9 Awesome AI-generated Videos Made with Sora

Earlier this month, OpenAI announced the release of Sora, a text-to-video model that can create AI-generated videos from written prompts.

Sora is able to generate complex scenes with multiple characters and motion while also understanding how details in the user’s prompt exist in its physical world.

And while Sora is currently only available to a select number of red teamers at this time — the hype surrounding its ability to create highly realistic, detailed images has captured plenty of attention.

As a result, we decided to look at some of the best examples of the tool in action — nine awesome AI-generated videos made with Sora.

This includes a review of what each video did right (and wrong) and, where possible, a summary of the original prompt.

Key Takeaways

  • Techopedia explores nine impressive AI-generated videos created using Sora, from depictions of realistic scenes like a woman walking in Tokyo to more surreal scenarios like a post-apocalyptic jellyfish in a cityscape
  • Despite some imperfections, these videos show Sora’s potential to revolutionize the world of AI-generated content.
  • Sora is not yet publicly available, although other free AI video generation tools allow you to experiment with similar technology.

9 of the Best AI-Generated Videos Made with Sora

1. The Lady in Red

Arguably, the most well-known AI-generated video generated with Sora so far is OpenAI’s promotional video, which depicts a woman in a leather jacket and a red dress walking throughout the streets of Tokyo, Japan.

Advertisements

During the video, she can be seen walking through a vibrant urban environment with pedestrians moving in the background. The overall detail of the video, right down to small elements like the wet floor, makes it seem like the clip is real.

The only real giveaways we noticed were the unnatural motion when she walked and the unusual blurring in the background.

Original Prompt:

“A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots and carries a black purse. she wears sunglasses and red lipstick. she walks confidentially and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.”

2. Snowy Tokyo City

This next example, also created and released by OpenAI, once again depicts pedestrians moving through Tokyo City, but this time it’s caped in snow.

The dynamic camera movement following the central couple in the scene, combined with the motion of snowfall, background traffic, and pedestrians, gives the video clip a feeling of realness and depth.

However, we did notice some giveaways that the video was AI-generated. These included cars disappearing when crossing under the tree line and unusual distortion of the pedestrians on the right-hand side of the screen.

Original Prompt:

“Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous Sakura petals are flying through the wind along with snowflakes.”

3. A Dog Learns to Type

A fun example making the rounds on X was shared by Justine Moore, an investment partner at a16z, and showed an AI-generated video of a dog typing on a keyboard.

This example stood out because it looked extremely realistic, but more like the type of content, you’d shoot with a smartphone to share on social media rather than the highly polished aesthetic presented by videos such as the Lady in Red video.

In the video, the overall motion of the dog’s head and the lighting appear natural and believable. The only real giveaway that the video is AI-generated is the unusual movement of the paws (and the fact that a dog is typing!).

Original Prompt:

Not specified

4. A Cat Searching for Shelter

Another video that caught our attention was shared by Tim Brooks, a research scientist at OpenAI, which showed a cat traversing a back alley.

This video caught our attention not just due to the extremely detailed background of garbage and other debris but also due to how lifelike the cat looks and its reflection in the puddles on the floor.

Of course, we did notice that the motion of the cat walking was extremely unnatural – as was the movement of the tail in places. In any case, we felt the video still created a believable depiction of an animal looking for shelter (even if it failed to include rainfall, which was specified in the original prompt).

Original Prompt:

“A white and orange tabby alley cat is seen darting across a back street alley in a heavy rain, looking for shelter…”

5. Car Travels Multiple Landscapes

In a post on X, AI creator Bilawal Sidhu shared a video-to-video example of Sora in action, where a video of a car traversing a rural landscape was input into the model and transformed into something new.

For instance, throughout the video, the car can be seen traveling rural roads before shifting to a winter background, adding dinosaurs, switching to a lush jungle setting, and even a surreal rainbow road.

Though the dimensions of the road and the background look unnatural in places, this video highlights how users can take videos and give them a stylistic overhaul.

Original Prompt:

[Video input of a car driving down a country road, prompts in-line]

6. Puppies Playing in the Snow

Another video that captured our attention was one of OpenAI’s promotional materials – a short clip of a group of puppies playing in the snow.

What struck us about this image was the level of detail in the shots and how lifelike the movement of the snow looked.

Of course, there were some small issues with the snow moving unnaturally in places and the puppy on the right falling unnaturally below the snow line in the latter part of the video, but as machine learning and generative AI techniques continue to advance, these inconsistencies will become less and less common.

Original Prompt:

Unknown

7. A Postapocalyptic Jellyfish

In a more surreal example shared by Joe Taylor, a researcher at OpenAI, we can see a jellyfish moving through a post-apocalyptic cityscape.

The movement of the jellyfish was quite diverse – with the type of liquid aesthetic and motion in the tentacles that you’d expect from a marine invertebrate. Likewise, we also found the background of the cityscape to feel quite authentic.

In terms of issues with the video, the main thing we noticed was that the jellyfish appeared to be sitting in front of a green screen rather than actually moving through the environment.

Original Prompt:

“A surreal scene unfolds as a giant, translucent jellyfish floats gracefully through a deserted cityscape at dusk. The scene is shot on 35mm film.”

8. An Old Man Eating a Burger

Our next example, this time shared by an X account known as AiBot, provides a short clip of an old man eating a burger.

At first glance, the video appears real, with the man’s face and the cheeseburger looking distinct and lifelike. The movement of other people depicted in the background also gives the scene more depth.

Despite this, we did notice some unusual elements in the video. The lettuce and the sesame seeds look out of place, and the man’s bite into the burger is inconsistent with the effect on the bun.

Original Prompt:

“An older man with gray hair and glasses devours a delicious cheeseburger. the bun is speckled with sesame seeds, fresh lettuce, a slice of cheese, and a golden brown beef patty. his eyes are closed in enjoyment as he takes a bite. he wears a red jacket and appears to be sitting inside a fast food restaurant.”

9. Late Night Supercar

Finally, in an example shared by an X account known as Global Things, a supercar can be seen traveling through rain-soaked city streets.

On first viewing, this video appeared to be real, with a background city environment that looked detailed and lived in with natural lighting.

Our only real criticism of the video was that the traffic on the other side of the road often appeared unnatural, with two taxis appearing out of thin air at the end of the video.

Original Prompt:

“A supercar driving through city streets at night with heavy rain everywhere, shot from behind the car as it drives. While the wet floor was noticeable, we found a lack of rain.

The Bottom Line

Together, these videos highlight that Sora has the potential to be a game-changer in the world of AI-generated videos. While it isn’t publicly available at the moment, early videos have shown that it can create highly realistic and immersive content.

If you want to get started with using AI to create your own videos, you can start by looking at free tools like Runway Gen-2, Stable Video Diffusion, and PixVers. Just remember to make your prompt as detailed as possible so that the model generates the content you’re looking for.

FAQs

Can AI generate videos?

Is Sora AI open to the public?

How can I access Sora?

Is there a free AI video generator?

Advertisements

Related Reading

Related Terms

Advertisements
Tim Keary
Technology Specialist

Tim Keary is a freelance technology writer and reporter covering AI, cybersecurity, and enterprise technology. Before joining Techopedia full-time in 2023, his work appeared on VentureBeat, Forbes Advisor, and other notable technology platforms, where he covered the latest trends and innovations in technology. He holds a Master’s degree in History from the University of Kent, where he learned of the value of breaking complex topics down into simple concepts. Outside of writing and conducting interviews, Tim produces music and trains in Mixed Martial Arts (MMA).