Midjourney is an AI model that generates images based on user inputs. The results depend on how the company's AI interprets the associated words and style. Following the input, the AI makes an image for the user. Artists follow the platform on Discord to see the designs for inspiration or to make creations. Midjourney licenses the designs from creators, and users own the images. Design studios and marketing firms utilize these generated assets to design and create mock-ups for clients.
Users of the product are allowed to sell the images that are generated but they waive the right to exclusivity if another individual recreates the image with similar inputs. However, users who pay for higher tiers of service are given access to a private Discord, where they can pick and choose the creations that remain private or open to the public, as well as the inputs that generate the creations.
Midjourney's image-generating software went into limited beta on March 21, 2022, and open beta on July 12, 2022. In July 2022, the research lab began testing the third iteration (V3) of its image-generating algorithms. V5 of Midjournery was released on March 15th, 2023. The model improves how it interprets natural language prompts, generates higher-resolution images, and supports advanced features, such as repeating patterns. In April 2023, the company released a new feature reversing the image generation process, allowing users to transform images into words.