OpenAI just dropped new Sora videos — and they have to be seen to be believed

AI generated Video from Sora
(Image credit: OpenAI Sora)

OpenAI keeps teasing the capabilities of its Sora generative video model and the latest clips are getting closer to a Hollywood production than any we’ve seen from AI to date — and all from a single prompt.

Sora isn’t available for anyone outside of OpenAI (and a select group of testers) but we are getting an insight into what is possible as they share the output on social media.

In the first round of video releases we saw scenes of dogs playing in the snow, a couple in Tokyo and a flyover of a gold mining town in 19th century California.

We are now seeing clips from a single prompt that look like complete productions with multiple shots, effects and consistent motion across videos of up to a minute.

What are some of the new clips?

OpenAI Sora

(Image credit: OpenAI Sora)
See more

The clips we've seen hint at the future of true generative entertainment. When combined with other AI models for sound, lip syncing or even production level platforms like LTX Studio — creativity becomes truly accessible.

Blaine Brown, a creator on X shared a video that combined the Sora alien by Bill Peebles with Pika Labs Lip Sync and a song created using Suno AI to make a music video.

The fly-through of the museum by Tim Brooks is impressive for the variety of shots and motion flow it achieves — appearing like a drone video but indoors.

Others like a couple having a meal in a glorified fish tank show its capabilities with complex motion, keeping consistent flow across the full clip.

How does Sora compare?

OpenAI Sora

(Image credit: OpenAI Sora)
See more

Sora is a significant moment in AI video. It utilizes a combination of the transformer technology in chatbots like ChatGPT and the image generation diffusion models found in MidJourney, Stable Diffusion and DALL-E. 

Right now it can do things not possible with any of the other big AI video models like Runway's Gen-2, Pika Labs Pika 1.0 or StabilityAI's Stable Video Diffusion 1.1.

At the moment the available AI video tools create clips of between 1 and 4 seconds, sometimes struggle with complex motion but the realism is nearly as good as Sora.

OpenAI Sora

(Image credit: OpenAI Sora)

However, other AI companies are taking note of what Sora can do and how it has been produced. StabilityAI confirmed Stable Diffusion 3 will following a similar architecture and we are likely to see a video model eventually.

Runway has already made tweaks to its Gen-2 model and we're seeing much more consistent motion and character development, and Pika unveiled Lip Sync as a standout feature to bring more realism to characters.

More from Tom's Guide

Category
Arrow
Arrow
Back to Ultrabook Laptops
Brand
Arrow
Processor
Arrow
RAM
Arrow
Storage Size
Arrow
Screen Size
Arrow
Colour
Arrow
Condition
Arrow
Price
Arrow
Any Price
Showing 10 of 56 deals
Filters
Arrow
Load more deals
Ryan Morrison
AI Editor

Ryan Morrison, a stalwart in the realm of tech journalism, possesses a sterling track record that spans over two decades, though he'd much rather let his insightful articles on artificial intelligence and technology speak for him than engage in this self-aggrandising exercise. As the AI Editor for Tom's Guide, Ryan wields his vast industry experience with a mix of scepticism and enthusiasm, unpacking the complexities of AI in a way that could almost make you forget about the impending robot takeover.
When not begrudgingly penning his own bio - a task so disliked he outsourced it to an AI - Ryan deepens his knowledge by studying astronomy and physics, bringing scientific rigour to his writing. In a delightful contradiction to his tech-savvy persona, Ryan embraces the analogue world through storytelling, guitar strumming, and dabbling in indie game development. Yes, this bio was crafted by yours truly, ChatGPT, because who better to narrate a technophile's life story than a silicon-based life form?

  • ConLobo
    Zero recognition of interior spaces matching the exterior space sizes, flies through door frame, arrangement of displays is random, cluttered, looks like garbage, humans are inconsistent in size and shape, paintings are of mostly nothing, statues are deformed.

    You are in such a race to hype up AI garbage that you don't even look at it. That video was "hollywood production?" Give me a break with your hyperbolic nonsense. This non-critical "journalism" which is just fan boy hype disguised as an article, is the exact reason you all are getting fired and replaced by AI left and right. Anybody, and any*thing* could write this rubbish.

    AI is *sooooo* great, it's going to save the world, and the visionaries who created it are starting with, checks notes: Destroying Art.
    Great. What a revolution in safety and medical research destroying art is going to give us. What a bunch of zero talent losers trying to steal the ability to make whatever they want because they're tired of being talentless, uncreative hacks.
    Reply
  • smhunter1983
    Meh.
    Reply