Member-only story
It comes as no surprise that the massive brainiacs working for Google are improving upon text-to-image technology that powers a slew of artificial intelligence art platforms.
I utilize quite a few of them, myself, and have sold some NFTs created with them.
These days, my favorite two apps are Starry AI and Night Café, both of which I utilize frequently to generate “art.”
Because I click on stories related to AI art and VQCLIP+GAN, Google has placed some stories about its own emerging technology, Imagen, in my Google feed.
It appears as if the engineers who are creating this have, indeed, come up with something above and beyond the typical DALL-E 2 and other competing text-to-image methods. As with other technologies, it stands to reason that text-to-image generators will continue improving, likely to the point where nobody will be able to discern a real photo from a generated image.
Imagen’s website, itself, refers to the technology as a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding.
