Key Takeaways
- Sora by OpenAI generates videos from text prompts: This new tool allows artists to create diverse and imaginative videos, ranging from surreal to bizarre.
- While the videos are creative and visually impressive, there are signs of AI-generated artifacts, like jumbled text, indicating some limitations.
- Despite its imperfections, artists are exploring new creative avenues, creating short films, music videos, and even physical sculptures inspired by Sora’s outputs.
The creators of ChatGPT, OpenAI, will soon introduce a new tool called Sora that can generate videos based on text prompts. This feature is still in the testing phase, and what better way to test its limits than to let a bunch of artists play with it?
Testers have started sharing their creations with the world, and so far, the results range from weird to surreal. Here’s a roundup of the best Sora AI videos that truly showcase what OpenAI’s text-to-video tool can do.
I tried ChatGPT Plus. Here’s everything it can do
ChatGPT Plus is for those who want a reliable, efficient ChatGPT experience. But, for $20 monthly, what else does it include?
1 Air Head
Don’t lose your head
Air Head is a mockumentary about a man with a peculiar condition: His head is a yellow balloon. We see him doing mundane things like driving, riding the subway, and going shopping while discussing the challenges of his daily life, such as literally losing his head on windy days. Then, he describes the benefits of seeing the world from a different perspective as he floats above ancient ruins, mountainous landscapes, and a pod of killer whales swimming in the ocean.
The short film was made by a studio called Shy Kids based in Toronto. The visuals are impressive, and while obviously computer generated, you wouldn’t guess that it was completely made by AI if you didn’t already know. It’s unclear whether the balloon man’s voice was also generated by Sora or had to be added later.
How to master GPT-4 in ChatGPT: Prompts, tips, and tricks
I’ve asked ChatGPT-4 to create everything from poetry to a job application. Here’s what I’ve learned.
2 AI Speedrun
Take a quick trip around the world
This video by Paul Trillo might give you a migraine, but it’s a diverse showcase of Sora’s capabilities. The film puts viewers behind the “camera” as it zooms through various locations, from a suburban neighborhood to the depths of the ocean. We then see a man turn into a disco ball as a breakdancer made of trash dances for a crowd of spectators. After that, a man made of liquid gold melts in and out of existence as he navigates a rocky landscape.
I’d really like to know the text prompts for this one. The “real-life” footage looks like it was filmed on a camera from the 1970s, a trick commonly used to mask the deficiencies of CGI. The fast-moving camera also has the same effect, since your brain can’t register everything happening in the frame. Like an impressionist painting, the video invites your imagination to fill in the blanks.
10 ChatGPT prompts to unlock the full power of OpenAI’s chatbot
Want to get the most out of ChatGPT? Try these prompts to unleash its full potential and make the AI work harder for you.
3 Salt Soda
It’s more appetizing than it sounds
Directed by Nik Kleverov, this video is mostly a random assortment of scenes including old men working on mysterious gadgets, clips from a non-existent film noir movie, and construction workers dancing around a giant shoe (or tiny workers dancing around a regular-sized shoe, depending on your perspective). It ends poignantly with a can of Salt Cola and a magical city made of mushrooms. I can hear the cries of Nintendo’s copyright department.
Eagle-eyed viewers will start to notice Sora’s shortcomings, like the sign for a “Bicycle Repaich” shop. The jumble of letters on the Salt Soda can is also a telltale sign of AI-generated images. Nonetheless, the artist deserves some credit because AI couldn’t imagine something this weird by itself.
How to use ChatGPT to make AI-generated art and images
Whether you need a stock photo or a portrait of Big Foot, ChatGPT can now use DALL-E AI to generate images. Here’s how, plus tips and tricks.
4 Sugarize
The future of music videos
Musical artist August Kamp used Sora to create a video for his song “Sugarize.” The imagery in this video is very abstract, an area where Sora seems to excel. We see diamonds spinning under blue lights, a computer interface with jumbled text, a spacecraft on the moon, and some mysterious mechanical Totem poles in a garden. The theme seems to be the tension between nature and technology.
I can certainly see AI music videos becoming normalized considering the shots in this video would normally require a lot of time and money to produce, whether using real props or CGI artists. We don’t know exactly how long it took Sora to spit this out, but the artist’s intent still shines through since the imagery perfectly fits the music.
5 mind-blowing AI tools to try other than ChatGPT
The potential of gen AI is limitless. Here are a few tools — other than ChatGPT, Copilot, and Gemini — currently using it in fun, interesting ways.
5 Underwater fashion show
The future of fashion
Josephine Miller, a specialist in digital fashion, used Sora to curate an unusual runway showcase. Her video has models floating underwater while wearing suits made of stained-glass scales. One woman looks like a mermaid while another is clearly wearing a scaley dress that floats around her frame.
Scenes such as these would be impossible to create without CGI, and the assistance of AI only helps make the illusion seem more “real,” so long as you don’t look too hard at the models’ faces. The clip is only a few seconds long, yet it highlights both the strengths and limitations of Sora.
8 ways ChatGPT Plus is better than Gemini Advanced and Copilot Pro
ChatGPT Plus faces stiff competition from Gemini Advanced and Copilot Pro. But I’ve tried all three AI subscription services. Here’s how it’s better.
6 Beyond our reality
Pigs can fly, for real
My personal favorite is Beyond our reality, a fake nature documentary about made-up animal hybrids including the bunny armadillo, the giraffe flamingo, and the eel cat. We get to see these creatures up close in their natural habitats in stunning detail.
It’s unknown whether the voiceover was created by Sora or the artist, but the video’s visuals are impressive enough on their own. Netflix could easily make a series out of something like this, and it would attract millions of viewers.
I tested Gemini Advanced against ChatGPT Plus to see which AI is better
I conducted a Gemini Advanced vs. ChatGPT Plus face-off, because I wanted to know which AI chatbot subscription service is actually best.
7 AI Sculptures
Reverse engineering AI art
Alex Reben decided to try something different. Rather than just using Sora to create videos, he makes physical sculptures inspired by AI-generated models. This video shows off some of the models he’s reproduced in real life.
For those of us who worry about the proliferation of AI resulting in creative atrophy, this video, like the others, indicates that AI could actually help artists push their limits. After all, Sora can’t make videos without human input, at least not yet.
Trending Products
