Is Artificial Intelligence (AI) singular? How original or different can the outcome be if you use the same prompt in different models? Let’s consider, for example, Sora OpenAI and Midjourney.
Recently, OpenAI introduced its artificial intelligence model Sora, from which it will be possible to generate high-quality videos from text.
Sora represents OpenAI’s first foray into video generation through AI, expanding its repertoire of technological tools that include the text generator ChatGPT and the image generator DALL-E.
The results of Sora have garnered admiration from users and AI specialists alike. In this regard, Nick St. Pierre, creative director, undertook the exercise of replicating Sora OpenAI’s prompts in Midjourney, and the result was several very similar images.
I ran all of the Sora prompts through Midjourney
Interesting how similar some are
side-by-sides against vids:
— Nick St. Pierre (@nickfloats) February 16, 2024
An extreme close-up of an gray-haired man with a beard in his 60s, he is deep in thought pondering the history of the universe as he sits at a cafe in Paris, his eyes focus on people offscreen as they walk as he sits mostly motionless, he is dressed in a wool coat suit coat… pic.twitter.com/sUOLsmz0xy
— Nick St. Pierre (@nickfloats) February 16, 2024
An adorable happy otter confidently stands on a surfboard wearing a yellow lifejacket, riding along turquoise tropical waters near lush tropical islands, 3D digital render art style. –ar 16:9 –style raw pic.twitter.com/rdDB4fnxt9
— Nick St. Pierre (@nickfloats) February 16, 2024
Historical footage of California during the gold rush. –ar 16:9 –style raw pic.twitter.com/dVcprOyFOU
— Nick St. Pierre (@nickfloats) February 16, 2024
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. –ar 16:9 –style raw pic.twitter.com/mcoU8JQohZ
— Nick St. Pierre (@nickfloats) February 16, 2024
Archeologists discover a generic plastic chair in the desert, excavating and dusting it with great care. –ar 16:9 –style raw pic.twitter.com/mvX7vjbkfC
— Nick St. Pierre (@nickfloats) February 16, 2024
A grandmother with neatly combed grey hair stands behind a colorful birthday cake with numerous candles at a wood dining room table, expression is one of pure joy and happiness, with a happy glow in her eye. She leans forward and blows out the candles with a gentle puff, the… pic.twitter.com/MBxlJdTRCG
— Nick St. Pierre (@nickfloats) February 16, 2024
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. –ar 16:9 –style raw pic.twitter.com/OoJkzDwYdo
— Nick St. Pierre (@nickfloats) February 16, 2024
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. –ar 16:9 –style raw pic.twitter.com/50OH1BaLIG
— Nick St. Pierre (@nickfloats) February 16, 2024
A litter of golden retriever puppies playing in the snow. Their heads pop out of the snow, covered in. –ar 16:9 –style raw pic.twitter.com/bNLRBxWwM8
— Nick St. Pierre (@nickfloats) February 16, 2024
What is Midjourney?
Midjourney is an artificial intelligence tool that has revolutionized the world of visual creation. It allows users to generate realistic images from textual descriptions, opening up a new world of possibilities for artists, designers, and anyone looking to unleash their creativity.
With Midjourney, users can create all kinds of images, from realistic landscapes to fantastical characters. The only limitation is the user’s imagination.
Who created Midjourney?
Midjourney is the brainchild of David Holz, an entrepreneur and inventor with a long history in the technology world. Holz is known for his work in creating Leap Motion, a gesture control device that was acquired by Google in 2019.
What is Sora OpenAI?
Sora is a multimodal language model that can generate realistic videos from textual descriptions.
Users simply need to write a description of the scene they want to see, and Sora brings it to life. The model can create videos of up to 60 seconds in length, with quality comparable to that of a professionally produced video.
ALSO. Sora OpenAI. Another 5 Things You Can Do with This Artificial Intelligence
How to make videos with Sora?
According to OpenAI’s revelations, Sora works in a very similar way to ChatGPT and DALL-E. That is, a descriptive prompt is sufficient to obtain results.
Text to video
Sora is not the first artificial intelligence model capable of generating video from text. However, there are factors that highlight its breakthrough.
Its ability to interpret textual instructions and turn them into complex scenes, complete with emotionally expressive characters and precise environmental details, is certainly impressive. Users can choose between photorealistic or animated styles, suggesting a wide range of applications, from creating educational content to entertainment production.
However, what makes Sora particularly unsettling is its ability to generate videos that are indistinguishable from reality.
The videos shared by OpenAI depict scenes that never happened, with characters that never existed. Nothing you see here is real, but it looks like it.
Sora OpenAI and the ethical dilemma
The use of a diffusion model to smooth videos from static noise to achieve impressive clarity is a technical feat, but it also raises questions about the potential for abuse. Deepfakes, manipulated videos to make it appear as if someone is saying or doing something that never happened, are already a significant concern. With technologies like Sora, the fear is that such forgeries could become even more convincing and difficult to detect.
OpenAI is aware of these concerns and has pointed out that Sora is still in development, with limited access to a small group of researchers and creatives for testing and feedback.
The company has acknowledged that, while Sora outperforms competitors like Midjourney and Stable Diffusion in creating longer and smoother videos, there are still areas that require improvement, especially in understanding cause and effect and spatial awareness.
Expectations surrounding Sora are high. Its ability to generate personalized educational content, detailed historical recreations, or visualizations of future products are just some of the potential applications.
