It's just not that big of a deal. How often does it happen? And you can just reply to yourself too to "fix" it. Better than the chaos of unrestricted edits.
This is simply amazing. There were so many images there that are photorealistic enough that I was trying to figure out was this a real live action project? Or had someone simply staged the images as part of a larger "art project " or something...
Took me by surprise that this was AI generated, although in hindsight it should have been obvious. For me, this is the moment I realized AI art had become something "useful", and the world isn't going to be the same.
I can see where this is going... The commercial implications are enormous. Speeding up the concept art process for movies, etc. As someone here mentioned, why not make entire movies this way? Once they figure out how to animate this stuff, it puts the movie industry out of business.
I can only imagine what my grandkids are going to be using this for.
> Once they figure out how to animate this stuff, it puts the movie industry out of business.
I'm also intrigued about the potential of AI-generated animation.
However, I don't think the industry would be "out of business", but rather they would simply evolve into a new phase. The established movie industry will most likely have access to the most expensive and performant AI models to make short and long form animations, which would be time and cost prohibiting for hobbyists.
Agree, the movie industry won't be out of business overnight.
Like IBM, the rumors of "company X" demise are greatly exaggerated, and this tech is far from mature. But my god at first I thought this was real. The clock is now ticking, fast forward several generations, and what are we dealing with here?
To me this is a Napster moment. If your job is related to the movie making industry at all, you should be sitting up and taking notice. The industry is a massive/slow behemoth that is a ripe target for this kind of disruption. What's the point of building sets once these tools become photorealistic? Yes we're still in the Uncanny Valley, but that's just a matter of time to solve these kinds of problems (deepfakes anyone?).
CGI killed the traditional animation industry. Even Disney shuttered it's traditional animation department. I think we're looking at the same kind of disruption here on the live action side of things. Why have a studio lot at all ? Equipment rental, prop rental, stunt actors, logistics, food service, you name it. Talk about the end of brick and mortar.
My guess is it will look a lot like the music industry, which has essentially become all Marketing and Promotion, where the actual production of music has almost become an afterthought. The Marketing arms of the industry may be the only thing that survives the transition in some recognizable form.
There will always be a demand for "live action", just like traditional animation is still being done in some niche corners. [1] But that's the exception, not the rule. You'll continue to have enthusiasts using traditional methods for the sake of it. But I think the clock is now ticking. It may be in its primitive infancy, but add time and the tech stack will eventually mature.
Lately, more and more, I feel like I'm actually living in the future.
There won't be a sea of new young faces trying to break into a role anymore, or be an extra, or work on the stage crew, since they just won't be able to compete with the AI alternatives. Hollywood thrives on a human pyramid of desperately motivated individuals trying to get noticed and willing to do anything. This might shatter that base, and could have knock on consequences: agent-star exclusivity, entourages, glam mags, production crews. Celebrities will be the same ones we see today, the door for new talent is closing fast.
This. The trend has already started, tech like this will (eventually) accelerate the transition.
People don't go to movies to see movie stars anymore. They go to see Marvel characters. [1]
I think we're at the bookend of a transitional era for movies (and for many other things). Transition started with Napster, iPod, Netflix, etc. and ended with the "mainstreamization" of Marvel. Traditional movies are dead, what's left is something that really doesn't look anything like the movie industry I grew up with. Like other art forms (opera, theater, orchestras, etc) traditional movie story telling just isn't where it's at any more, the "masses" have moved on. The industry used to be full of passionate creative types. Now it's full of people working their butts off to get their name somewhere in the 20 minutes of credits at the end of a film, for the prestige of being able to tell their friends they work in the industry. It's a self-sustaining business at this point, full of nepotism, cronyism, and people happy just to stay employed doing whatever it is they do (digital work, setting up lights, renting equipment, managing the logistics).
I've asked my cinemaphile friends if they can name a big up and coming director? Who is the next Tarantino? No one has any real answer. At best I get JJ Abrams, who (at 56) is on the tail end of his career, and if anything he's a symptom of the problem (mom and dad worked in the business). It's a group of insiders churning out jobs for their kids and a steady stream of income. Hollywood is nothing more than a brand now.
Whatever the "future" is, it's here. More Marvel, less relevance.
Villeneuve! Bladerunner and Dune were both beautiful and highly stylized, and his work is enough to sell me on Cleopatra and Rama. Yes he's also in his 50s,but at least that means he's getting huge budgets to do what he wants now.
Wes Anderson is a similar story, though he's been doing it for longer because his films don't need as big a budget. Most people I know would go to see "the new Wes Anderson" sight unseen.
Although I haven't seen his earlier acclaimed work, Bong Joon-ho certainly does not seem to be at "the tail-end of his career".
I think the reason these directors are all in their 50s is that studios aren't willing to trust younger directors as much, but that just means there ARE up and coming directors in their 20s and 30s who are making low-budget short/art films, who have not yet found public appeal.
Expanding to TV series, Alex Hirsch is not technically a director but his name is a major stamp of quality assurance.
Edit: Ari Aster is 36. Jordan Peele is 43 but just beginning his directing career. Roger Eggers is 39. Damien Chazelle is 37. I'm using age here as a metric for being at an early point in their career.
I have no problems with Villeneuve... he's more than competent, definitely interesting. But (to me anyways) directors like this aren't the same league as the giants that came before them. I'd trust him enough not to mess up an interesting picture, but he's not really pushing the envelope as much as before. I'll take another Tarantino or Rodriguez, and I doubt we'll see the likes of Kubrick, Welles, Fellini, Tartovsky, Leone, etc. ever again. Heck I'd settle for another Spielberg, he may be a bit saccharin, but he has a killer instinct for the art based on his mastery every single aspect of filmmaking.
> I think the reason these directors are all in their 50s is that studios aren't willing to trust younger directors as much
That's sort of my point... Until recently, every generation had it's great young directors. Seems that is no longer the case. Now you have to play the studio game before they give you a film, and by the time they do you're such a predictable and "safe" player that you can't make (or don't want to make) an edgy / important / risk-taking statement-making kind of film.
Sort of like punk rock, it takes a young and angsty person to take the kind of risks needed to push the envelope in interesting or artistically important ways. Once a director grows up, has kids and hits middle age, well they get a bit more boring, and it comes across in the toned down films they deliver. Lucas and Ridley Scott come to mind as two very capable directors that have "matured" enough to see that what matters is popular appeal and profitability. They start out as artists and end up as producers.
> but that just means there ARE up and coming directors in their 20s and 30s who are making low-budget short/art films, who have not yet found public appeal.
Absolutely! A24 films come to mind of course. They are about all that remains of the old way of making movies. Guys like Ari Aster come to mind. The sad part is I doubt we'll ever get a "mainstream" picture out of him. Hollywood and the masses have moved on from this kind of storytelling. So the "old way" of doing things has been relegated into some niche corner of limited commercial appeal.
Honestly I'm not quite sure how A24 manages to stay in business. They take a lot of chances for the limited budgets they are working with. Not all of their films are great, but all of their misses are interesting. At the end of the day what matters are they making enough money to keep going?
I don't understand how is A24 delivering the kind of high quality pictures that they are, while studios like Band/Empire/FullMoon (which seem to be in the same league, same small/mid budget arena, also seem to be taking the same kind of risks that have limited commercial appeal) can't deliver anything beyond direct-to-video and MST3K quality films? I mean is A24 really profitable? Or is this a labor of love for them? If A24 was profitable you'd think someone in Hollywood would take notice.
Thank god for A24! Any film they produce is an automatic "goes on my watchlist".
Lastly, Jordan Peele is another name that comes to mind. I'm not quite sure how he's crossed over to more mainstream appeal, but I'm glad it's there, his films are great.
Anyhow my 2 cents, I understand this is all a matter of opinion.
To be fair both Kubrick and Tarkovsky probably felt dwarfed by the likes of Vertov, Eisenstein, or even Chaplin. Specifically in terms of pushing the envelope. These were different times with different envelopes.
Villeneuve innovates in a different space, maybe not as philosophical as Tartovsky, and not as symbolic as Fellini... but I don't think that language and that storytelling would work nowadays anyway. There is also Nolan with his very sophisticated world building. Yes it's all pretty mainstream, but so was Kubrick and Tarkovsky (at least in the USSR).
You mention Tarantino (which I personally don't like), but there are many lesser known directors from the 90s-2000s with a fantastic filmography. Kim Ki-Duk and Noel Gaspar come to mind. The world of cinema has not stalled, maybe we need to look outside of Hollywood more eagerly (but then again, neither Fellini nor Tarkovsky where Hollywood).
I love the interesting stuff coming out of South Korea. It's great to see foreign directors getting their due again.
I get why Tarantino divides people. He's sort of low brow, lowest common denominator cinema. But he loves spectacle, and he knows how to make things cinematic. In my mind, he's America's answer to Leone. Flashbacks and non linear storytelling, larger than life characters with larger than life conflicts, and use of music as a central part of the film experience. In many ways you could argue he's been copying Leone's style his entire career.
I miss Leone. We got so few films from him. But what films! No one other than Tarntino/Rodriguez (maybe Coen brothers) has really carried any of this kind of cinematic storytelling forward. Tarantino at his best has Leones sense of timing, subtle wit, conflict, and ability to suprise. But they miss most of the subtleties Leone brought, the subtext of humanity and tragedy hiding just below the surface of his films. Tarantino is simply spectacle, Leone was something greater.
I think perhaps your friends need to expand their circle of interest when it comes to film. The film industry is full brilliant up-and-comers with very distinct voices doing original works:
Ari Aster,
The Safdie Brothers,
Robert Eggers,
Daniels,
Greta Gerwig,
Rose Glass
I love this list... especially fond of Aster.. these are some great young directors, when given the opportunity they'll deliver something worth watching.
Notice there is a lot of overlap with A24 here.
As important as these voices are, they aren't "up and coming" directors in the classic sense. The studio system isn't interested in giving anyone here the chance to do something larger with more mainstream impact. These directors seem to be relegated to indie films, as Hollywood is no longer interested in risk taking.
To clarify: I'm not saying these aren't great directors, they are. I'm saying Hollywood doesn't want to work with this kind of talent, is no longer capable of developing this kind of talent, and wont take the kind of risks necessary to deliver the kinds of films they used to be able to using this kind of talent.
Spielberg and Tarantino are household names, because of the studio films they made. These other directors will likely never have that much mainstream appeal.
I suppose another thing that the people on my list have in common is that they're all writer/directors.
You could also say that most of them also fall into the category of "auteur" as well. Though that can be a little bit of a loaded term, so the individuals might reject that designation, even if they do embody it.
One director who does stand out as doing well-regarded indie stuff and now blockbuster films is Chloe Zhao. I haven't actually seen any of her films and couldn't comment on the content of her work, but she seems to check your criteria, if only on a surface level (nothing against Chloe).
What about Christopher Nolan? He seems to be winning all fronts as someone who is in bed with major studios, has wide critical acclaim, commercial success, and makes bold, creative movies. I guess he's not up-and-coming, though.
What I‘d gather about him over the decades of work, is that he deliberately uses provocation/expressive words for his art/communication.
I think in the context of that little clip he was hinting at the ruthless commercialisation of American cinema/comics; and indeed since then it had well developed to today‘s Marvelization of Hollywood[0], a multi-billion industry of its own.
He is 93 now, so I think he doesn’t give a shit about anything at this point, but I like to think that back then as a young artist he would have embraced/explored/experimented with AI generated good shit to enhance/help his artistic vision. In the end it seems that mattered to him most.
Commercialization and info overload has diluted the impact of ALL art to just sensory stimulation.
After the oohs and aahs there is nothing else going on in anyones head, cause there is always something else thrown infront of them on their infinite streams.
And while AI generated art is just another tool in a giant warehouse of ever expanding tools, who gives a shit?
Cause take a look around at the impact of the best of the best. There is none.
>And while AI generated art is just another tool in a giant warehouse of ever expanding tools, who gives a shit? Cause take a look around at the impact of the best of the best. There is none.
The quality of that “tool” in particular is imho markedly different as opposed to non-AI digital tools. It opens up a space of possibilities for “visual art” which is now tangentially comparable to the impact of computers (i.e. computations per unit time) to the art of proofs in mathematics. One way of using its power is by calculating pi to the n-th place (“eye candy” in “visual art speak”) or another to overcome the sheer amount of calculations necessary (technical limitations) for a viable proof.[0] If there is one way to prove it can inspire confidence for a more elegant/aesthetically pleasing/understandable proof.
As for the impact, I agree, we have yet to see. Maybe I’m too optimistic.
One [1] of my favourite music clips from now over 20 years ago which looks (in its sterility) entirely AI/computer generated but actually is modelled frame by frame in Lightwave 3D (by the artist Alex Rutterford).
>The quality of that “tool” in particular is imho markedly different as opposed to non-AI digital tools.
Do you remember the printing press? Computers? How is it different than just another jump in magnitude of production (if it pans out to establish itself as such to begin with)?
It seems like a continuation of the same process which is what grandparent seemed to be saying
I don't believe that anyone who says anything about how X or Y as a Jodorowsky movie would have been $positiveHyperbole has seen anything other than the documentary about the unmade Dune movie.
First, because his most compelling stuff is heavily surrealist and I've found the audience for that is niche and has very little overlap with what modern Sci-Fi/Fantasy fans have in mind. Second, because at this point whatever they have in their minds for what it would have been is likely an impossible standard for any director, much less the one that made El Topo or The Dance of Reality (not a slight, just pointing out this guy makes art pieces - not blockbusters).
I experimented with midjourney and while it produced some interesting pieces I couldn't imagine creating something like these tron images with it. Like I couldn't get midjourney to even create a proper looking chess piece for instance
Having read the responses of the guy that generated these, the prompt is as simple as
production still from 1976 of Jodorowsky's TRON, 20 ASA 35mm --v 4 --ar 3:2
production still in version 4 doing most of the heavy lifting, with the year and film propeties giving a bit more vibe, and of course the overarching theme of TRON in the style of Jodorowsky. Add some extra words to differentiate scenes, such as light cycle or disc or computer. Add wide aspect ratio, and that's it. So it's 99% Midjourney. Mind blowing.
I was about to say 'I can't tell if this is AI generated or not at this point' mostly as a joke based on first impressions, but it's actually shocking that it turns out to be.
Version 4 of Midjourney, released 2-3 weeks ago, is an outrageous improvement over all previous versions of Midjourney, and has gone mostly unnoticed by HN. IMO, v4 Midjourney is to DALLE2 what DALLE2 was to all previous AI art generation.
However while there is an awful lot of 'background symmetry' AI seems woefully incapable of 'human figure' symmetry that, to me anyway, it really sticks out. Eyes not quite the same size, breasts pointing in markedly different directions, bone structure on the face markedly different to each side.
To that end I am also amazed at how forgiving our brains are for this stuff (a bit like being able to listen to music over a fuzzy, in/out AM station without much bother).
Anyway, thanks to whoever made this. I think there could be a market in 'imaginary film posters'.
P.S. Did it really need the 'Disney' logo on it though?
While we're generally symmetrical, the human body is full of wonderful irregularities -- different sized eyes or slightly longer/shorter limbs etc are exceedingly common.
> To that end I am also amazed at how forgiving our brains are for this stuff (a bit like being able to listen to music over a fuzzy, in/out AM station without much bother).
My brain was so forgiving that I didn't even really notice the asymmetries until I looked at the images a second time after reading your comment. I agree that especially in the case of eyes it distracts a bit. Those are generally pretty symmetrical (I say, with one eye that is always a bit narrower compared to the other ^^)
This is the most interesting aspect of all of this. It works for music, too: what if your audio playback device could modify a song in real-time to add or remove instruments, or play in a different style. The same could be done with a movie. This also has great applications for musicians looking to learn a piece. YouTube's ability to slow a video without modifying pitch has been really great for this application, too.
You can already do vocal replacement and create new covers of old songs.
High quality pitch matching and vocal replacement is here [1] and is going to be big. You can generate Smash Mouth's "All Star" as every single president, celebrity, vocalist, or cartoon character. Or whatever you feed it.
Within the next year the field will move onto changing instrumentals and generating novel tracks.
[1] The tool I've written and will be deploying as the next version of FakeYou.com does this at high fidelity
This feels like a peek at the first truly practical application of AI art beyond “I need a blurry illustration for my blog post”. I could easily imagine this as the first step in an art director's creative process of exploring the look of a project quickly and iteratively, yet at high fidelity.
Even with the unavoidable AI artifacts, the aesthetic of these images is incredibly evocative.
I could easily imagine this as the first step in an art director's creative process
I had a similar thought. What will AI-generated images means for production designers in film? Will the easy availability of AI images redefine a whole class of design or artist roles? Only time will tell, but I suspect it will happen quickly.
The amount of time it would take to edit these to remove the subtle AI nonsense/artifacts/dysmorphia is a fraction of that time it would take to make the images from scratch. There will still be art departments but they will be 10x smaller.
E.g., here, I'm skeptical about the specular reflections, which show a blue light on the left, a yellow light on the right, and a (seemingly) physically-accurate transition down the middle. Plus the too-plausible DOF in the background.
Yea, I could eat crow but I don't see any of the typical artifacts here, detail remains coherent all the way down. "Big if true", wouldn't it be simple for these images to be distributed with a signature by the midjourney API so that us doubters could check which version of the algorithm was used?
I get ya both. But, I frequently see plausible-ish reflections and DOF in MJ generations. Usually there is some error you have to look for. For example, 2 out of 3 windows reflected.
To my eye, they are clearly synthetic elements composited together in Photoshop or similar with a keen artistic, human eye. Doesn't keep it from being amazing, but there's no way these faux film stills are coming straight out of a generator.
It's plausible that this is a fake, but consider that what you described is based on reasonably simple physics, something than AI that's capable of generating human faces could likely figure out.
What makes me believe this is actually AI generated art is the hands. They're all fucked up, in every image. I don't know why, but all image generation AIs I've seen struggle with the human hand.
Why aren't film producers throwing money at Jodorowsky? The visuals and stories he'd tell would surely be mind blowing. (I ofc know these are AI generated images, but it still makes me wonder.) For instance I'm certain that it's his influence that made Nicolas Winding Refn make Neon Demon.
It's extremely difficult to make new "cult" cinema deliberately; this kind of thing (especially the psychadelia influences) is simply out of style, and middle-budget pictures are vanishing.
The nearest thing you might find today .. maybe Valerian and the City of a Thousand Planets? Luc Besson has some of the same pulp influences.
Maybe we just skip the middle steps and have the AI make the film.
It would be cool if these AI tools ushered in an era of low-budget cult movies that have the visual effects of big budget movies. Think a few college students with a green screen in the garage producing epic sci-fi.
It's only a matter of time before we get there. Models will be built for film. It's a matter of scaling the resources. I'd imagine the computing increase would be mostly proportional to the number of frames to be generated.
> The nearest thing you might find today .. maybe Valerian and the City of a Thousand Planets? Luc Besson has some of the same pulp influences.
Yes. Valérian is on the mainstream side of that 1980s sci-fi movement. One of the authors also was an artist for the Fifh Element. And a heavy influence on George Lucas (several Star Wars scenes are straight out of Valérian).
> Maybe we just skip the middle steps and have the AI make the film.
Several of these artists would have loved to have AIs to use back in the day. Very fitting in the whole artistic project.
He’s been groundbreaking since the 1970s or so. He’s a difficult person to work with and he’s very opinionated and hates Hollywood, though, which probably does not help.
Holy Mountain made big chunks of money. Jodorowsky is the only alt/psychedelic filmmaker I know of who ever made money. That’s how he got to keep making films.
After the Holy Mountain in 1973, it wasn't until 1989 he made another proper 'Jodorowsky' movie. Then until the 2010s when he was able to make two more films from crowdfunding. I don't think his films have made much money at all, compared to someone like Lynch who was able to get movies made for a long time.
My impression from watching the Dune documentary is he couldn’t get money to get the movies he wanted to make.
So he turned to graphic novels with Moebius, which I believe were successful (leading him to make a lot of them with a variety of artists - Manara, Jimenez).
My impression from the Dune documentary is he could find enough funding to pay for all the pre production work that now is in the book, which including hiring 3-4 artists. So I’m not sure he stop making films because he couldn’t get the funding, since the impression is he got enough to pay for those guys to work for him for a while.
Hmmm from the Dune documentary Holy Mountain was a “hit”, particularly in Europe. That’s why he got funding to work on pre production for a Dune film, hired multiple artists to work on it for a period of time etc.
The box office you’re quoting is from a re-issue. It says right there on the page.
Again if you watch the Dune documentary, it’s stated there that:
- holy Mountain did relatively well at the box office
- that led producers to fund concept stage for his next idea, Dune
If the documentary is innacurate I don’t know. But that’s there, from memory.
It was a critical hit, but not financial. It’s an interesting movie and I’m glad it was made. I would never invest in it. Making Jodorowsky’s movies is like art patronage.
Im not sure how the documentary producers substantiated their claim, so I linked to a pretty reputable source that describes the budget and box office.
I have, and I think they're epic. That's why I think Jodorowsky has a big cult following that would have made it a financially sound idea to give him both money and creative freedom to make more movies.
"Dune, the greatest film that was never made" looked like it could have been incredible. Both casting and asthetic was in place, with the story they had it would have taken that film in a different and some would say more interesting direction.
Still very much a fan of how Villeneuve is handling things now with this established direction.
Villeneuve's movie as of now lacks some visual ambition and punch, and these "BADASS!" Momoa action scenes lowered its value, and the soundtrack felt generic.
I'd say the Dune 1984 "Alternative Edition Redux" remains the best version, yet. It's available on Youtube and definitely worth a watch,
Because as visually interesting as his films are they are barely watchable. I love how insane they are and I love the imagery but I've never watched one twice.
Having had the pleasure of listening to Chris Foss (concept artist for Dune) talk about it, it seems that Jodorosky and his circle were simply too drunk and/or high at that point to actually complete a movie.
if you watch the documentary "jodorosky's dune" he goes over it, and basically boiling down to the studios "liking the concept" but "not getting the director" especially that he wanted total creative freedom and to make the movie as long as he saw fit, but studios wanting a smaller budget and 90mins etc
btw, the incredible storyboards for dune are a feast if you can bits that are floating around
> studios "liking the concept" but "not getting the director"
It's funny to think about in context of the film eventually going to David Lynch. "Good thing this Lynch guy's a straight shooter, not a weirdo like that Jodorowsky fellow!" (Different producers/studios, I know, but still...)
"Why aren't film producers throwing money at Jodorowsky?"
Jodorowsky had some gargantuesque approach to managing film budgets. Not saying it's justified but studios at the time were likely scared of financing him. The Dune debacle was a precedent.
My guess would be that he knows what he wants and wouldn't dance to their fiddle, plus his ideas and methods must seem super risky from a producer's perspective.
I'm having trouble believing an AI did this. I mean, I know it did, and I trust HN to call BS. But ... it's just too perfectly imperfect. You can almost spot the cardboard headwear. I literally can't convince myself an AI did it. It's a weird feeling I'm experiencing.
The art cliche "hands are hard" strikes again. Lucid dreamers also describe hands not looking right in dreams, using it as a tell that they are dreaming. I've also seen my hands look like these pictures when taking LSD. With merged fingers etc.
Looking at my hands and counting 5 fingers is definitely comforting.
it's too good and if real im very impressed. these are the best AI generated images ive ever seen, they fit the theme almost too perfectly. I want to see the prompts that made something of this caliber
> There seems to be a current trend in AI circles of mashing up film genres or visualising existent films either within different time periods or with different directors.
Out of boredom, I fed the prompt "Fight Club" into Stable Diffusion, and it generated some interesting images of a human that looked like a mixture of Brad Pitt and Edward Norton.
I've seen similar mixed up results when I type a prompt that includes two obscure animals, such as "an emu playing chess with a lemur". The AI spits out an animal that looks like a cross between an emu and a lemur, instead of the two separate animals playing chess.
I want to know more about how these algorithms work, but that level of detail is hard for me to comprehend. I remember struggling in my college algorithms class to write code to do something relatively simple: I think the assignment was to: given a XY plane with a set of points, I had to find a set of lines that would create an intersection of polygons that contained only one point each.
These prompts remind me of how I always thought that the way Star Trek characters "authored" holodeck scenes with just a few words were utterly unrealistic, even by Star Trek standards. Ouch
I was about to reply to the skepticism of a poster, who deleted the post in the meantime:
This is a clear context in which re-doing something in the style of some Author can be radically inappropriate:
the visual style is stunningly good, but an unintelligent operation - it is relatively easy to mock a style, while the real thing was the judgement underneath. The Author knows if and why he would have used a curve made in such way in that place - not the simple mocker.
Edit:
in case some wanted to advance the idea that they are contented with the visuals, AJ is a foremost example of visuals studied to serve a content. Not to mention his declared contempt against states of poor hallucination.
You must mean «his declared contempt against states of poor hallucination» (pls avoid improper ambiguity): no, he had contemptuous terms for drug users he worked with.
Look at the flickering faces in the original Tron's composite screens, grainy high contrast black and white just tinted a little. That's a very deliberate choice, and given the prominence of Metropolis chances aren't small that the inspiration wasn't just any silent era look (granted, they all looked like that), but straight from Fritz Lang.
What do you think are the odds that we'll see a feature length AI powered "Jodorowsky's Tron" film within say.. the next 20 years? Some shepherding by humans allowed of course.
Would definitely want to watch it! That synthetic style (synthetic, as in "put-together" as well as in "created by technology") nicely picks up the expressionist high-contrast b/w that was so great in the original Tron's composite images and applies its attitude to the other visual dimensions as well.
If Jeff Bezos were to fall in love with that look and indulge in another of his "it's my money and I want to see it!" film hobbies, I wonder if a well-funded team like that could actually pick up the look and make it a movie reality? Or would they inevitably fail to capture the magic and churn out yet another interchangeable cgi rumble?
I think you seriously underestimate the pace of AI innovation these days. My conservative guess is 5 years for a single-human-supervised full length movie of this sort.
All I can think when I see this stuff is that the end is nigh. I'd assumed we'd have artificial intelligence before artificial creativity but it looks like nope.
One image has a recognizable Han Solo, with classic outfit, side parting, but not quite Ford's face. A weird cut'n'paste from the conceptual-visual space.
Endless Poetry (Poesia sin Fin) was for me one of the most beautiful and touching movies I ever watched - yet, it certainly was also very tough to watch at times. Some scenes pushed the cringyness factor to the limit. Other scenes were so mesmerizing that I'm coming back to them from time to time.
These graphics are amazing. I had to tweak the site just a little and the imagery is even easier to view... set the body to background:#000; and color:#eee; remove the float:left and set the main to width:100% - zoom the content 3 times and feast your eyes on amazing graphics.
This is my favorite "use" of AI generation. Imagining art in the style of artists who've passed away but in new settings and contexts. Unable to share right now but people like F.W. Murnau, Matisse, Paul Gauguin, etc
I suspect that something like this is running already on scripts and vfx and that explains some of the really mediocre content from Netflix, Disney, etc (ie, “they don’t make ‘em like they used to”).
This is incredible and beautiful. I think that as technologists we need to embrace this evolution, which will touch all areas of our work, or be left behind.
I can't tell if the people commenting are realizing that or not. In any case AI design ... I don't know, if I was a skeptic before I'm definitely curious now.
It does make me think about the legal implications. This reminds me about the makers of the song "blurred lines" getting sued by the estate of Marvin Gaye. To listen to that song and "Got to Give It Up" by Gaye is (to my mind) acknowledge that they didn't exactly take the song with out credit buy they did (to reference the Apple v. Microsoft case) take the look and feel.
INAL so I can't square those two cases in my mind (Gaye's estate won and Apple lost) but this really suggests that:
A - copyright is idiotic on some level
B - there's going to be a lot more of that type of case
Before I understood it was AI, I found it odd that some of the women were somewhat sexualized visually. That seemed to be a bit disconnected from the idea that this is a machine world where I expect it to be emotionless, sexless.
You may disagree but to me it points out the shortcomings still present in AI art — a lack of the ability to make editorial decisions.
Except the machine world in Tron has never been presented as emotionless or sexless. The plot of Tron 2 literally involves a budding romance between the protagonist and a hot computer girl. The franchise's lack of overt sexuality is due more to it being a Disney property than anything, but they didn't hire Olivia Wilde for her acting skills.
Plus, one could imagine the Jodorowsky version of Tron simply making different editorial decisions. It isn't as if fetishizing technology is unheard of - it was HR Giger's entire thing, and it goes back all the way to Metropolis.
Obviously this wasn't the result of a conscious application of vision, but it could very well have been.
The headline doesn't mention AI art, but it doesn't really imply that it's actually Jodorowski's work either. "Jodorowski's Tron" might have, but "Fantasy Jodorowski's Tron visualizations" strongly implies that this is some other artist's idea of what a Jodorowski Tron movie from an alternate universe might have looked like, which is pretty much the case.
There was nothing deceptive or clickbaity in the title, is what I'm saying.
Ah. So it’s a fast-takeoff then. Looking forward to being enslaved by the elites with AI being used as a wall to separate billionaires from everybody else.
Only huge multinational corporations can fund the production of movies like Dune and Tron today, and if anything it seems like this phase of ai art is surprisingly scrappy/democratic/grassroots and not hidden behind a billionaires lock and key.
This is why I'm very suspicious of any push for AI regulation in the guise of "safety", etc. There's just too much money involved to trust the motives.
