OpenAI’s Sora creates sensational videos

OpenAI’s Sora, an AI model that creates scenes from text instructions, has recently taken the world by storm with its creation of incredible videos.

The company that pioneered the large language model (LLM) ChatGPT is turning its attention to video by teaching artificial intelligence (AI) to “understand and simulate the physical world in motion.”

According to OpenAI, the software can create videos of up to 60 seconds, which it claims can maintain visual quality and adhere to users’ prompts,

Although OpenAI may not have worked out all of the kinks in Sora’s design, the output generated by the service is already captivating.

Here are some of the most compelling videos that have been generated by Sora so far:

Realistic wooly mammoths

Sora has created a 10-second video clip of three wooly mammoths stampeding towards a “camera” kicking up snow as they enter the shot.

The animals look incredibly convincing, their movement resembling that of their elephant descendants.

From afar, the video looks incredible, capturing the essence of the prompt accurately.

The prompt used to generate this video reads:

Several giant wooly mammoths approach, treading through a snowy meadow, their long wooly fur lightly blows in the wind as they walk, snow-covered trees and dramatic snow-capped mountains in the distance, mid-afternoon light with wispy clouds and a sun high in the distance creates a warm glow, the low camera view is stunning capturing the large furry mammal with beautiful photography, depth of field.

The prompt used is quite extensive, demonstrating the amount of detail needed to generate this type of photorealistic scene.

Yet, when you look closely, you can see that nothing in the background is moving. No trees are swaying despite the conditions.

It does look slightly mechanical, like images superimposed onto a background.

However, this doesn’t detract from how captivating the imagery is – it’s impressive, to say the least.

Scenic spaceman

A “movie trailer” featuring a spaceman wearing a red knit motorcycle helmet traversing a desert landscape is one of the richer videos that should raise red flags for all filmmakers.

The video features dynamic shots while frequently changing perspective to give it an action movie feel.

This video is an example of the amount of complexity and detail that can be generated when using specific prompts.

“Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions,” OpenAI explains.

The prompt used to create this video reads:

A movie trailer featuring the adventures of the 30-year-old spaceman wearing a red wool knitted motorcycle helmet, blue sky, salt desert, cinematic style, shot on 35mm film, and vivid colors.

Although the plot or narrative of this “movie trailer” is unclear, the visuals are incredible, demonstrating Sora’s ability to craft incredibly aesthetic scenes that may change the way we view media altogether.

Incredible paper fish

Using a simple prompt, Sora has created one of the most aesthetically pleasing AI-generated videos I have ever seen.

The viewer is presented with an intricate coral reef scene, and as the “camera” zooms in, it’s revealed that this reef is crafted entirely from paper.

We are confronted with beautiful images of fish swimming in this paper reef as we pan through the different crafted sea creatures.

The simple prompt reads:

A gorgeously rendered papercraft world of a coral reef rife with colorful fish and sea creatures

The only criticism of this piece is that the camera work feels mechanical. However, this doesn’t detract from the incredible output generated by the software.