I had a good laugh looking at the sliding and twisting legs in the "Girl walking in City" video.
I'm a little concerned that so many people in these comments say they wouldn't be able to tell that it's not real.
Sora: Creating video from text
151–160 of 1001 posts
Re: Sora: Creating video from text
#152This is bananas. This is ahead of anything else I've seen. The entire stock footage industry may be shut down over night because of something like this.
And it is still not perfect. Looking at the example of the plastic chair being dug up in the desert[1] is frankly a bit... funky. But imagine in 5 or even 10 years.
Re: Sora: Creating video from text
#153OpenAI demonstrating the size of their moat. How many multi-million-dollar funded startups did this just absolutely obsolete? This is so, so, so much better than every other generative video AI we've seen. Most of those were basically a still image with a very slowly moving background. This is not that. Sam is probably going to get his $7T if he keeps this up, and when he does everybody else will be locked out foreve…
"How many multi-million-dollar funded startups did this just absolutely obsolete?"
The play with AI isn't to build the tools to help businesses make money, the play is to directly build the businesses that makes the money.
In practice this means, don't focus your business model on building the AI to make text to video happen. Your business model should be an AI studio, if the tech you need doesn't exist, build it.... but if you get beat by someone with more GPU's and more data, cool use the better models. Your business model should focus on using the capability not building it. It's proving quite hard to beat someone with more GPU's, more data, more brain power.
Re: Sora: Creating video from text
#154OpenAI demonstrating the size of their moat. How many multi-million-dollar funded startups did this just absolutely obsolete? This is so, so, so much better than every other generative video AI we've seen. Most of those were basically a still image with a very slowly moving background. This is not that. Sam is probably going to get his $7T if he keeps this up, and when he does everybody else will be locked out foreve…
$7T is more than the budget of the US federal government, a third of the NASDAQ, or 2,3x AAPL market cap. Sam getting his 7T is not actually possible.
is 7T over a period of maybe 20 years. 1T is enough to buy out most engineers from TSMC, or maybe even buy out TSMC
Re: Sora: Creating video from text
#155OpenAI demonstrating the size of their moat. How many multi-million-dollar funded startups did this just absolutely obsolete? This is so, so, so much better than every other generative video AI we've seen. Most of those were basically a still image with a very slowly moving background. This is not that. Sam is probably going to get his $7T if he keeps this up, and when he does everybody else will be locked out foreve…
seems like a significant chunk of the population may opt in to the Matrix voluntarily. on another note I find it funny they released this right after Google announced their new model. Bad luck for Google or did OpenAI just decide to move up their announcement date to steal their thunder?
If there is a high fidelity nice simulation of a pleasant world, and the actual real world is a hellscape, what is the problem with that?
If you were presented with the fact that whatever your life is is just an illusion, and you are actually a starving slave in North Korea, you would choose to "wake up"?
Re: Sora: Creating video from text
#156Impressive actually, i can actually see UI being real time generated one day now.
You give it data like real time stock data, feed it into Sora, the prompt is "I need a chart based on the data, show me different time ranges"
As you move the cursor, it feeds into sora again, generating the next frame in real time.
Re: Sora: Creating video from text
#157How many of the video startups are shtting their pants right now?
Re: Sora: Creating video from text
#158This is insane. Even though there are open-source models, I think this is too dangerous to release to the public. If someone would've uploaded that Tokyo video to youtube, and told me it was a drone.. I would've believed them. All "proof" we have can be contested or fabricated.
This is what lots of folks said about image generation. Which is now in many ways “solved”. And society has easily adapted to it. The same will happen with video generation.
The reality is that people are a lot more resourceful / smarter than a lot of us think. And the ones who aren’t have been fooled long before this tech came around.
Re: Sora: Creating video from text
#159This is leaps and bounds beyond anything out there, including both public models like SVD 1.1 and Pika Labs' / Runway's models. Incredible.
Let's hold our breath. Those are specifically crafted hand-picked good videos, where there wasn't any requirement but "write a generic prompt and pick something that looks good", with no particular requirements. Which is very different from the actual process where you have a very specific idea and want the machine to make it happen. DALL-E presentation also looked cool and everyone was stoked about it. Now that we k…
In the past the examples tweeted by OpenAI have been fairly representative of the actual capabilities of the model. i.e. maybe they do two or three generations and pick the best, but they aren't spending a huge amount of effort cherry-picking.
Re: Sora: Creating video from text
#160In less than a few hours Gemini 1.5 is old news. Sam is doing live demos on Twitter while Google just released a blog.
Didn't think Google would be the first of the Facebook, Apple, Google and Microsoft to get disrupted.