Sora, which OpenAI created and disappeared like a ball of light, fascinates some and scares others with what it can do.
OpenAI, DALL-E When we first saw the model, we were surprised that we could obtain high-quality visuals with simple recipes at that time. While the visual production tools that have developed radically since then have left DALL-E behind ChatGPT We witnessed its birth and development until today’s GPT-4.
ChatGPT, which currently uses GPT-4, is known as the simplest to use and best-yielding model. At least what OpenAI has revealed so far largest language model That was the case until they brought out Sora. Of course, it is difficult to understand at first glance what this model that is placed in front of us at night is and its difference from others. That’s why Sora’s We will explain to you what it is, how it works and what it enables.
Just as DALL-E gives us visuals of recipes, Sora also gives us videos. But that’s not all.
Sora, as we said OpenAI The largest language model he has ever produced. What they can do is not limited to video production. It animates still photographs, it can stretch videos forward or rewind, it can produce simple photographs other than video, it can link videos together, it can take descriptions both visually, video and with prompts, it moves objects and people more consistently in camera movement, the object moves out of the frame and Even when you return makes it look consistent etc. In many respects, Sora is far ahead of his peers.
So how can this model appear in different sectors?
Thanks to Sora, independent game developers can make better quality cutscenes with less effort.
Sora and text both video, text and visual It will work in this area because it provides quality video outputs with its input and can combine them consistently.
With this artificial intelligence model, the inclusion of deceased actors in new productions may require less labor.
Another contribution to the cinema side could be the possibility of rejuvenating and aging the actors without having to use a ton of make-up.
It can solve your stock video and photo search in seconds.
With Sora, you can add effects to your videos in seconds, which would normally take hours in programs such as After Effects.
Sora does not work on small size videos like its counterparts. Instead, it can sample all videos between 1080 x 1920 and 1920 x 1080.
This is for different platforms different width/height This means you can produce videos with high ratio.
Going back to the game side, you can play on certain parts of the videos and change objects with Sora.
This means changing the environment or object. maskingIt will make it possible to create scenes and add your object there without having to deal with loads such as space filling. This could also be the opposite, it’s up to your creativity. For example, in the video above, you can see lossless transition to different environments.
We talked about independent game developers. But short film makers can also realistically create scenes that would normally cost huge sums of money.
Of course, our model will also radically change the marketing methods on the start-up and entrepreneurship side.
Content producers who put game footage behind and talk about it can also benefit from Sora’s opportunities.
Thanks to Sora, not only temporary images but also narratives that are difficult to describe can be easily presented to us.
Of course, Sora isn’t exactly perfect right now.
Currently, this model cannot handle some laws of physics, so the model you see in the video above plastic chair or a glass that needs to be broken It doesn’t work exactly as it should. But take a look at the video below.
If we have reached this stage in less than a year, Sora will overcome these problems in a very short time. What are your thoughts?