OpenAI revealed Sora, its artificial intelligence video generator to the world in February this year, seemingly leaving every other generative video tool looking like archaic technology.
However, despite multiple calls for its release, suggestions other models could catch up soon and claims the data used to train it may not be licensed by OpenAI — nobody but its developers have actually used it to make a video.
CTO Mira Murati has revealed Sora will be released to the public at some point this year, but first they have to make it cheaper to run, faster and tackle some safety issues.
That doesn’t mean we haven’t seen it in action. So far dozens of clips have been shared by OpenAI or members of the Sora team and some from prompts suggested by commenters.
The best and worst of Sora
Some of the videos look like they are a scene cut from a Hollywood movie, others more closely resemble early experiments in AI video or a student film made by someone that knows they are going to the fail the class.
OpenAI revealed some of the videos can take minutes to generate, even long enough to go off, make a coffee and come back to the computer to see it still working.
I’ve been sharing clips since Sora first launched and have pulled together my favorites so far.
1. An alien in the city
An alien in the city was the first real iconic moment in the Sora story. Other videos had been shared before including the dogs in snow, but this looked like a music video and has even been remixed with lip syncing and and sounds to build on that essence.
The prompt: “an alien blending in naturally with new york city, paranoia thriller style, 35mm film".
2. A leafy elephant
A leafy elephant came out around St Patrick’s Day, a bright green pachyderm covered in leaves, each moving independently and with the wind. It was majestic and shockingly realistic.
The prompt: "An elephant made of leaves running in the jungle."
3. Astronaut preparing for launch
Available on the Sora website, this video is 17 seconds long, which might not seem like much but it was created from a single prompt and features multiple scenes and cuts.
The 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.”
4. Drone flying over cliffs
This one was just eight seconds but the motion and realism made it stand out. However, it is also one that could reasonably be recreated with other current-generation AI video tools.
The prompt: “Drone view of waves crashing against the rugged cliffs along Big Sur’s garay point beach. The crashing blue waters create white-tipped waves, while the golden light of the setting sun illuminates the rocky shore. A small island with a lighthouse sits in the distance, and green shrubbery covers the cliff’s edge. The steep drop from the road down to the beach is a dramatic feat, with the cliff’s edges jutting out over the sea. This is a view that captures the raw beauty of the coast and the rugged landscape of the Pacific Coast Highway.”
5. A historical perspective
What stood out for me here was the potential. It was a multilayered recreation of a gold mining town in California complete with wooden buildings, people walking and even horses walking along the road. The drone motion made it feel like the opening to a new period drama.
The prompt: It was surprisingly short for such a complex, multi-view video. It read: “Historical footage of California during the gold rush.”
6. Pirate battle in a mug
I adore the pirate ships in a choppy cup of coffee. It gives off a sense of adventure and you have to do a double take to realize they're in a cup, not a very dirty ocean.
The prompt: “Photorealistic closeup video of two pirate ships battling each other as they sail inside a cup of coffee.”
7. Cats everywhere
I love this cats everywhere video by Bill Peebles, head of the Sora team. It feels like a post-apocalyptic movie but with cats in the museum.
The prompt: "a giant cathedral is completely filled with cats. there are cats everywhere you look. a man enters the cathedral and bows before the giant cat king sitting on a throne."
8. Dogs in the snow
Dogs in the snow was one of the videos OpenAI used to explain the scale effect. Sora’s biggest improvements come not from model changes — although there are some big changes — but from a massive leap in compute power and training time. The final dogs in the snow was photorealistic and engaging motion, previous versions not so much.
The prompt: “A litter of golden retriever puppies playing in the snow. Their heads pop out of the snow, covered in.”
9. Tokyo in the snow
Tokyo in the snow was one of the first clips to go viral from Sora on X. It features a drone shot following a couple as they walk from Tokyo, covered in snow and pink petals.
The prompt: “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.”
10. Kitten on a robot vacuum
We've all wondered what it would look like if we turned a robot vacuum into a pirate ship for a kitten — haven't we? Well wonder now more because that is exactly what OpenAI have achieved in this Sora video.
The prompt: "An adorable kitten pirate riding a robot vacuum around the house."
11. A single Dalmatian
I love this video for the color and the motion of the lone Dalmatian puppy as it crosses from ledge to ledge over brightly colored Italian buildings.
The prompt: “The camera directly faces colorful buildings in Burano Italy. An adorable dalmation looks through a window on a building on the ground floor. Many people are walking and cycling along the canal streets in front of the buildings.”
12. Steam train in Scotland
This short eight second photorealistic video depicts a beautiful old steam train as it moves towards the camera across a viaduct. It is beautiful in its simplicity.
The prompt: "The Glenfinnan Viaduct is a historic railway bridge in Scotland, UK, that crosses over the west highland line between the towns of Mallaig and Fort William. It is a stunning sight as a steam train leaves the bridge, traveling over the arch-covered viaduct. The landscape is dotted with lush greenery and rocky mountains, creating a picturesque backdrop for the train journey. The sky is blue and the sun is shining, making for a beautiful day to explore this majestic spot."
13. The stylish woman in Tokyo
Here's another early video shared by Sora and available on the website. It shows a stylish woman walking through the streets in Tokyo. This stood out to me as it had a stunning sense of movement.
The 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 confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.”
14. The cartoon monster
One area AI video might dominant in future is animation. If control can be improved we could see animations made in seconds from a text prompt. This is a 3D cute monster with a flame.
The 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 wide eyes and open mouth. Its pose and expression convey a sense of innocence and playfulness, as if it is exploring the world around it for the first time. The use of warm colors and dramatic lighting further enhances the cozy atmosphere of the image.”
15. All of the TVs
Finally, we have a video showing a dozen or so televisions stacked together, each showing different visuals. That part is what made it stand out for me as this is not easy for AI to do.
The prompt: “The camera rotates around a large stack of vintage televisions all showing different programs — 1950s sci-fi movies, horror movies, news, static, a 1970s sitcom, etc, set inside a large New York museum gallery.”
More from Tom's Guide
- Google’s new VLOGGER AI lets you create a lifelike avatar from just a photo
- Apple could bring Google Gemini to the iPhone for AI tasks
- I gave Claude, ChatGPT and Gemini a photo of ingredients to see which came up with the best recipe
