Tim Fu · Sora Showcase
HTML-код
- Опубликовано: 15 сен 2024
- We’re continuing to slowly expand Sora testing to more creatives (digital VFX pioneers, architects, choreographers, engineering artists, and creative entrepreneurs) to help us understand the model's capabilities and limitations, shaping the next phase of research to create increasingly safe AI systems over time. While access is still extremely limited while safety testing is underway, we wanted to celebrate these artists’ work with their reflections on how they use Sora in their process. (The underlying visuals were generated solely with Sora without any VFX, but artists added sound and edited using traditional filmmaking software.)
Tim Fu is a designer and founder of @StudioTimFu a high-tech architectural practice pioneering in computational design and AI, formerly from Zaha Hadid Architects. “Sora revolutionizes architecture by allowing us to vividly explore concepts, while we can build these ideas to life.”
“Beyond images and videos, generative visualization serves as a design process. Spatial quality and materiality can be readily explored in unprecedented speeds, allowing architects and designers to focus on the core values of design instead of the production of visuals.”
![[MV]回家-實驗品V4](http://i.ytimg.com/vi/KueZFl6NpGg/mqdefault.jpg)
![The moment we stopped understanding AI [AlexNet]](/img/1.gif)
a person playing a piano was a bold choice of prompt given how AIs make hands
The hand look great
I think they are showing us this because they want to show us how good the model is with hands
@@IdoHadar They really do look great - Although 1:52 is looking a little painful.
Most AIs aren’t that bad with hands anymore
@@jimmyt_1988 indeed, the starting shot looks really good tho, the hands are kinda blury, but it is a pass, other ones in the middle of the video are not as good, but makes sense they would start with the best generation
the walking transitions are creepy but damn this is impressive when you think about how fast it's evolving.
You have to imagine how good it will be two more papers down the line
And wrists look like second elbows
@@Berkelisure gets better from here 😅
هل هذه المرأة حقيقية ام الة ؟
@@Tech-hamza1 This whole video is created automatically by a computer Brain without human touch...
Okay enough teasing; let us play now!
You need to Wai to 2026....they become google2
Let us cook now!
"Do you want it? Do you want it? 😀"
Agree!
OpenAI went fully close - SORA only for Hollywood and GPT5 only for Corpo - it is great that we have options:)
Remember kids: this is marketing material carefully tailored and carefully curated to keep the hype high
yes sir!!
yes, I agree.
I think it sucks
I don’t think it was really cherry picked since it sucks
@@ShawshankLamlol, big talk from a small guy
VOICE. MODE.
Yes.
whats voice mode? i want avatarr mode, a hot chick i can talk to
lol yep
lol yep
i want avatar mode, a chick i can talk to
No sharp corners were harmed during making of this video
Curves are beautiful.
Sharp corners more chance to hallucinate and branch out into weirdness
Sora is an amazing example of where this technology is heading, but there are still obvious perspective issues and etc still. Sora 2 is gonna be crazy.
First give us 1 and then we will talk about 2
Nah, Sora 2 will still have some issues. Sora 5 gonna be amazing fo real fo real.
@@jonl.b7168you horribly underestimate. sora 3 will be the model that starts real problems.
Nahh man, wait till sora 6. That's the big one
@@InternalStryke jeez dude have you not heard about Sora 9? This is the REAL deal!
wow. What a time to be alive!
hold on to your papers scholars
Hey emratich :)
You should get out of the house more.
@@trappedcat3615you should stop getting mad on the internet
wow what a time to be jobless 😂
This is beautiful , I am a Machine Learning student and nothing is more motivating than seing such models , a state of art.
I am the opposite, I'm a student-learning machine.
@@brexitgreens yesh I'm learning-student machine
Meanwhile art/animation students are buying rope. But hey what would the world care
@@shredd5705 Why? Nobody's stopping them from making art. They lament the death of commercialised art. It only shows what kind of "artists" they are. No love lost!
@@brexitgreens You think people study art/animation in universities to get a nice hobby? It's a job. Commercial art is a job. And it was a dream job, for many. For example, working in video game industry. Because it was the only way to do art and feed your kids. You are delusional with your idealism. Do you really think anyone has time to "make art" if their career is something else? Career takes 90% of your energy, after you get home, make food for the kids, do chores, do some basic exercise to maintain your health... you won't do jack s**t, except crash into sofa or bed. Tale as old as time. This technology will make people with artistic genes suicidal, I wouldn't be surprised if thousands already took their lives (hundreds of thousands are considering it) because of Midjourney, Suno, Udio etc.. it won't be in the headlines, because suicides never get into headlines (unless it was a celebrity)
We went from predicting next word to predicting next frame 🚀
A few of these clips, strategically-placed, could serve to massively raise the perceived production values of many a film. Even without using any characters, simply used as B-roll or establishing shots, a production could save countless thousands of dollars in sets and CGI. Obviously, longer term, things like consistent character and set-generation, lip-syncing to prerecorded audio, and camera control are needed to take this technology all the way, but what exists right now would already be enormously useful to many productions.
I’m actually impressed, but I still want the VOICE MODE!
What do you mean about voice mode? Everybody write that why?
تقريبا حاجة تخص اخر اصدار من GPT أنه بقى يشتغل بالأوامر الصوتية أو حاجة زى كده @@سجاد-2007
@@سجاد-2007 means chatgpt voice mode
so, wtf is the voice mode?
They showcased a voice mode for gpt4o, and said it was ready to release, but it’s been over a month and no release, same with Sora. People are tired of OpenAI teasing features and not be able to use them
This is the 4th Sora video today. Ship something please.
They can't... you know why.
But, they are shipping. Just stay there and you can enjoy more a year around, ahahah.
@@asterlofts1565 someone else will do it if they don’t
@@kc-jm3cdAlready. Runway Gen 3 and Kling AI. That's why Open AI is like: hey guys, wait, we also have something here, look at this... You can't touch, but please watch
@@asterlofts1565 Why?
Where’s voice mode?
Thank that stupid scarlwt johanson
so, wtf is the voice mode?
Coming up on September, I guess
@@chancepark247 The promised new mode of GPT-4o that has been promised but isn't really rolled out
🇧🇷🇧🇷🇧🇷🇧🇷👏🏻, So impressive! OpenAI is truly amazing. I just love everything about OpenAI...
0:16 only four fingers for her right hand.
Aliens
We have a heart. No one can make a heart with feelings. Because the robot has a chip. Only one, but we have two. heart of stone..
I find myself wanting a banana peel placed somewhere in here.
🤣
bad boy
Just Wow!... we might be close to a type 1 civilization
I think it’s predicted by the year 2100 we will be. But I can’t remember my sources so take it with a grain of salt.
The way it handles reflections on some of the materials we see here is actually really cool.
Most people are afraid after seeing things like this, but I'm filled with pride of the unbound human intelligence, which allows us to create such amazing things.
Just imagine what can be possible in the future. You won't need millions of dollars for production, you will be able to create a movie of your dreams at home without any technological knowledge. That's incredible opportunity for all creative people on the planet
I don't agree you. I think after all of these ai things, the people will lose their creativity and they will become even lazier than before.
@@posuga ok, I'll give you an example. Interesting stories for anime/manga/videogame/movie come into my head every month, but I can't draw, so I can't realize them in any way. With AI like Sora my inability to draw won't be an issue, so I could realize my ideas
They just feed us with expectations. They didn't provide the language model, and now there are other promises.
almost as if OpenAI is a closed source corporation 🤔🤔🤔
I am the opposite: my reaction to increased teasing is increased skepticism. We'll get GTA 6 before we get Sora.
I believe that Sora will not be available to the general public.
Here we go again! Let’s forget about 4o voice mode shall we?
If I see one more person whining about voice mode I’m gonna lose it
Right. We're told a couple weeks, then three months later there's been zero mentions of it. But sure, we're whining🙄
@@epicboy330
@@epicboy330NEED VOICE MODE NOW
@@epicboy330 WEEEE NEEDD VOICE MODEEEE
now to looser it, start explosive loose motion diarrhoea
We can't 4get bout it, that one is better than this for most ppl, I think most ppl don't use ai to generate videos like this, just normal texting things
Greatest stock video generator of all time
Brilliant! Even if fingers and music are not in sync... Can we expect cool but ended TV series to be continued with this technology?!
That's an interesting thought! you could feed it the series or films (with copyright owners permissions of course) and then they could potentially, one day, easily continue things! would be awesome.
Great job Team.....
I know this video has thousands of bugs, but when man first created the radio, it also had a lot of bugs. It works great now, so I believe that one day this video will be very close to perfection. good look to the development team
Ok Now that's enough for testing , Now give this control to us for playing this amazing GAME
This is amazing. In five years, we will be able to make a full movie with AI alone.
imagine you wearing a VR glass and immerse in these 3D video. NPC also can talk to you like real human. It is definitely my dream.
The actual release date is going to be 2050
We'll get GTA 6 before we get Sora.
I think after August when NVIDIA releases the Blackwell B100 and the H200, they need more compute power to minimise the generation time.
Advertising choreography simple understanding.
Girl with blouse walking. Playing piano. Been to different places. Light. Art. Building.
Conclusion: men of culture. We meet again.
Like how all the comments are unrelated to how historic this is.
"Historic" as in "outdated". OpenAI is late with releasing it. They've learnt nothing from the DALL·E 2 fiasco.
why do you think this is historic?
@@Corusame Cause AI video generation is new
its not good if you ask me.
@@Corusameyour joking right
When this gets released to the public, Kling will already own the market.
It's in Chinese you can't even use it
Amazing, let give to everyone to playing with 😊
It is crazy how real it looks. Im so making a video of me jumping out of space without a parachute to scare my friends lmaoooo
Dope, can we get a date on when it will be released?
Autumn 6th
@@dogzerWhat
like he said, Autumn 6th 2037
Autumn is not a month. wth is autumn 6th??
Winter 3rd
This is getting much better. I remember last month a music video on this channel that was so bad, I thought someone posted it on accident.
Making great improvements here. Well done.
Once men turned their thinking over to machines in the hope that this would set them free. But that only permitted other men with machines to enslave them.
That’s very bold of you to assume that men will be men in the future.
WAIT! Are you telling Sora created it? What an unbelievable advancement in AI!
What did you expect?
You guys should be working on these outages. Another partial outage today. Cmon dude I pay 20bucks for you guys. Im considering building my own chatbot with the API instead. Seems like that never goes down.
You can just use API playground instead.
They introduced a new model today: *GPT-4o mini.* Must be why.
this is just fantastic
V.O.I.C.E M.O.D.E !
Can’t wait to this technology becomes perfect 🔥
Yeah, another showcase. If Sora can create videos like this already, why did we end up with THAT video of a Toys "R" Us commercial????
I'm positive about the advantages that AI will provide us with. AI is basically the most important invention today. Just looking at this video gave me enough confidence to further expand my explorative and imaginative brain. Just think how the application in the practical filmmaking . The lengths that humans would go in order to level up the storytelling game.
Imagine one day using ai to make your own netflix show
two years from now pal
Well, great job, I now just have to accept the end of my animation job. All my passion for art,,,, well, some things have to come to an end.
Can't wait to generate floating people too
The aesthetic is mesmerizing, huge props to all involved! It came out great!
Once gaming is this real (or better) ain't nobody gonna want to live in reality.
Except those who like to have power over others. 🥰
I feel sorry for you and those who will. Humans will lose a lot of qualities, it’s already happening since computers and internet are in our daily lives…in exchange for what?
@@tomm5023 We become Teletubbies.
@@ayoutubechannelname You’re being too nice
Except those who get laid. Which isn't gamers, so yeah I get why gamers wouldn't want to do anything else
The way the woman sits on the couch and naturally looks to her right looks so real. If you made this into a commercial I doubt any would notice it's ai.
We are in westworld now
Wow, evenif there are quirks here and there, it's pretty awesome!!
whats with the reupload the original video looked fine
What did you mean?
@@سجاد-2007 OpenAI uploaded this exact same video a few hours ago then deleted it now its reuploaded
I recall noticing that the woman playing the piano appeared to have three legs at one point in the original video. There were likely a few other issues, so they attempted to correct them and re-upload the video. 💀
They edited the video to delete some terrible artifacts like the woman with 3 legs... Sora is still immature.
also blurred out the car logo
Its like watching a baby first crawl, then walk, then run. Soon it will be indistinguishable from reality. What ever you can imagine and never thought you could imagine will be possible. How exciting and terrifying all at the same time. I cant wait to get my hands on the final product!
voice？
The hands. The walking transitions. Everything blending into each other and the nauseating feeling argh
I can’t even tell at this point it’s generated content
yes you can
the piano playing gives it away completely. The fingers are not only not synced with the music, it's also completely unnatural and the keys being pressed down are not the keys the fingers are pressing
So much perspective distortion and arms and legs distortion
It's getting there, slowly
Sora sora buralara geldik. Artık yayınlayın da kullanalım
Onu yayınlayamıyoruz maalesef
To see how much they struggle to create things that make physical sense just goes to show we humans really make magic with cameras.
Amazing
In the fall, open ai will try to deliver the new vision mode to all chat gpt plus users. At the end of July, some users will receive it in an alpha version for testing. This message will already appear in the chat gpt application if you start the speech function at the information sign in the upper right corner.
Looks demonic. Wow. Good job.
Plz voice mode! Been paying for so long!! 😢
1:52 - And still bad with hands. AI hates hands😂
I'd like you to please take note of the urgency expressed by enthusiasts. Sora's team must keep up with the fast-paced advancements in tech, and timely releases can make a big difference in maintaining a competitive edge. The enthusiasm shown reflects the excitement and anticipation in the community for innovative tech solutions. Let's hope the makers take notice and bring their tech to the market soon.!
Don’t tease just release 😢
Please stop gatekeeping this amazing tech and OPEN it up to the people
This is incredible, thank you that this happens during my lifetime ❤
This will be a revolution in advertising, content creation
Can’t wait for the first fully AI generated movie in the cinema!
Actually it will be only 60 seconds
It's crazy how fast our eyes have become accustomed to clocking AI generated vids. How long before we won't be able to tell?
This is the most beautiful sore example yet!
One day, most creative innovations will come from AI, impacting not only medicine but also visualizations and other fields.
AI is not a database; it's not designed for database functions. It's a creative machine.
Insane, the future is here
TBH, I don't know what this is but I love every bit of it.
It's getting there but not quite yet. Let's see what you have in a year. As a filmmaker I'm looking for small direcoral nuances that differentiate humans from AI. There are some choices we make as humans that are missing in these clips. Not all of the clips but enough to where we can tell. But with this level of quality, a story can be told to a degree. The stage I wish to see is speaking.
Imagine this in 5 years. It's going to be crazy!
Can't believe I'm one of the first to watch it like they literally just posted share some love
👇
The pace of improvement is staggering.
Slowly but surely 🙂It's getting there. This would have had been impossible to imagine just three years ago.
I think you mean : 1 year ago* we really came from a weird Will Smith video eating spaghetti to THAT! That's more than incredible man that’s GODLY
I Love AI. All those people hating on AI and saying it is useless crap need to watch this. It is mind-blowing
EXCLUSIVE PLUS MEMBER FEATURES!!
As long as you can't eliminate the uncanny valley completely, it's not gonna work (e.g. woman's appearance morphing at 1:08). At this point whenever I see AI generated stuff I just look out for those moments. Sorry, it's getting old.
That’s incredible AI has come along way. In a short period you will not be able to tell the difference between AI and reality
Visually impressive... it was like walking on air*
Wow i wanna live in an AI generated house
*A few days later…*
The producers of Westworld suing OpenAI for copyright infringement
Beautiful!!
Wow, the environmental scenery and panning shots are amazingly convincing and consistent in art direction/aesthetic. The humans, on the other hand, still show many subtle, uncanny valley characteristics. Curious to hear the actual music that would be produced by the keys being played with those 'hands'.
Wow... looks so photorealistic, masterpieces!!!
I don't understand why AI can't make hands right ? Is it doing on purpose for making sure the video is real or fake ?
Or it just can't analize the hand structure?
ok, the future near we all will sit and meditate, that the best life
Open a I except for it's not open and you can't use it unless we specifically choose you... Otherwise, try and do something else.The others are surpassing sora anyway
open ai is making low cost movie possible, this gonna make revolution to society
Thank you @OpenAI for this opportunity!
We will continue to experiment and share results
Hmmm interesting
Once AI will understand physics things will be going craaaazzzyyyy !
Incredible 🔥⚡
A Honor for Zaha Hadid
A piano with a sneeze guard! It’s like all the advantages of a musical instrument and a salad bar all rolled into one. Now you don’t have to choose between one or the other.
But seriously, looks nice.
Almost there but not quite there yet, the walking is a bit off
nitpicking
@@itskittymethats why they said almost there🤦🏾♂️