Nvidia Archives - Page 2 of 6 - Completely Machinima

Tech Update 2 (June 2023)

Tracy Harwood Blog June 12, 2023 1 Comment

Its a week of mono|meta|omni-versal updates!

Mono

We’ve been following the debate on copyright, fair use and transformative use of IP for what seems like 30 years in the world of machinima (see some of our posts here, here and here) – oh, actually its 27 years…! On 18 May, the world was exercised a little further on the issue of transformative use when the Supreme Court (US) reached its decision on Andy Warhol’s use of a photograph of Prince in a magazine – a case that’s been running since 2016, following Prince’s death. Many suggested this decision is the beginning of end of transformative use – or at least ‘narrows the ‘fair use’ doctrine‘ – and will have massive detrimental impacts on all things created, such as machinima from games engines… however, with the particular scenario fully outlined, this was probably the right outcome for this case. The scenario relates to an unattributed use of an image from a private collecton of works (created and held by Warhol/foundation), where other works involving the same creatives in the collection had previously been attributed and the photographer recompensed when having been used in magazines, and the fact that both Warhol and the photographer (Lynn Goldsmith) made money from selling images individually. So, this decision is about context of use involving the individuals as much as it is ‘fair use’ per se. Justice Sotomayor stated the important factor in the fair-use analysis was that “the purpose and character of the use, including whether such use is of a commercial nature or is for nonprofit educational purposes” pushed the decision in favour of the photographer, arguing that “licenses, for photographs or derivatives of them, are how photographers like Goldsmith make a living. They provide an economic incentive to create original works, which is the goal of copyright.” You can read the ruling in full here – or use your favorite search tool for a link to any one of the numerous news articles covering the case.

So, until such time as the principle applied in this case is actually applied to a creator context, where income is rarely a goal of productions beyond individual recognition and perhaps the meagre YouTube % share for eyeballs it receives, and transformation is generally well beyond that originally intended by say a game dev, it feels like there’s nothing to see here.

Tech Update: AI (June 2023)

Tracy Harwood Blog June 5, 2023 Leave a reply

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 –

Tech Update 2 (Apr 2023)

Tracy Harwood Blog April 10, 2023 Leave a reply

This week, tech updates cover Epic’s new tools for self-publishing, Omniverse’s USD rebrands, thoughts about the nascent metaverse and some throwbacks to good-old-fashioned machinima creative techniques.

Epic’s Games Store

Surely a move that will make rival Steam squirm, Epic announced on 9 March that it has launched new tools for self-publishing on the Games Store, all on the back of its 68M active monthly users. Publishers will receive 88% of the revenue through sales (compared to 70% on Steam). There are some interesting points raised in the T&Cs, such as the need for cross-playability (across all PC stores), achievement tracking for games, age rating requirements and an affiliate creator programme that enables publishers to share their takings with others – check out the T&Cs on their announcement here. The announcement intimates at much bigger things to come, relating to metaverse propositions, but its an interesting development for now. Here’s a walk through of the tools from their livestream about it –

Omniverse USD

Nvidia’s Omniverse Create and Omniverse View are rebranding, announced on 3 March. These will now be called, respectively, Omniverse USD Composer and Omniverse USD Presenter. The omnipresence of USD (Universal Scene Description) has become a driving force for 3D creative development in a very short space of time – just last August, Nvidia summarized its vision with embedding USD as the foundation of the metaverse for creatives (and also industrial teams, smart services providers and such), where content could be pushed across a vast array of different platforms. Less than a year later, workflows everywhere have evolved with it and USD is now a ubiquitous technology, much like the internet is the driving force for the web. What’s a little intriguing is why draw attention to it at this juncture, and what’s the point of editing archival videos to include the new names, like this one – recognition, reinforcement, repositioning or something new coming down the pipeline?

Blended

Beyond the hype, and clearly the practices as we’ve highlighted above, the metaverse is taking shape in interesting ways. An interesting article, published in VentureBeat on 4 March, highlights the lengths that media and entertainment companies such as Sony are going to in creating virtual worlds that transcend film, game and experiences, including in VR and theme parks. These are more than alignments of creative talent teams, but allude to the potential of vast new ecosystems for collaborators and partners. What’s interesting of course is that the inflection into such ecosystems can be from any creative medium (game, film or artwork presumably), with outputs that are going to be more visceral and consequently more immersive. Since toolsets such as USD facilitate the creation of these ecosystems, it will be interesting to see how indies get in on this action too – we’re already seeing a number of start-up enterprises pushing the boundaries, but there’s also scope for small studios to join in. Question is, where are they now?

Cinematics (the Old Way)

No Man’s Sky has been a machinina creators’ go-to for some time, and this short gives a great overview of how to create cinematics in the environment, by EvilDr.Porkchop (also our blog post feature image) –

Eve Online is another such environment, and now of course a [very] old one, but here’s a nice ‘how to’ for making epic looking machinimas, by WINGSPAN TT –

Tech Update 1: AI Generators (Apr 2023)

Tracy Harwood Blog April 3, 2023 Leave a reply

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 👇

🧵 Thread w/ examples & prompts in ALTs pic.twitter.com/qkoaVLVmWl
— Nick St. Pierre (@nickfloats) March 6, 2023

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 –

Tech Update 2 (Feb 2023)

Tracy Harwood Blog February 13, 2023 Leave a reply

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.

3D Modelling

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 –

Tracking

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 –

Nvidia

Tech Update 2 (June 2023)

Tech Update: AI (June 2023)

Tech Update 2 (Apr 2023)

Tech Update 1: AI Generators (Apr 2023)

Tech Update 2 (Feb 2023)

Tracy Harwood and Ben Grussi’s Machinima Book, On Sale Now!

Recent Posts

Recent Comments

Archives

Categories