A new Midjourney feature called Describe aims to take the guesswork out of generative AI art. It works like any other Midjourney command, but instead of using /imagine, you use /describe. After entering the command, a drop / drag box appears, allowing you to upload a picture you want to use as the basis for a creation. It was launched last week with a tweet,
Today we’re releasing a /describe command that lets you transform images-into-words. Give it a shot! We think this tool will transform your liguistic-visual process both in terms of creative power and discovery.
Tech site Decrypt uploaded a famous picture of CalTech jet propulsion scientist John Whiteside Parsons, who was a follower of British occultist Aleister Crowley.
From the four options they were offered they than chose the prompt “an old photograph of a man holding a wire, in the style of gritty Hollywood glamour, synthetist innovator –ar 16:9”.
Midjourney then produced four images based on that prompt.
They chose this one and from there they were able to make alterations to the image to suit their particular requirements.
And produced a result that they felt represented a good balance of science, occultism and period drama.
For advice, guidance and support on how to go about safely using machine learning for content creation yourself, feel free get in touch via the Mondatum Contact Us page.