OpenAI is continuing to tease its pending AI video generator Sora with yet more text-to-video clips that are capturing people’s imagination.
In a recent interview with The Wall Street Journal, OpenAI’s Chief Technical Officer Mira Murati said that Sora will be released “definitely this year, but could be a few months.”
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
This video was made by OpenAI’s new text-to-video model Sora
Prompt: A mini Aussie painting a picture of his favorite toy
Entire industries are being upended by AI. Our politicians are not giving this the attention it deserve. #BasicIncome pic.twitter.com/Bs4DD2TTzA
— UBI Works 🇨🇦 (@ubi_works) March 11, 2024
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 generates an imaginary video of the interview. pic.twitter.com/nF5MQba5I2
— Andrew Curran (@AndrewCurran_) March 13, 2024
3. Amalfi Coast
Source: OpenAI TikTok pic.twitter.com/7HetGGFYNi
— Min Choi (@minchoi) March 14, 2024
Mira Murati talked to the WSJ about Sora. Sora will be available this year. Plans are in place to add sound, and eventually, Sora videos will contain metadata as a watermark. OpenAI is currently giving some individuals in the film industry early access for testing. pic.twitter.com/wCNmo4d62u
— Andrew Curran (@AndrewCurran_) March 13, 2024
5. Niagra falls made out of colorful paint
source: OpenAI TikTok pic.twitter.com/GsVW6Mu1mu
— Linus ●ᴗ● Ekenstam (@LinusEkenstam) March 18, 2024
4. Tour of Futuristic House with Modern Aesthetics
Source: OpenAI TikTok pic.twitter.com/FHv4rNt9Gb
— Min Choi (@minchoi) March 14, 2024
5. Horse Roller Skating on Half Pipe
Source: OpenAI TikTok pic.twitter.com/q54xNm3Gx5
— Min Choi (@minchoi) March 14, 2024
6. Teapot Pouring Magic Liquid
Source: OpenAI TikTok pic.twitter.com/c0FdD5bum8
— Min Choi (@minchoi) March 14, 2024
“an alien blending in naturally with new york city, paranoia thriller style, 35mm film”
Video generated by Sora. pic.twitter.com/KReZdvlB0N
— Bill Peebles (@billpeeb) March 2, 2024
Also in The Wall Street Journal interview conducted by Joanna Stern, Murati skirted the question of training data for Sora.
“We used publicly available data and licensed data,” Murati says.
“So videos on YouTube?” Stern asks. “Videos from Facebook, Instagram? What about Shutterstock? I know you guys have a deal with them.”
“I’m actually not sure about that. If they were publicly available, publicly available to use, there might be that data, but I’m not sure. I’m not confident about it,” Murati says.
“I’m just not going to go into the details of the data that was used, but it was publicly available or licensed data.”
Generative AI companies have become increasingly secretive about the training data used to build large-scale models such as Sora and image generators.
