Surreality

◥◣ Building imaginary worlds.

[Surreality @svrreality]

In which @jwz takes a stab at rendering Borges' Library of Babel: 1. https://t.co/swG0h8UZXW 2. https://t.co/IP5rfWakAD (cc @Oniropolis)

[PJ Ace @PJaccetturo]

Gossip Goblin is arguably the best AI filmmaker in the world.

His new film THE PATCHWRIGHT is a masterpiece (10M+ views).

But nobody knows how he actually makes these.
Until now.

He let me share every step of the workflow with you 🧵👇

[梶谷健人 @kajikent]

これまでに見たAI生成動画作品の中で圧倒的によく出来てる。

今までのAI生成動画は数分くらいしか観てられないけど、これなら映画くらいの長さでも観てられるかも

[Not Jerome Powell @alifarhat79]

Wow this video has racked 5 million views already. AI is crazy

[Mr. Star Spangled MAGA @4thOfJuly365]

I bet this is exactly what it looked like.

[Làzaro @lazaro45ive]

I spent 20 days creating these 20 seconds

[taoki @justalexoki]

idgaf about the ram prices. i want more of whatever this is

[Framer 🇱🇹 @Framer_X]

This tool is insane.

Upload any image.
Move camera in 3D space.
And get a completely new camera angle 🤯

Also it’s free! 👇

[el.cine @EHuanglu]

this is the biggest revolution in film history

AI can literally make an entire transformer film in days.. they say Seedance 3.0 can generate 5mins film in one shot

[Alan The Alchemist @Alanv1988]

In 2010 I smoked some purple 5x strong Salvia thing off the internet.

I filled my party bowl up in my 3ft bong and ripped the biggest hit I could handle and held it for as long as possible.

I then melted into the couch and became the handle of a shopping cart looking up at some lady I never met pushing me.

[Matt Van Horn @mvanhorn]

I grew up in the biz - my dad produced Independence Day, my mom worked on Seinfeld. I've seen firsthand what it costs to create worlds on screen. This video from the @thedorbrothers below is mind-blowing.

Software is going through the same shift right now. Writing code is no longer the bottleneck, knowing what to build is. Film is next.

But production was never really the magic. The magic was always taste, story, and knowing your audience. The barrier to making something is collapsing to zero. The barrier to making something *great* never changes.

The real golden age of storytelling is about to begin.

[Michael Kutsche @michaelkutsche]

I'm stating the below as someone who has worked extensively at the cutting edge of AI augmented filmmaking for the past three years (part of it inside of a program at one of the big studios here LA), so I have pretty good insight into the whole process:

I would argue that the most important parts of filmmaking, story and authentic design of the characters and world, will take longer than 2-3 weeks to develop for a good movie, and this is the part that filmmakers still want (and should) control.

The more they put themselves into it, and the more they see AI as a powerful rendering and VFX engine (as opposed to an idea engine), the more they will differentiate their work from automated "slop".

I also believe there will always be a shortage in compelling ideas, regardless of how much AI tools will reshape the process.
Original ideas and the limits of human imagination will still be the bottleneck (which is the main reason why most of what we see people creating with these tools and call film is in fact just "slop").

Regarding the speed of generation and the technical aspects, funding and new channels of distribution, I believe Schrader's prediction is pretty accurate.

What all these very opinionated critics of AI augmented filmmaking don't get, is that no filmmaker ever enjoyed the tedious (and rarely successful) process of begging for 130M USD budgets at the studios to get their films made, and then waiting for another 3 years (after finishing principal photography!) to have an army of VFX artists finish it.
Most directors will happily skip those steps, which created nothing but friction in their pursuit of bringing their vision to life.

And with the tools evolving so rapidly, these movies will look even less CG and closer to the director's original vision than any VFX-laden Hollywood blockbuster.

Imagine if Kubrick had been able to create many more of his iconic films during his lifetime.

This is where we're heading towards.

[Marcio Lima 利真 マルシオ 💎 @Preda2005]

My brain can’t process this…🤯

[el.cine @EHuanglu]

seedance 2.0 is the only model make me so scared

literally every job in film industry is gone, you upload a script, it generates scenes (not just clips) with vfx, voice, sfx, music all nicely edited, we may not even need editors anymore

and now I understand why it’s not available outside china

there are features that feel so illegal, you upload screenshots or storyboard frames from any movie, and it generates full scenes that feel like from the original movie, but its different and sometimes looks better

another feature is crazier, you upload any film clips, and you can just… edit anything.. like swap characters, add vfx, change bg, color grading..

at this point
maybe the only thing we still need is screenwriters because the stories AI write are still cliché but..

the machine is learning faster and faster

this feels like the quiet end of traditional film industry
and the beginning of something we dont know

[el.cine @EHuanglu]

oh my.. hows this even possible

Meta just dropped SAM 3D, you can auto select any object in still image and.. turn them into high quality 3D model

the model is free to download and test in playground

link in comments

[TweetingGaruga @TweetingGaruga]

I don't think I'll ever recover from the fact that the first episode of Uzumaki was the most perfectly crafted passionate adaptations that a fan of Junji Ito could hope for but the executives of anime industry decided to sabotage the rest of the production

[jon | super vhs @reaction105]

added some real world scale to the environment, makes the sense of speed wild

[cinesthetic. @TheCinesthetic]

This run is unbelievable.

[Travis Davids @MrDavids1]

This is BLITZ 🏍️ starring myself. I've tested a workflow that combines two of the best AI image editing models right now, Nano Banana and Seedream 4. Using these together feels like a superpower. Seedream 4 for instance generates much more dynamic camera angles BUT Nano Banana does a better job with overall consistency, so utilizing both is super beneficial.

I wanted to create a sequence where I'm riding a Cyberbike with an electric booster that overclocks the motor to deliver short, high-risk bursts of extreme speed. The location is a white sand desert.

I decided to also test @Hailuo_AI start and end frame feature which in my opinion is one of the best since it understands so much about context and camera movement.

Start and ends frames let you have much better control over camera movement but where Hailuo truly excels is that it understands speed and camera shake which are essential for any fast paced action sequences.

The music was generated with Suno 4.5+ and some additional sound effects like the bike and wind in the desert were sourced from Artlist. Edited with Capcut.

There's some more tips and tricks in the thread 👍👍

[Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex]

Genie 3 is the first videogen that has fully denied me my usual «animated stills» dismissal
these aren't animated stills, not even zoomed/panned/rotated stills, nor «hologram augmented stills» nor «NeRF on stilts». These are explorable spatial worlds that take a still as a seed.