Terry Gilliam has had such a hard time trying to fund his last few projects that he’s hinted about retirement. However, back in April, fansite Gilliam Dreams reported that the director was set to direct a new, maybe final, film, titled “The Carnival at the End of Days.”
This past May, Gilliam claimed he had found funding for ‘Carnival.’ We already know that Johnny Depp will play Satan and that the rest of the cast would be composed of Jeff Bridges, Adam Driver and Jason Momoa. A January 2025 shoot was being eyed. (via Premiere)
No surprise, five months later, Gilliam is now telling Czech media that he doesn’t have the sufficient funds to make ‘Carnival,’ and that he would have to creatively compromise his vision to make it happen (via Novinky).
I don’t have all of the money for it right now. I would have to compromise some of my ideas. Which I don’t want to. I’m angry with myself for not being able to do it. Which is not always a bad thing. When I get angry, some interesting ideas come out […] Maybe I’ll start shooting it soon, albeit with a smaller budget.
…
Here’s Gilliam describing the plot of ‘Carnival’:
This is a simple tale of God wiping out humanity for fucking up his beautiful garden Earth. There’s only one character who’s trying to save humanity and that’s Satan, because without humanity he’s lost his job and he’s an eternal character and so to live without a job is terrible. So he finds some young people and he tries to convince God that these young people are the new Adam and Eve. God still gets to wipe out humanity. It’s a comedy.
The last time Gilliam directed a feature was 2018’s “The Man Who Killed Don Quixote,” a film he was trying to make for more than two decades. It came and went without much excitement, although I thought it was his, de facto, best film since the late ‘90s. The lack of commercial success on ‘Don Quixote’ is essentially the reason why Gilliam can’t find funding for his next projects. His films of the last 25 years have been both critical and commercial misfires.
His films of the last 25 years have been both critical and commercial misfires.
That’s the problem and that plot outline, while sounding like something he can get his teeth into, doesn’t have the look of box office gold.
Convincing execs to give him Depp/Bridges/Momoa money without a decent return is a huge ask.
I wonder if he’s in a tricky position where he needs big names attached to get funding.
“That’s a wild idea Terry, but who’s starring in it that I’ve heard of?”
It seems to date back to The Fisher King after he ran out of Python momentum in the 80s.
He never had enough money to make any of his movies.
In total sincerity - this is what video generators will be for. Letting the robot make it all up from one sentence is an overblown demo. Anyone with a killer script and a great visual imagination should be able to make a two-hour film instead of a comic book.
The technology modifies existing frames. If you feed in some actors doing a scene, and describe what it’s supposed to look like, you should get out dirt-cheap CGI to fix up all the details. The closer the input looks, when blurred, the better the results should be. So if the script says the clouds part and a giant hand gives us the finger, well, grab some pillows and a ladder.
Or, this being Terry fucking Gilliam, animate some flat cutouts, and have the computer make that visual punchline plausible.
So… “use AI”?
If you want to oversimplify future expectations of a brand-new technology to two loaded words.
The people insisting it’ll never be useful are as off-base as the grifters insisting it’s the next everything. Right now, on consumer hardware, you can take a photograph of a toy spaceship and tell your video card to make it look real, and it will. No kidding we’re gonna see that used professionally.
Even if we’re still way too early - sometimes the alternative is that a thing does not get made. Fancy new ways of faking stuff don’t need to be flawless, when they’re competing with non-existence. Early special effects were laughable. Early CGI was hideous. But they did things a production couldn’t possibly do, or couldn’t afford to do. If this stew of linear algebra and pirated DVDs lets weirdos like Gilliam show us a mildly gloopy version of what’s going on his head, with a budget he can scrounge together in less than thirty goddamn years - great. I’d rather have a mildly gloopy movie than what-ifs.
Right now, on consumer hardware, you can take a photograph of a toy spaceship and tell your video card to make it look real, *and it will.*
Out of curiosity, what can you use for that? I haven’t kept up with AI, but that sounds like the sort of thing that my kid would love to try :)
Stable Diffusion seems to be the done thing. Apparently you provide a list of tags with numeric weights, and it “denoises” all the ways the image doesn’t fit. From-scratch images are generated from a canvas full of random noise.
Basically “remove all the marble that doesn’t look like a statue.” The missile knows where it is because it knows where it is not.
Ah, ok. I thought it was just for generating from scratch. I’ll give it a try, thanks :)
