Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?
This is your opportunity to ask questions. No question too simple or too silly.
Culture war topics are accepted, and proposals for a better intro post are appreciated.
Jump in the discussion.
No email address required.
Notes -
AI videos. Have you seen any good short films that were made with the use of GenAI tools, in entirety or in large part? I don't mean oneshot from prompt to full movie, it can be any kind of multistep process where the creator may generate character sheet images with one model, then use a video model to make videos, and any other steps with AI models can be involved. I can only find a handful, and they aren't great. Though YouTube's search is notoriously broken anyway.
The ones I could find are very flat storywise and are more like a techdemo, packed with action movie shots. I'd be interested in a more story and character-driven one or just anything where the filmmaker wants to tell a story. Less "I wanted to geek out with AI tools so I have to come up with a story for this movie now", more "I wanted to make a movie and now AI makes it possible and simple to realize my vision".
It seems that the story, the content is the harder part. Which isn't surprising, since having access to pen and paper / printing press / rich word processor software didn't suddenly turn everyone into a book author either. The bottleneck is having something to say.
Or perhaps the human acting performance is just too subpar for creative people to accept it as of yet. I mean that the people / characters in a generated AI video often seem to express emotions in an uncanny way etc.
Or perhaps all creatives who would have story ideas and execution capability don't use it because A) they are strongly anti-AI of the bluesky sort, or B) they anyway have access to friends who can act for their short films and it's more fun to do it with other people for such non-nerd creative types. or perhaps C) the latest generation of AI tools need more time to penetrate the creative spaces because they are still mostly present in tech-geek spaces only, i.e. creative types don't yet know about how good the latest models are and have dismissed them months ago when they were worse. or maybe D) creatives have very low tolerance of deviating from their vision, and current models are too random and too hard to control for them to be a good vessel to carry their vision and ideas.
The stories themselves are pretty easy. There's a lot of people who already had 'stories' in their heads that they wanted to bring to the screen, to the point where script-fic is a little derogatory in fanfic spaces. And we're at the point where you can give an LLM a pretty rough idea and get a coherent story out from them (cw: 30k words AI-generated story, painfully full of obvious spaces for improvement and still about on par with recent Disney output).
The tech's just hard. There's people messing with it, and for short periods you can get human-like emotion and acting, especially if you're open to pretty non-standard definitions of human (cw: sound, hellhound with human teeth). And then the background fades into a dream, or the character suddenly looks subtly different, or things start clipping, or the lipflaps don't match up with the actions.
Some of that's because people are just dabbling hobbyists: if there are people building their own unique voice clones, converting renders or live video into to pose2video work, or doing a lot of layering, there's definitely no one publicly doing all of those things combined. There's probably a way to make it work, by exploiting first-frame-last-frame and controlnet. But that requires a pretty sizable set of storyboards, and a stronger vision, and the ability to maintain focus when you're presented with something close but not quite good enough..
It's also just hard to do at home. Wan2 or LTX kinda work on an nVidia 3090 or better, but it's minutes-per-generation in the simplest cases. Add on that overhead and it can take the better part of an hour to make a single ten-second clip. With the right workflow or tooling you might be able to make that work out - that's still about a week per hour of video - but right now those workflows are things you'd have to build yourself.
I'd expect we'll eventually get some sketch-focused artist or rough animation-focused modeler working directly with them, and it'll have some major benefits, but I couldn't tell if you if that'll be a weeks, months, or years.
Higgsfield is making some series with Seedance 2.0 and Nano Banana:
https://youtube.com/watch?v=LQ-vSa9_H98 https://youtube.com/watch?v=digHr6k38x0
I just can't stand watching this genre (superhero action movie or whatever), more than 30 seconds at a time, but it looks fine on a technical level. It would be great to have something with a bit more interesting story.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
The revisited Harry Potter by Balenciaga is both hilarious and surprisingly a genuinely good parody. There are still AI tells all over the place but they honestly don't distract from the short film itself.
It also desperately needs a fanfic that tells the back story of howFilch became like that .
More options
Context Copy link
Breaking Balenciaga is the best I’m aware of.
I watched some of it and it’s…mid. My problem with AI art is that it’s all mid. Although here the idea is also mid.
I feel that so far, even good GenAI is either an excellent idea or lucky (or trial-and-error) output, and in both cases a real artist could’ve executed better. Even for works where more effort would be wasted, like jokes and concept art, I prefer a simple handmade drawing like a sketch.
The one exception may be hidden images via Stable Diffusion ControlNet (e.g. text, QR code, spiral), because I haven’t seen any human-made pictures nearly as detailed and seamless. Also, GenAI is great for intentionally bad works, like memes making fun of AI.
GenAI is genuinely useful for routine tasks, forms, etc. where quality isn’t important; and with code, where quality is only important to an extent (nobody will notice your micro-optimizations or unnecessarily readable implementation) and there are decent objective metrics (lints and tests, and I still think AI code is hard to read). But art has no practical limit to quality, and good artists apply themselves to every noticeable detail. Also, art (like music, food, and attractiveness) is best slightly imperfect, in a way that human amateurs execute without trying, and experts learn (“learn the rules, then break them”), but AI seems to struggle.
You may like Harry potter by balenciaga
I think AI acting is getting better and maybe more serious stories could also be told, see for example this proof of concept (the actual content of what she's yapping about is quite boring, but the facial expressions and voice tone are getting more and more realistic).
I agree it’s getting better.
Although I think it will only surpass human art if/when the user has fine-grained control, because my favorite art is that I can relate to, and a general LLM isn’t relatable. I’d rather use AI to make art I really like (even with difficulty, as long as there’s a clear progression…I’ve wanted to get into art, but it’s overwhelming and I’m particularly bad at it), than have the AI autonomously make something I mildly like.
Or if/when we get ASI.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
Not sure if it's what you're after (nor the creative process they're using), but the ongoing "Amelia" series on Brit-Twitter is producing coherent and effective political shorts on a fast timeline...
Political as in commenting on concrete British political events, or more like political drama as a genre?
To maybe specify better what I would like to see is stuff in the ballpark of this, just with better ideas: https://youtube.com/watch?v=bYW_7rWjQMs Or a good thriller, or something psychological, or a good scifi that makes you think etc.
I guess a good start for people with fewer ideas would be to do film adaptations of interesting online short stories or highly upvoted nosleep stories, or even just regular short stories that appeared in print over the last 50 years or more.
Very much the former -- it's an unabashed propaganda campaign that would be completely unsurprising if it were done conventionally by some government hiring actors etc -- indeed it's in response to just such a campaign by the UK government!
What's interesting about it is that it seems to have been put together in a matter of days, by (as far as anyone knows!) non-state actors with limited resources and strong government operations. (the videos are probably illegal in the UK on the grounds of promoting hate)
So more of a worked example of AI videogens to create impact IRL than anything with much artistic merit. Just as handheld firearms democratized warfare (for a while), maybe publicly available AI (plus social media) will democratize the mobilization of egregores upon the genpop?
https://x.com/LBC/status/2015894345770045489 (MSM backgrounder)
https://x.com/ABridgen/status/2013157247820406995 (first video)
https://x.com/AmeliajakSolana (whoever's doing the videos -- I notice they've pretty much switched to images now, so probably Sora is indeed what they were using -- you'd need to scroll way down for the rest of the videos, they were coming out regularly a few months ago)
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link