Tim Fu · Sora Showcase

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.”

[lugui]

a person playing a piano was a bold choice of prompt given how AIs make hands

[flightmode]

the walking transitions are creepy but damn this is impressive when you think about how fast it's evolving.

[avwie]

Remember kids: this is marketing material carefully tailored and carefully curated to keep the hype high

[amoghskulkarni]

No sharp corners were harmed during making of this video

[anony]

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.

[the-tankeur]

This is beautiful, I am a Machine Learning student and nothing is more motivating than seing such models, a state of art.

[Umarbit]

We went from predicting next word to predicting next frame 🚀

[JohnSmithAB]

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.

[jl]

0:16 only four fingers for her right hand.

[claudioagmfilho]

🇧🇷🇧🇷🇧🇷🇧🇷👏🏻, So impressive! OpenAI is truly amazing. I just love everything about OpenAI...

[jointreality]

I’m actually impressed, but I still want the VOICE MODE!

[lamardoss]

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.

[DanielSeacrest]

The way it handles reflections on some of the materials we see here is actually really cool.

[sevennom]

Imagine this in 5 years. It's going to be crazy!

[InternalStryke]

Greatest stock video generator of all time

[ErnestoConfused]

The aesthetic is mesmerizing, huge props to all involved! It came out great!

[THORACL]

This is the 4th Sora video today. Ship something please.

[neodidi]

Impressive... Was the music also AI? Cause that was so soothing

[smokedrumi]

Dope, can we get a date on when it will be released?

[ClintonWhites]

Just Wow!... we might be close to a type 1 civilization