Midjourney: AI creator for images

Midjourney, currently in an open Beta version, generates images from natural language descriptions or prompts. It works best with good prompting (photographic style, Japanese style…)  and allows continuous refinement in versions or variations or alternatives. It works very satisfactory for creative work, artwork or illustrations. Due to the heavy use of the service, there is no free usage anymore, the cheapest subscription starts at 10 USD per month. At present Midjourney must be accessed via Discord bot commands but it is expected that Midjourney will launch its own web interface in the future. Response time is quite short (about a minute) and the images it produces are certainly suitable for brainstorming, idea generation and even for publication. Users can use Midjourney through Discord either through their official Discord server, by directly messaging the bot, or by inviting the bot to a third-party server. To generate images, users use the /imagine command and type in a prompt, the bot then returns four images, which users are given the option to refine or upscale. To generate images on the Midjourney website itself, users must first have generated at least 1,000 images through the bot.