Midjourney describes itself as “an independent research lab exploring new mediums of thought and expanding the imaginative powers of the human species.” This is a text-to-image AI system that produces unique images from human text input.
Trained on millions of artworks (often without author consent, which raises much controversy around the model), Midjourney is best known for its artistic, not photographic style. The resulting images rarely look like photographs — they seem more like paintings, so the model is best for creating video game-type images. Midjourney is only accessible through Discord. The first 25 images were free as it launched, however, now it's fully subscription-based.
Best AI Text-to-Image Generators: What Designers Think
Generative AI refers to the subset of artificial intelligence focused on creating new content, ranging from images and music to text and more.
Text-to-Image Translation (T2I)
Text-to-image (T2I) translation is a type of artificial intelligence that generates an image based on a written description or a textual prompt.
Stable Diffusion is an open-source text-to-image model by CompVis Group at LMU Munich, released in 2022.