See this image above? It's not exactly real--it was created by a computer. That's right, a human being did not draw this picture, an Artificial Intelligence designed and "painted" it. I merely inputted a phrase into a program, in this case I wrote "bowl of fruit, painterly" and this is what the computer came up with based on my prompt. So, how does this work?
Well, an Artificial Intelligence is "trained" by being fed billions of images and captions, enabling it to learn the relationship between text and pictures. The result is programs that can generate incredibly accurate images from text prompts.
AI image generators have been trained on combinations of existing images and captions, including photography, paintings, illustrations – really any image found online. They learn to identify what kinds of pictures match certain phrases, be it 'in the style of Picasso' or '50mm portrait photography', allowing them to create new and unique combinations of visual elements when given a text prompt.
But one of the things that makes AI image generators so powerful is just how easy they are to use. Once you have an account, you can go to the website, type in a text prompt and generate images. In theory, anyone can type in "a vase of flowers in the style of Van Gogh" or "a photographer taking a selfie in a desolate futuristic landscape' and get something that at least vaguely resembles that with no need to learn any particular skills.
However, it's not all perfect. AI image generators can't make value judgements on what looks good, realistic or even possible. They don't know how many fingers a human should have or how many legs a tripod should have.
But, that said, it is an exciting new field that has huge potential for the future of image production.
コメント