OpenAI, the latest creation, DALL-E is able to generate images from natural language text thanks to artificial intelligence.
OpenAI, artificial intelligence is already able to generate images from text
Artificial intelligence continues to grow by leaps and bounds. It is no longer just capable of producing text with stunning precision, beating chess players, and taking on professional video game teams, to name a few examples. It is now able to produce realistic images from descriptions written in natural language.
OpenAI, an artificial intelligence research company co-founded by Elon Musk and backed by Microsoft, has developed a system called DALL-E. This is a neural network that lays the groundwork in GPT-3 for interpreting the text, associating with various visual concepts, and creating images. In some cases, the results are so good that they look like real photographs.
DALL-E is brought to life by 12 billion parameters of GPT-3, the third-generation self-regressive language model based on Deep Learning that will be launched in May 2020. This artificial intelligence program combines a wide range of concepts related to common expressions. One of its most striking features is that it can create objects that do not exist.
DALL-E, artificial intelligence accomplishes what it sets out to do
You should not try too hard to think of something rational. The system has the ability to combine concepts to create entirely new concepts. For example, if you want to see any object walking with a dog, your wishes become your commands. DALL-E’s artificial intelligence will create any objects while walking with your pet. As if that wasn’t enough, you’ll get a series of images from which you can choose the most pictorial one.
On the other hand, if you ask for a living room with armchairs and a painting of the Colosseum in Rome, the artificial intelligence system will present you with a series of images based on its interpretations. According to the OpenAI team, unlike 3D rendering engines, DALL-E is able to substitute details that are not explicitly stated before presenting the results.
OpenAI is one of the companies that has made the most progress in the field of artificial intelligence. One of its long-term goals is to build “multimodal” neural networks. The company claims that DALL-E could better understand the world thanks to its ability to learn different visual and textual concepts.