Ongoing research project
Machine learning model: Midjourney
No postprocessing
WHAT'S IN THE PROMPT
The use of text-to-image machine learning algorithms is expanding. These artificial intelligence-powered apps turn written descriptions, often known as "prompts," into images.
Text-to-image machine models can be used to develop convincing concept art. The aforementioned ultra-sharp photography style of, for example, Midjourney really shines at any scale, whether it’s monumental interiors or intricate details. MidJourney is also more than capable of taking inspiration from a wide variety of different art mediums, styles, and historic artists. From ornate ‘paintings’ to blocky, abstract illustrations, analogue sketches to digital art.
As MidJourney images are used more widely, these aesthetics might start to feel "played out.” Especially for artists trying to create “original” artwork. Hence, the challenge with MidJourney is no in creating a beautiful image – that’s remarkably easy – but to pushing the model to create a distinct image with a novel style.