Matrix trailer dynamically uses current time

Post by EGreg » Tue, Sep 07, 2021, 6:29 PM UTC

echelon wrote: post #33

TYPE_FASTER wrote: post #25

Each segment of the trailer is a different MP4. They are all hosted on the AWS CloudFront CDN. My guess is, like somebody stated, they pre-rendered many videos, and use a lambda at the edge to decode a GUID in the URL into a S3 path.

They probably used concatenative audio rendering since the digits are tractable to get the actor to record. (Probably just on the borderline in terms of effort for now.) But can you imagine when they are able to use real time text to speech with high fidelity? We're not far from emotive TTS + photo realistic rendering in a real time engine, potentially with neurally generated models to match real time events or camer…

Post by Apocryphon » Tue, Sep 07, 2021, 6:31 PM UTC

arthurcolle wrote: post #42

yitchelle wrote: post #27

Earlier quoted context omitted.

Hopefully, his character Agent Smith is still in?

I don't think so, Neil Patrick Harris might be playing an equivalent role it seems like. The old storyline is done, this is now the present or near future or so it seems. Kind of alluding to "you don't need super tactical Agents, you can just give them a pill and a nice Chardonn... er.. cellphone and distract people into oblivion."

Post by rezmason » Tue, Sep 07, 2021, 6:32 PM UTC

yitchelle wrote: post #17

Who had the Matrix screen saver back in the day? I was in an open plan office at the time of about 30 desks. Every single one of the machines had this screen saver running.

Post by jjoonathan » Tue, Sep 07, 2021, 6:35 PM UTC

echelon wrote: post #44

jjoonathan wrote: post #39

Earlier quoted context omitted.

What does the state of the art look like? I'm not following closely enough to know, I only get an update when something leaks into the meme-o-sphere, like the recent "World Leaders singing Numa Numa:" https://www.youtube.com/watch?v=Y8CKlTlQA64

Here's my stupid text to speech website: https://vo.codes And you can try the alpha of "version 2" by visiting this, which has improvements in synthesis and vocoder quality, and also lets people contribute: https://api.vo.codes/enable This is far from state of the art, but you can see at the other end of the spectrum that it's an easy toy that anybody can use. I'm working on a photo -> 3D rigged model system and mode…

Post by robertlagrant » Tue, Sep 07, 2021, 6:36 PM UTC

prox wrote: post #53

2Gkashmiri wrote: post #22

this is kinda nice. you see guys, there is no need to look at the correct time and go and use "AI" to generate the speech and text in real time using the latest and greatest in tech. you can just as simply pre record all time 1 to 59 and then join them. much easier and i dare say, much more elegant

It’s not a recording. Modern video editors/compositors can do batches with dynamic content. So someone had a list and just rendered all the segments out.