Creating Photos and Artwork
We have all seen science fiction movies with incredible visual effects. The images are so realistic that it is difficult to tell if they are real or fake and those movies take us to parallel universes that don’t even exist in our wildest dreams. The production of such images is a tedious process that involves a lot of expertise, manpower, and time.
With modern AI technology we can leverage neural networks that can create images from textual descriptions with incredible accuracy. A simple text input ("prompt") can generate an image of incredible detail and variation. Open AI's DALL·E model for example can generate images from textual descriptions of natural scenes and objects, often exhibiting remarkable detail and variation. This engine can understand complex prompts describing natural scenes, such as "a blue bird sitting on top of a large brown horse" and generate corresponding images.
The technology behind this is called Generative Adversarial Networks and it was invented in 2014 by Ian Goodfellow, a research scientist at OpenAI. Now – creating images of Star Wars themed bunk beds may sound like a lot of fun, but this technology can also be used for serious applications, such as improving the accuracy of medical diagnoses, ideation and product development and prototyping. This technology could have a profound impact on the way we consume media and the way we interact with each other. The metaverse is one example of how this technology can be used to create a virtual world that mimics the physical world. Imagine a world where you can meet with your friends and family in a virtual setting and interact with them as if you were in the same room.
The following image shows how we can use AI to reimagine real estate without the need to use Photoshop, but by simply removing parts of an actual photo and using a text prompt for instructing the AI to create a new image:
Creating artwork is another application for this technology. Imagine being able to generate a painting of a sunset just by describing it in words. You could even say that the piece should be an oil painting, a pencil and watercolour painting or even a digital painting and the AI would create the image for you.
This technology is still in its infancy and there are many challenges that need to be addressed before it can be used on a large scale. But the potential applications of this technology are endless and we are just beginning to scratch the surface.
Of course, in the hands of the wrong people, this technology could also be used for nefarious purposes, such as creating fake images and videos that could be used to spread misinformation. This is why it is important to ensure that this technology is developed responsibly and with the proper safeguards in place. It is not hard to imagine a future where AI generated images and videos are so realistic that it is impossible to tell if they are real or fake. We need to make sure that we are prepared for this future and that we can distinguish between real and fake images and videos.
Check out our online art exhibition: Pictures Of The Floating World
"An art collaboration between human and AI"
Here are some more examples how you could quickly turn ideas into visuals to inspire your product team. A donut in the shape of a cartoon character, an arm chair in the style of a mango, a steampunk styled smartphone, an action figure of a rockstar from the 1960ies – your ideas are the only limit!