[ad_1]
Digital arts are all the time trying to find new prompts to generate the following massive factor in AI artwork. A brand new characteristic on the generative AI design website Midjourney—referred to as Describe—lets creators add an image as the premise for his or her artwork tasks. Launched this week, it goals to take the guesswork out of producing pictures and artwork.
Describe works like every other Midjourney command, however as a substitute of /think about, a creator makes use of /describe. After getting into the command, a drop/drag field will come up, letting the creator add an image they need to use as the premise for his or her creation.
For this instance, we used a well-known image of John Whiteside Parsons, co-founder of the Jet Propulsion Laboratory on the California Institute of Expertise (CalTech). Parsons was an enigmatic determine who was additionally a follower of British occultist Aleister Crowley.
After the picture was uploaded to Midjourney, the AI gave 4 choices to generate the following image. For this instance, we selected “an outdated {photograph} of a person holding a wire, within the type of gritty Hollywood glamour, synthetist innovator –ar 16:9.”
Midjourney then produced 4 photographs based mostly on the immediate.
From there, we might make variations, upscale, remaster or obtain the picture.
An attention-grabbing footnote: Midjourney appeared to remedy a long-standing drawback it has: it might’t convincingly draw palms. Regardless of unimaginable leaps in synthetic intelligence, generative AI platforms proceed to wrestle with creating human palms. Specialists attribute this to a scarcity of information on the human physique that features photographs of palms given to this system to course of.
And voila! The AI seems to be studying. Very Cool. Or… creepy?
Keep on high of crypto information, get each day updates in your inbox.
[ad_2]
Source link
