The battle of AI art generators has intensified as big tech giants enter the ring. While the space is currently dominated by DALL-E 2, Stable Diffusion, and Midjourney, Microsoft, Meta, and Google have all announced text-to-image (or text-to-video) tools on the way. Now Google has just made its offer public – or at least part of it.
Google first gave us a glimpse of Imagen, its AI image generator, in May with the release of a proof-of-concept document and the launch of a website showcasing some of the tool’s results. He just released limited features of the tool to the public – and they’re oddly specific (for more on how AI art generators work, check out our article on using DALL-E 2).
Image 1 of 2
A product created in Google’s AI test kitchen, Imagen is a powerful AI text-to-image art generator that can turn written prompts into compelling images. The results shared so far suggest that it can stand up to the best AI art generators, which have generated a lot of controversy due to their increasingly compelling results and concerns over copyright. , abuse and the future of artists’ jobs.
Despite the controversy, the genie really seems to have come out of the bottle with the big tech heavyweights entering the scene. Microsoft Designer looks set to offer what looks like a form of AI clip art while Meta’s Make-a-Video promises to offer a text-to-video generator. Google beat them to a public release with the launch of Imagen (opens in a new tab) in beta version. but it retains most of the tool’s power.
We still won’t have the ability to use text prompts like “a cute corgi living in a house made of sushi” or a dragon fruit wearing a karate belt in the snow (animals and fruits are more of a topic). popular for AI imaging, see results above). All we can create are fantastic buildings and Pixar-style monsters.
Image 1 of 2
For now, we have access to two functions of Google Imagen: ‘City Dreamer’ and ‘Wobbler’. The first allows users to describe a city to model SimCity-like isometric designs. Let’s say you want a city made of cookies, for example. City Dreamer will offer you designs of plots and buildings. Wobbler, on the other hand, allows users to create and dress up a little monster. They can choose the material to make it, for example felt or marzipan, dress it then make it dance by stitching it.
Such a specific tool, with a very specific aesthetic, nowhere offers the creative options offered by existing AI image generators. But that doesn’t mean Google doesn’t have them. Considering the controversy around AI art, it looks like Google is playing it safer than other platforms have. He says the beta is meant to gather feedback from the community so they can refine the tool and fix any issues before the full release.
The other issue is that, as with many such tools, there is a waiting list. You can apply through the AI Test Kitchen app, available on Google Play (opens in a new tab) and the iOS App Store (opens in a new tab).
What is Google Imagen?
Google Imagen is the search and tech giant’s AI-powered text-to-image generator. Google revealed the tool in May in a research paper and website that shows capabilities that closely resemble those of tools like DALL-E 2. It has now released two limited parts of the platform. publicly available in beta via its AI test. Kitchen.
Read more:
#Google #finally #public #amazing #imaging #tool #sort