Where did all of these image generating AIs came from, and why did they develop so quickly in the last year or so?


Some time ago an AI which could convert an image of someone into a drawing would be an idea of science fiction, but in the last year they suddenly blew up on the internet and became widespread, encompassing so many different variations of the images it can generate.

Why did this type of artificial intelligence develop so suddenly? Did someone code an all-purpose source program that enabled this or something?

In: 8

Check out https://openai.com/ for the nitty gritty, but basically, yea. There are a few different software libraries that made it possible to do these kinds of operations without having to write a lot of code yourself, and a bunch of different people built products based on those libraries around the same time. It’s a bit like how assembly line car production happened, and shortly after, there were a heap of different consumer car companies – while beforehand it was a very niche field.

In recent years, there has been a significant amount of research and development in the field of artificial intelligence, particularly in the area of deep learning. This type of machine learning involves training large neural networks on vast amounts of data, which enables them to learn to perform a wide range of tasks, including generating images.

The sudden popularity of image-generating AI is due in in part to the availability of large amounts of data and computational power, which has made it possible to train these neural networks more quickly and effectively. In addition, advances in algorithms and software tools have made it easier for researchers and developers to create and work with these AI models.

It is also possible that the popularity of image-generating AI may be due in part to the widespread use of social media and other online platforms, which has made it easier for people to share and discover these AI tools. As more people become aware of these AI models and use them to generate images, the popularity of these tools is likely to continue to grow.

Something not already mentioned is that while the images being shared have suddenly begun appearing, the AI behind them didn’t come out of nowhere. People have been working on the pieces for years.

For example, one of the big reasons these image generation systems are possible is the previous work on image classification. A huge number of training images along with an incredible manual effort enabled some of these neural networks to be able to tell if an image contains, say, a hot dog. It started out simple, but now the classification systems can give much more accurate responses, including facial recognition.

So the next logical step was to use these classification systems to train image generation algorithms using what is called a Generative Adversarial Network (GAN). Adversarial is the key point. A rough simplification is a network is seeded with some kind of random noise, then random changes are made to the image and tested by the classifier. Images that score higher for the target classification are fed back into the system in a kind of positive feedback loop. Meanwhile, the classification system gets better at spotting fake images. This continues until the generator produces images that are highly successful at fooling the classifier.