure!
Not necessarily machinima but for those interested in more serious facial mocap, Weta has been talking about how it developed its facial mocap processes for Avatar, using something called an ‘anatomical plausible facial system’. This is an animator centric system that captures muscle movement rather than ‘facial action coding’ which focusses on identifying emotions. Weta stated its approach leads to a wider set of facial movements being integrated into the mocapped output – we’ll no doubt see more in due course. Here’s an article on the FX Guide website which discusses the approach being taken and for a wider ranging discussion on the types of performance tracking used by the Weta team, Corridor Crew have bagged a great interview with the Avatar VFX supervisor, Eric Saindon here –
In this episode, Tracy talks to John Gaeta about his interests in machinima and real time filmmaking, The Matrix Awakens Experience, the influence of the bullet time shot, building the metaverse, future of storytelling in immersive environments, the potential of NFTs and his advice for indie creators.
Released in November 2020, this viral short by Birchpunk is a lot of fun. Uses VFX to present a vision of how we might colonize Mars and the future of cyber-farming, so our beloved Percy (NASA’s Perseverence) has a way to go to catch up with the vibe… eat your heart out Mr Musk, the Russians have beaten you to it. “We have love…”! Enjoy. You can follow Birchpunk’s channel on YouTube
Tracy Harwood and Ben Grussi’s Machinima Book, On Sale Now!