The AI-generated ones are also human-made; the difference is that an AI messed with them.
Show HN: Can you tell if an image is AI-generated?
91–100 of 107 posts
Re: Show HN: Can you tell if an image is AI-generated?
#92You correctly classified 25 of 30 (83%) images!
You identified 12 of 12 (100%) AI-generated images.
You identified 13 of 18 (72%) human-made images.
Re: Show HN: Can you tell if an image is AI-generated?
#93I wonder if all the text people input here, about the models' mistake, could help the model somehow.
Re: Show HN: Can you tell if an image is AI-generated?
#94You're not even going to tell me which ones I got right?
I only got one wrong and I want to know which one I missed.
Re: Show HN: Can you tell if an image is AI-generated?
#95I was looking for tells, but things like landscapes or pictures where there's no hands or eyes tend not to have them as much.
If you can see a certain vagueness in a landscape, its AI. A stone/mountain/grass/river/hill can appear diffusing/blending to become something else.
Re: Show HN: Can you tell if an image is AI-generated?
#96Earlier quoted context omitted.
> Actually no, they were not cherry picked. Except for generations which did not match the prompt at all Second sentence describes process of selection. Is there difference in English between "filtered" / "selected" and "cherry picked"? Is "cherry picked" implying extreme filtering?
Filtered is the process of removing parts from the whole. Like how a water filter removes unwanted chemicals. Selected means it was chosen. So after filtering you could make a selection from all or part of the remaining choices. Cherry picked, means selected individually to meet a goal. Selecting very bad results to be removed is almost the opposite of cherry picking. Cherry picking would be picking only the best ima…
> picking only the best images and presenting them
> they removed the worst images and showed the rest
Is removing rejects not a way to pick only the best?
Re: Show HN: Can you tell if an image is AI-generated?
#97To go through all that and not be shown the answers at the end is beyond infuriating.
If you save your email, full results will be emailed next week.
Re: Show HN: Can you tell if an image is AI-generated?
#98How about you pay us for training your models instead of doing it for free!
These results are not used (at least by me) to train models.
Re: Show HN: Can you tell if an image is AI-generated?
#99The city drawings have very obvious underdiffusion in them.
Re: Show HN: Can you tell if an image is AI-generated?
#100Earlier quoted context omitted.
Filtered is the process of removing parts from the whole. Like how a water filter removes unwanted chemicals. Selected means it was chosen. So after filtering you could make a selection from all or part of the remaining choices. Cherry picked, means selected individually to meet a goal. Selecting very bad results to be removed is almost the opposite of cherry picking. Cherry picking would be picking only the best ima…
> picking only the best images and presenting them > they removed the worst images and showed the rest Is removing rejects not a way to pick only the best?
To me, there’s no right answer, hence why I listed set of examples and ended list with etc.
Based on my own experience, selecting images that fit the prompt and images that just happened to be generally speaking a fit for the creator are different modes of producing outputs to share.
That said, as it relates to the topic of this HN post, understanding the systems, assumption, workflow, etc used to render the survey, its content, and results to me are vital to understanding what actually going on.