“AI” image generation actually takes a lot of human knowledge and understanding of the models to manipulate outcomes. It is a different kind of effort, but the issues with it are based in human use of the tool.
I think the scale of image believability is logarithmic. Going from “believable at a glance” to “believable under scrutiny” requires an exponential increase in performance compared with going from “not believable at a glance” to “believable at a glance”. The same principle applies to text generation, facial recognition, sound generation, image enhancement, etc. One of the many reasons AI should not be being integrated in many of the ways world governments and corporations are trying to integrate it.
It’s unclear if the current models can reach that level though. They seem more like they’re asymtotically approaching their limit.
Maybe I’m wrong and GPT 5 will be the end all and be all - but I don’t think generalist models will ever be consistent enough. Specialist generators focused on specifics, trained to output very defined data seem more likely to be useful than this attempt to make a single catch all LLM.
Dang, that is pretty spot on! When I go camping, I often find myself contemplating a pretend fire in front of me while I prepare for carbon monoxide poisoning in my tent…but I keep my flaps open! Safety first!
Create 1,000 images with a model like Stable Diffusion XL, and you’ve produced as much carbon dioxide as driving just over four miles in a gas-powered car, according to the researchers Melissa spoke to.
The lighting doesn’t feel very natural. It’s inconsistent.
Her hair and face suggest a direct sunlight from the left, but the environment suggests indirect sunlight. The background trees should have more direct sunlight to the left.
The tentfire should also spill out some light to the environment.
The tent also suggests the sunlight comes from the right.
Consistent lighting is something AI is currently struggling with. It gives off a Photoshop edit vibe.
It’s funny how similar AI generated images are to accompanying drawings for “what are ten things that are wrong with this picture?” style questions in an IQ test.