AI artwork is cropping up in all places. And if the explosion of AI picture mills weren’t sufficient, an engineer has simply designed a weird compact ‘AI digital camera’ that turns photographs of actual scenes straight into novelty AI-generated pictures.
DreamGenerator runs Steady Diffusion (see our decide of one of the best AI artwork mills) to remodel pictures as quickly as they’re taken. Described as “a toy that sparks new concepts and provides an surprising twist to on a regular basis images”, it offers 30 themes to select from. However why?
Introducing DreamGenerator! 📸✨A digital camera that transforms your pictures into one thing new utilizing the ability of generative AI.Select from 30 prompts, seize, and watch as your picture morphs right into a one-of-a-kind masterpiece proper earlier than your eyes! 🧵 pic.twitter.com/NJMxQ09RnaJuly 18, 2023
Presently solely a prototype, DreamGenerator is a wierd proposition. The immediate ‘themes’, which embrace ‘retro’, ‘sci-fi’, ‘fairytale’ and ‘pirate’, really feel like an extension of the idea of smartphone filters, though they remodel pictures in additional radical methods. In concept, the generated pictures reference the composition and pose of the unique picture, however some examples seem to indicate generations that look utterly completely different from the supply.
The bigg query is why put this in a digital camera physique slightly than in an app for one of the best cameraphones? And even why not simply make the AI transformation in post-production on one other machine?
Effectively, the digital camera’s creator Kyle Goodrich, a 3D artist and augmented-reality product designer at Snapchat, says the purpose is to make AI artwork less complicated. He says that many AI picture mills provide difficult consumer experiences. The simplicity of a point-and-shoot digital camera would make AI artwork era extra intuitive.
“AI picture mills are a sport changer, however arising with the proper immediate is hard,” Goodrich writes on Twitter. “Plus, navigating a few of these platforms looks like fixing a puzzle. I needed to simplify this course of and create a software that mixes intuitive design with the ability of AI.”
He added: “I really like my DSLR, however lugging round a cumbersome digital camera can really feel like a burden. Sensible telephones do an honest job, however there’s one thing simple concerning the simplicity of a point-and-shoot… and I discover that I take much more pictures.”
DreamGenerator appears to be like and works far more like a conventional digital camera than a earlier instance of an AI digital camera that we noticed – the Paragraphic digital camera, which has no lens and Google Road View information slightly than pictures to generate AI artwork. Goodrich’s machine has a fundamental digital camera module that feeds pictures to a Raspberry Pi pc operating an occasion of Steady Diffusion and ControlNet. A easy interface permits a consumer to take a photograph after which toggle by means of the immediate themes. The unique picture seems within the viewfinder however is rapidly remodeled in response to the theme chosen. Totally different buttons allow you to generate variations of a picture.
However whereas the UX is easier and extra intuitive, the outcomes would appear to be far more restricted, even when a ultimate product launched greater than the 30 themes used on the prototype. It is not clear if the unique picture can be saved, and Goodrich hasn’t clarified the place the computing takes place – given the scale of the machine we presume it offloads to the cloud slightly than processing the photographs on the machine itself (in the event you’re wanting to make use of AI artwork in post-production, see our information to one of the best AI artwork tutorials).