Google’s Imagen 4 text-to-image mannequin guarantees ‘considerably improved’ boring pictures

Google has unveiled its newest text-to-image mannequin Imagen 4 with the same old promise of “considerably improved textual content rendering” over the earlier model, Imagen 3. The corporate additionally launched a brand new deluxe model known as Imagen 4 Extremely designed to observe extra exact textual content prompts for those who’re keen to pay further. Each arrive to a paid preview within the Gemini API and for restricted free testing in Google AI Studio.

Google describes the principle Imagen 4 mannequin as “your go-to for many duties” with a worth of $.04 per picture. Imagen 4 Extremely, in the meantime, is for “while you want your pictures to exactly observe directions” with the promise of “robust” output outcomes in comparison with different picture mills like Dall-E and Midjourney. That mannequin boosts the value by 50 % to $.06 per picture.

The corporate confirmed off a spread of pictures together with a three-panel comedian generated by Imagen 4 Extremely exhibiting a small spaceship being attacked by a large blue… house lizard? with some sound results like “Crunch!” and inexplicably, “Had!!” The picture adopted the listed immediate beat for beat and appeared okay, not in contrast to a toon rendering from a 3D app.

One other immediate learn “entrance of a classic journey postcard for Kyoto: iconic pagoda beneath cherry blossoms, snow-capped mountains in distance, clear blue sky, vibrant colours.” Imagen 4 output that to a “T,” albeit in a generic fashion missing any attraction. One other picture confirmed a mountaineering couple waving from atop a rock and one other, a faux “avant garde” vogue shoot. The pictures have been positively of excellent high quality and adopted the textual content prompts exactly however nonetheless appeared extremely machine generated.

Imagen 4 is ok and does appear a light enchancment from earlier than, however I am not precisely wowed by it — significantly in comparison with the market leaders, Dall-E 3 and Midjourney 7. Plus, following an preliminary rush of enthusiasm, the general public appears to be getting sick of AI artwork, with the principle use case apparently being spammy advertisements on social media or on the backside of articles.