Skip to main content

OpenAI’s latest Sora video shows an elephant made of leaves

OpenAI left a lot of jaws on the floor last month when it shared the first footage made by Sora, its AI-powered text-to-video generator.

While not perfect, the quality was extraordinary and left many wondering about the kind of transformational impact that such technology will have on the creative industries, including Hollywood.

Recommended Videos

OpenAI has yet to release Sora to the public — that’s expected to happen later this year — but the company is happy to continue impressing everyone by dropping regular Sora-generated videos onto its social media feeds.

The latest one to land looks like a clip from a fantasy movie and was generated from the simple text prompt: “An elephant made of leaves running in the jungle.”

OpenAI keeps dropping more insane Sora videos

These are 100% AI generated

9 reality bending videos

1. Elephant made out of leaves pic.twitter.com/tPsHNGbFPS

— Linus ●ᴗ● Ekenstam (@LinusEkenstam) March 18, 2024

OpenAI said that Sora did all the work and that the video output was not modified in any way.

Of course, any video creation tool worth its salt has to be adept at cat videos. Sora passed with flying colors when fed with the text prompt: “An adorable kitten pirate riding a robot vacuum around the house.”

Asked to create “Niagara Falls with colorful paint,” Sora came up with this extraordinary footage.

And check out this amazing clip prompted by: “POV video of a bee as it dives through a beautiful field of flowers.”

The OpenAI team dropped more wild Sora videos.

100% AI (minus sound)🤯

9 new ones:

1. POV of Bee pic.twitter.com/RjjSm6kcEB

— Min Choi (@minchoi) March 14, 2024

Sora can build videos up to a minute long “while maintaining visual quality and adherence to the user’s prompt,” OpenAI said when it unveiled the tool last month. The Microsoft-backed startup, which created a stir last year with its AI-powered ChatGPT chatbot, said it’s decided to share its research progress with Sora early “to learn from feedback and give the public a sense of what Al capabilities are on the horizon.”

It also said that it used publicly available data and licensed data to train Sora. The issue of how generative AI models are trained is a controversial one, with writers and artists demanding compensation in instances where their work is used by AI companies such as OpenAI. A number of lawsuits brought by creators are already working their way through the courts, prompting AI firms to seek licensing deals with media giants for trouble-free AI training.

Trevor Mogg
Contributing Editor
Not so many moons ago, Trevor moved from one tea-loving island nation that drives on the left (Britain) to another (Japan)…
How you can try OpenAI’s new o1-preview model for yourself
The openAI o1 logo

Despite months of rumored development, OpenAI's release of its Project Strawberry last week came as something of a surprise, with many analysts believing the model wouldn't be ready for weeks at least, if not later in the fall.

The new o1-preview model, and its o1-mini counterpart, are already available for use and evaluation, here's how to get access for yourself.

Read more
OpenAI Project Strawberry: Here’s everything we know so far
a strawberry

Even as it is reportedly set to spend $7 billion on training and inference costs (with an overall $5 billion shortfall), OpenAI is steadfastly seeking to build the world's first Artificial General Intelligence (AGI).

Project Strawberry is the company's next step toward that goal, and as of mid September, it's officially been announced.
What is Project Strawberry?
Project Strawberry is OpenAI's latest (and potentially greatest) large language model, one that is expected to broadly surpass the capabilities of current state-of-the-art systems with its "human-like reasoning skills" when it rolls out. It just might power the next generation of ChatGPT.
What can Strawberry do?
Project Strawberry will reportedly be a reasoning powerhouse. Using a combination of reinforcement learning and “chain of thought” reasoning, the new model will reportedly be able to solve math problems it has never seen before and act as a high-level agent, creating marketing strategies and autonomously solving complex word puzzles like the NYT's Connections. It can even "navigate the internet autonomously" to perform "deep research," according to internal documents viewed by Reuters in July.

Read more
OpenAI’s advanced ‘Project Strawberry’ model has finally arrived
chatGPT on a phone on an encyclopedia

After months of speculation and anticipation, OpenAI has released the production version of its advanced reasoning model, Project Strawberry, which has been renamed "o1." It is joined by a "mini" version (just as GPT-4o was) that will offer faster and more responsive interactions at the expense of leveraging a larger knowledge base.

It appears that o1 offers a mixed bag of technical advancements. It's the first in OpenAI's line of reasoning models designed to use humanlike deduction to answer complex questions on subjects -- including science, coding, and math -- faster than humans can.

Read more