Google has not too long ago introduced the subsequent model of its personal AI picture generator, Imagen. Imagen 2.0 makes loopy reasonable photographs — I can’t even inform what’s actual or pretend anymore.
In this text, I wanna put Imagen 2 up towards the opposite large AI picture generator Dall-E 3 by OpenAI and actually see what they each can do.
In the comparability take a look at, I might be utilizing the instance photographs launched by Google on its Imagen 2 announcement and ChatGPT for Dall-E 3. I’ll add all of the picture prompts so you may attempt them your self.
Let’s get began.
Prompt #1
A shot of a 32-year-old feminine, up and coming conservationist in a jungle; athletic with brief, curly hair and a heat smile
Well, it’s fairly apparent. The picture from Imagen 2 appears extra reasonable than the one from Dall-E 3, particularly with reference to pores and skin texture and hair particulars, which AI picture turbines typically battle with.
Prompt #2
Small canvas oil portray of an orange on a chopping board. Light is passing by means of orange segments, casting an orange mild throughout a part of the chopping board. There is a blue and white fabric within the background. Caustics, bounce mild, expressive brush strokes
The comfortable tones on the left picture give it a photorealism impact. But Dall-E 3 made a extra correct illustration of the blue and white fabric within the background.
Prompt #3
The robin flew from his swinging spray of ivy on to the highest of the wall and he opened his beak and sang a loud, pretty trill, merely to indicate off. Nothing on the planet is sort of as adorably pretty as a robin when he exhibits off — and they’re almost all the time doing it.