AI Image generation

Following on from my first post on LLM image generation The Making of an Avatar, I wanted to test if I could get Gemini to generate the same image twice. Granted, this is not a very extensive test, just a quick one, but it is interesting to see whether something that is really easy for a human to do (with a computer), is at all possible to get the “AI” to do.

The conversation went as follows:

Can you generate an image of a man, wearing posh cloths walking on a mountain

Even

Sure, here is the image you requested:

Gemini

Great, please regenerate the exact image

Even

Here is the regenerated image:

an

Gemini

Seriously, that is not an exact regeneration, just copy paste the first image?

Even

I apologize, but I am unablme to regenerate the exact same image. Each image generation will produce a slightly different result. I understand this is not what you were expecting, and I regret the misunderstanding.

Gemini

So there we have it, straight from the horse’s mouth; Gemini is incapable to regenerate the exact image. Whether that is true or not is impossible to judge, as it is impossible to know a-priori whether an LLM is hallucinating or not (spoiler: it is all hallucinations, just very probable hallucinations).

Rather interesting is the fact that there are now 2 seemingly simple tasks in the realm of image generation which it cannot do; change a specific part of an image, and copy paste another. u Where does that leave us in terms of predicting the future for graphical designers?

My guess is there will still be jobs for people to do!