Skip to main content
The Markets by Proactive
Go to Proactive UK
Proactive UK has moved. Proactive’s coverage of London’s small caps continues on proactiveinvestors.com Go there →
Advertisement
The Markets
by Proactive
Proactive UK has moved.
Coverage of London’s small caps continues on proactiveinvestors.com
Go to Proactive UK
The Markets
by Proactive
Proactive UK has moved.
Small-cap coverage continues on .com
Go to Proactive UK
Advertisement
The Markets
by Proactive
Proactive UK has moved.
Small-cap coverage continues on .com
Go to Proactive UK

Tech

Sora: OpenAI’s new AI video examples revealed  

OpenAI workers have been highlighting the power of its newly announced AI model Sora, which can create videos from text.

On Thursday, the ChatGPT creator revealed it was in the preliminary stages of building an AI model which creates high-quality videos from basic text instructions.

Initial videos shown by the tech company highlighted the model’s ability to create both crisp animations and hyper-realistic images.

Prompt: “A movie trailer featuring the adventures of the 30 year old space man wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, vivid colors.” pic.twitter.com/0JzpwPUGPB

OpenAI (@OpenAI) February 15, 2024

Prompt: “Animated scene features a close-up of a short fluffy monster kneeling beside a melting red candle. the art style is 3d and realistic, with a focus on lighting and texture. the mood of the painting is one of wonder and curiosity, as the monster gazes at the flame with… pic.twitter.com/aLMgJPI0y6

— OpenAI (@OpenAI) February 15, 2024

Tech enthusiasts took to Twitter to engage with OpenAI’s management, requesting their own personalised prompts, highlighting the wide range of the model’s capabilities.

Not only can the technology develop the tiniest of details, but it can also produce multiple videos side-by-side, and utilise camera movements and cuts.

"pov footage of an ant navigating the inside of an ant nest"

Video generated by Sora pic.twitter.com/N3Ik9QBinU

— Aditya Ramesh (@model_mechanic) February 18, 2024

welcome to bling zoo! this is a single video generated by sora, shot changes and all. https://t.co/81ZhYX4gru pic.twitter.com/rnxWXY71Gr

— Bill Peebles (@billpeeb) February 15, 2024

However, OpenAI pointed out that the limited access model still suffers from issues in some videos.

In some cases, images appear to struggle with morphing, others appear to create too many versions of animals or people, while difficulties with creating hands also persist.

Sora is obviously really good, but it hasn't crossed uncanny valley yet. Just look at the woman's hands in the back.pic.twitter.com/IzltjLJefh

— Stephen Flanders (@SteveFlanders22) February 15, 2024

Funny glitch with OpenAI Sora.

Interesting how it looks so real yet obviously fake at the same time. pic.twitter.com/vgip4rhGqb

— Farhan (@mhdfaran) February 16, 2024

Advertisement
The Markets
by Proactive
Proactive UK has moved.
Small-cap coverage continues on .com
Go to Proactive UK