Our May update on machinima and virtual production related news highlights some of the latest generative AI tools, warts and all, and brings to attention several of the latest machinima potential games, including Jaws, Jurassic World Evolution, 1943: Rise of the Hydra and Harold Halibut. We discuss the challenges filmmakers face when developing games from their IP, why Kickstarter isn’t a good strategy for raising funding for smaller studios, the [almost] final instalment of the RoosterTeeth saga and Second Life’s latest film festival, Fantasy Faire. All with our usual discursive aplomb (despite Ricky being mia, reportedly on a skinny dipping retreat) and a few non machinima related asides!
YouTube Version of this Episode
Show Notes & Links
AI Genies
Art of the Problem about the history of development of generative AI – it’s a documentary including interviews with some of the scientists attributed with developing the building blocks for the techs. Link here.
Google Deepmind has created a new AI model Genie that can create playable worlds in the style of 2D platforms, using an image as a prompt, or a sketch or text description. A twitter thread link here.
Stability AI has introduced its Stable Audio 2.0 model, that enables high quality, full tracks with musical structure up to 3 minutes long from a single text prompt –
According to some, however, its not quite as good as Suno –
Musk has announced that Grok 1.5 Vision which aims to connect the digital and physical worlds with a multi-modal model will be released imminently – here’s link to the website about it https://x.ai/blog/grok-1.5v
Here’s the original style transfer post using Joker –
In comparison to the previous six months, the past month has not exactly been a damp squib but it has certainly revealed a few rather under-whelming releases and updates, notwithstanding Adobe’s Firefly release. We also share some great tutorials and explainers as well as some interesting content we’ve found.
Next Level?
Nvidia and Getty have announced a collaboration that will see visuals created with fully licensed content, using Nvidia’s Picasso model. The content generation process will also enable original IP owners to receive royalties. Here’s the link to the post on Nvidia’s blog.
Microsoft has released its Edge AI image generator, based on OpenAI’s DALL-E generator, into its Bing chatbot. Ricky has tried the tool and comments that whilst the images are good, they’re nowhere near the quality of Midjourney at the moment. Here’s an explainer on Microsoft’s YouTube channel –
Stability AI (Stable Diffusion) has released its SDK for animation creatives (11 May). This is an advancement on the text-to-image generator, although of course we’ve previously talked about similar tools, plus ones that advance this to include 3D processes. Here’s an explainer from the Stable Foundation –
RunwayML has released its Gen 1 version for the iPhone. Here’s the link to download the app. The app lets you use a video from your roll to apply either a text prompt or a reference image or a preset to create something entirely new. Of course, the benefit is that from within the phone’s existing apps, you can then share on social channels at your will. Its worth noting that at the time of writing we and many others are still waiting for access to Gen 2 for desktop!
Most notable of the month is Adobe’s release of Firefly for AdobeVideo. The tool enables generative AI to be used to select and create enhancements to images, music and sound effects, creating animated fonts, graphics and fonts and b-roll content – and all that, Adobe claims, without copyright infringements. Ricky has, however, come across some critics who say that Adobe’s claim that their database is clean is not correct. Works created in Midjourney have been uploaded to Adobe Stock and are still part of its underpinning database, meaning that there is a certain percent (small) of works in the Adobe Firefly database that ARE taken from online artist’s works. Here’s the toolset explainer –
Luma AI has released a plug-in for NeRFs in Unreal Engine, a technique for capturing realistic content. Here’s a link to the documentation and how-tos. In this video, Corridor Crew wax lyrical about the method –
Tuts and Explainers
Jae Solina aka JSFilmz has created a first impressions video about Kaiber AI. This is quite cheap at $5/month for 300 credits (it seems that content equates to appx 35 credits per short vid). In this explainer, you can see Jae’s aged self as well as a cyberpunk version, and the super-quick process this new toolset has to offer –
If you’re sick to the back teeth of video explainers (I’m not really), then Kris Kashtanova has taken the time to generate a whole series of graphic novel style explainers (you may recall the debate around her Zarya of the Dawn Midjourney copyright registration case a couple of months back) – these are excellent and somehow very digestible! Here’s the link. Of course, Kris also has a video channel for her tutorials too, latest one here looks at Adobe’s Firefly generative fill function –
In this explainer, Solomon Jagwe discussed his beta test of Wonder Studio’s AI mocap for body and finger capture although its not realtime unfortunately. This is however impressive and another tool that we can’t wait to try out once its developoer gets a link out to all those that have signed up –
Content
There has been a heap of hype about an advert created by Coca Cola using AI generators (we don’t know which exactly) but its certainly a lot of fun –
In this short by Curious Refuge, Midjourney has been used to re-imagine Lord of the Rings… in the style of Wes Anderson, with much humor and Benicio del Toro as Gimli (forever typecast and our feature image for this post). Enjoy –
We also found a trailer for an upcoming show, Not A Normal Podcast, but a digital broadcast where it seems AIs will interview humans in some alternative universe. Its not quite clear what this will be, but it looks intriguing –
although it probably has a way to go to compete with the subtle humor of FrAIsier 3000, which we’ve covered previously. Here is episode 4, released 21 March –
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.
Rights
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.
NVisionary
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 –
Pro-seed-ural
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 –
🌱 –seeds in Midjourney
What they are, why they're useful, where to find them, & when/how to use them 👇
and you can see the result of the approach in his example of an aging girl here –
Animation
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 –
Tracy Harwood and Ben Grussi’s Machinima Book, On Sale Now!
Recent Comments