The companies behind these programs scraped billions of images from the web, including the hard work of artists, both dead and alive. The other major issue that artists pointed out was that the databases of these image generators-DALL-E 2, Midjourney, Stable Diffusion-are largely built off existing images from artists. If anyone could make a painting in just a few seconds, why would someone need to commission an artist to produce an illustration, or even bother spending years learning art at all? Tech enthusiasts lauded the achievement, while artists were largely concerned and critical. Realistic, near-instant image generation was suddenly here-and reactions were just as potent as their creations. The State Fair work showed this technology had taken a giant leap forward in its sophistication. The winning painting wasn’t made by a human, but by an artificial intelligence app called Midjourney, which takes text prompts and turns them into striking imagery, with the help of a neural network and an enormous database of images.ĪI-based text-to-image generators have been around for years, but their outputs were rudimentary and rough.
Afterwards, Jumalon illustrated the above based on those concepts.īack in August, controversy erupted around the winning submission of the Colorado State Fair’s art content. The initial concepts for this painting (pictured below) were produced by the AI image generator app Midjourney.
0 kommentar(er)
