The idea of using a picture upload for automated verification is completely unviable. A much more commonly used system would be something like telling you to perform a random gesture on camera on the spot, like “turn your head slowly” or “open your mouth slowly” which would be trivial for a human to perform but near impossible for AI generators.
It’s not that difficult to identify if you have a good understanding of photography principles. The lighting on this image is the biggest tell for me personally, since I can’t visualize any lighting setup that can cast shadows in the directions that’s shown on this picture, it just instinctually looks wrong to me on first sight because of the impossible light sources.
That’s the reason the picture looks WRONG, even if you can’t identify the reason why it looks wrong.
I only focused on the nonsense background clutters because I think it’s easier for people who don’t work around cameras all day.
This is what makes this technology anxiety inducing at best…
So, for yourself, you have no issues seeing the artificiality of the image due to your extensive exposure to and knowledge of photographic principles. This is fair… that said, I have read your earlier comment about the various issues with the photo as well as this one about light sources, and I keep going back to scrutinize those elements, and… for the life of me… I cannot pick out anything in the image that, to me, absolutely screams artificial.
I’m fairly sure most people who look at these verification photos would be in a similar boat to me. Unless there’s something glaringly obvious (malformed hands, eyes in the wrong place, a sudden cthulhu-esk eldritch thing unnaturally prowling the background holding a stuffed teddy bear) I feel most people would accept an image like this at face value. Alternatively, you’ll get those same people so paranoid about AI generated fakes they’ll falsely flag a real image as fake because of one or two elements they can’t see clearly or have never seen before.
And this is only the infancy of AI generated art. Every year it gets better. In a decade, unless there are some heavy limitations on how the AI is trained (of which, only public models would ever really have these limitations as private models would train be trained on whatever their developers saw fit… to shreds with what artists and copyright said), there would probably be no real way to tell a real image from a fake out apart at all… photographic principals and all.
That’s not really the case but moreoever the gap is closing at a blistering pace. Approximately two years ago this stuff was in the distant future. One year ago the lid was blown open. Today we’re seeing real-time frame generation. This rallying against the tech is misguided. It needs to be embraced and understood. Trying to do otherwise is great folly as everything will fall even further behind and lead to even larger misunderstandings. This isn’t theoretical. It’s already here. We can’t bury our heads in the sand.
If you look at gaussian splatting and diffusion morphs/videos, this is merely in the space of “not broadly on hugging face yet” and not impossible, or even difficult depending on the gesture.
We’re months away from fully posable and animatable 3d models of these AI images. It already exists in demos and on arxiv, it runs on consumer hardware but not in realtime, so a video upload would work but a live stream would require renting a cloud GPU ($$$).
Having an AI act out random gestures is really not that different from generating an image based on a prompt if you think about it. The temporal element has already been done, the biggest factor right now is probably that it’s too computationally heavy to do in real time, but I can’t see that being a problem for more than a year.
More than that - these systems will eventually figure out how to not bitch the background so obviously. Then what? As others have said, we could switch to verification videos. That will be an extra year or two.
I think so. I don’t think there would be more than a few dozens of verification to do every day, with a dozen of mods, it seems doable in this context. It’s not like millions of users are asking for verification every day.
Her clavicles are asymmetrical, never seen that on a real person.
Shit, are you telling me that every time I see myself in the mirror I’m actually looking at a string of AI generated images, generated in real-time? The matrix is real. 😱
It’s either that, or my clavicles are actually very asymmetric. ☹️
You’re reaching. I don’t think this is “easy” to tell as you’re making it at all. You’re benefiting enormously from knowing the results before you begin extrapolating.
Yeah, I see what you mean, but my shoulders look almost exactly like that. Doesn’t hurt at all, just very annoying when carrying a backpack as the straps will always tend to slide off from my ‘drooping’ shoulder.
But I agree with your comments about the background, that looks like a fever dream. And of course my situation isn’t the norm, so the shoulders/clavicles can be treated as a red flag, it’s just not definite proof and care should be taken to realise some people might actually just be built weird.
Me neither. There’s clearly more pictures that aren’t included here, so maybe on one of those?
The odd thing about the hair in that picture to me is that on the left side of the photo, there’s one piece that seems to go on a nearly 90 degree bend for seemingly no reason, mid air. I don’t generally see hair get… Kinked like that. I suppose it’s not outside the realm of possibility, but it’s odd at least.
The rest of the hair seems fine to me, but I’m no expert.
I will note however that the object(s) in the background on the left side of the photo look like a gigantic (novelty sized) point and shoot camera from the 90’s. The box on top is the viewfinder and there’s the impression of a circle below that which would be the lens.
Just makes me giggle at the thought of such a large disposable camera.
every time I’d seen this photo, I only focused on the subject in the foreground, if I were the one verifying that the person in the photo is real, I’d have fallen for it. To me, the subject is entirely convincing. the issues you mentioned about the clavicles and hair, i think kind of make it a bit more convincing. Nobody is completely symmetrical for one, so seeing something like that, while not common, wouldn’t be necessarily uncommon. The hair, to me, just looks like normal person hair. sometimes hair do be like that.
Dude same, before I even read anything I was thinking ‘that’s a cute girl I didn’t know they started doing verifications on lemmy’ then I read and saw the whole hullabaloo.
An easy ‘solution’ to fix the background is to just use a mild blurring tool. They’re verifying you not your house, it wouldn’t be sus to just have a mild messy blur around you.
The bokeh effect is surprisingly hard to fake, actually, because it has to do with the physical properties of the camera lens. I think with a light Gaussian blur it would be even less convincing.
The “holes” on her cheeks are easy to miss but seriously unsettling close up. They’re not like freckles or blackheads but more like what termite tunnels look like in wood.
Due to having so many people trying to impersonate me on the internet, I’ve become somewhat of a expert on verification pictures.
You can still easily tell that this is fake because if you look closely, the details, especially the background clutter, is utterly nonsensical.
The point isn’t that you can spot it.
The point is that the automated system can’t spot it.
Or are you telling me there is a person looking at every verification photo, and if they did they would thoroughly scan the photo for imperfections?
The idea of using a picture upload for automated verification is completely unviable. A much more commonly used system would be something like telling you to perform a random gesture on camera on the spot, like “turn your head slowly” or “open your mouth slowly” which would be trivial for a human to perform but near impossible for AI generators.
…I feel like this isn’t the first time I heard that statement before.
It’s not that difficult to identify if you have a good understanding of photography principles. The lighting on this image is the biggest tell for me personally, since I can’t visualize any lighting setup that can cast shadows in the directions that’s shown on this picture, it just instinctually looks wrong to me on first sight because of the impossible light sources.
That’s the reason the picture looks WRONG, even if you can’t identify the reason why it looks wrong.
I only focused on the nonsense background clutters because I think it’s easier for people who don’t work around cameras all day.
This is what makes this technology anxiety inducing at best…
So, for yourself, you have no issues seeing the artificiality of the image due to your extensive exposure to and knowledge of photographic principles. This is fair… that said, I have read your earlier comment about the various issues with the photo as well as this one about light sources, and I keep going back to scrutinize those elements, and… for the life of me… I cannot pick out anything in the image that, to me, absolutely screams artificial.
I’m fairly sure most people who look at these verification photos would be in a similar boat to me. Unless there’s something glaringly obvious (malformed hands, eyes in the wrong place, a sudden cthulhu-esk eldritch thing unnaturally prowling the background holding a stuffed teddy bear) I feel most people would accept an image like this at face value. Alternatively, you’ll get those same people so paranoid about AI generated fakes they’ll falsely flag a real image as fake because of one or two elements they can’t see clearly or have never seen before.
And this is only the infancy of AI generated art. Every year it gets better. In a decade, unless there are some heavy limitations on how the AI is trained (of which, only public models would ever really have these limitations as private models would train be trained on whatever their developers saw fit… to shreds with what artists and copyright said), there would probably be no real way to tell a real image from a fake out apart at all… photographic principals and all.
Interesting times :D
That’s not really the case but moreoever the gap is closing at a blistering pace. Approximately two years ago this stuff was in the distant future. One year ago the lid was blown open. Today we’re seeing real-time frame generation. This rallying against the tech is misguided. It needs to be embraced and understood. Trying to do otherwise is great folly as everything will fall even further behind and lead to even larger misunderstandings. This isn’t theoretical. It’s already here. We can’t bury our heads in the sand.
If you look at gaussian splatting and diffusion morphs/videos, this is merely in the space of “not broadly on hugging face yet” and not impossible, or even difficult depending on the gesture.
We’re months away from fully posable and animatable 3d models of these AI images. It already exists in demos and on arxiv, it runs on consumer hardware but not in realtime, so a video upload would work but a live stream would require renting a cloud GPU ($$$).
Having an AI act out random gestures is really not that different from generating an image based on a prompt if you think about it. The temporal element has already been done, the biggest factor right now is probably that it’s too computationally heavy to do in real time, but I can’t see that being a problem for more than a year.
More than that - these systems will eventually figure out how to not bitch the background so obviously. Then what? As others have said, we could switch to verification videos. That will be an extra year or two.
The system doesn’t even need to get better at backgrounds, you just generate more images until one looks good.
I think so. I don’t think there would be more than a few dozens of verification to do every day, with a dozen of mods, it seems doable in this context. It’s not like millions of users are asking for verification every day.
Uh huh.
That’s esteemed Academy Award nominated verification picture expert/character actress Margot Robbie to you!
Now watch me win my Golden Globe tonight. (Still no best actress… sigh)
You sure you’re as dedicated to the awards as an actress as you are about posting to lemmy about android tech?
I’m hoping you win, as for best actress, they’re fools to not award you with that. So talented.
Keep doing what you’re doing.
Two win for Barbie is still winning, I guess.
On to the Oscars!
Shit, are you telling me that every time I see myself in the mirror I’m actually looking at a string of AI generated images, generated in real-time? The matrix is real. 😱
It’s either that, or my clavicles are actually very asymmetric. ☹️
What I meant is that her right clavicle (your left) is about an inch higher than her left.
I could be wrong, of course, but I imagine if that condition actually exists, then it would be extremely painful.
You’re reaching. I don’t think this is “easy” to tell as you’re making it at all. You’re benefiting enormously from knowing the results before you begin extrapolating.
Removed by mod
I’m sorry. ☹️
Removed by mod
Yeah, I see what you mean, but my shoulders look almost exactly like that. Doesn’t hurt at all, just very annoying when carrying a backpack as the straps will always tend to slide off from my ‘drooping’ shoulder.
But I agree with your comments about the background, that looks like a fever dream. And of course my situation isn’t the norm, so the shoulders/clavicles can be treated as a red flag, it’s just not definite proof and care should be taken to realise some people might actually just be built weird.
I’m not seeing the levitating hair
Me neither. There’s clearly more pictures that aren’t included here, so maybe on one of those?
The odd thing about the hair in that picture to me is that on the left side of the photo, there’s one piece that seems to go on a nearly 90 degree bend for seemingly no reason, mid air. I don’t generally see hair get… Kinked like that. I suppose it’s not outside the realm of possibility, but it’s odd at least.
The rest of the hair seems fine to me, but I’m no expert.
I will note however that the object(s) in the background on the left side of the photo look like a gigantic (novelty sized) point and shoot camera from the 90’s. The box on top is the viewfinder and there’s the impression of a circle below that which would be the lens.
Just makes me giggle at the thought of such a large disposable camera.
Curly hair can look like that when it’s curling tightly towards/away from you. It looks fairly natural to me.
every time I’d seen this photo, I only focused on the subject in the foreground, if I were the one verifying that the person in the photo is real, I’d have fallen for it. To me, the subject is entirely convincing. the issues you mentioned about the clavicles and hair, i think kind of make it a bit more convincing. Nobody is completely symmetrical for one, so seeing something like that, while not common, wouldn’t be necessarily uncommon. The hair, to me, just looks like normal person hair. sometimes hair do be like that.
Dude same, before I even read anything I was thinking ‘that’s a cute girl I didn’t know they started doing verifications on lemmy’ then I read and saw the whole hullabaloo.
Didn’t get the 5^th point, there’s only one clavicle visible, am I missing something?
Even so clavicles can be asymmetrical due to previous injury. We are pretty asymmetrical overall if you look closely enough.
Well she’s Margot Robbie, so her clavicles are symmetrical af. She probably just assumes the rest of us are like that too 😓
deleted by creator
An easy ‘solution’ to fix the background is to just use a mild blurring tool. They’re verifying you not your house, it wouldn’t be sus to just have a mild messy blur around you.
The bokeh effect is surprisingly hard to fake, actually, because it has to do with the physical properties of the camera lens. I think with a light Gaussian blur it would be even less convincing.
The “holes” on her cheeks are easy to miss but seriously unsettling close up. They’re not like freckles or blackheads but more like what termite tunnels look like in wood.
Nah. They just look like big pores. There are a few giveaways here that it’s AI generated, but the pores aren’t one of them.
Source: have big pores. Also, google images.
deleted by creator