[HN Gopher] Show HN: AI-generated images that look like real life
___________________________________________________________________
Show HN: AI-generated images that look like real life
Author : spaceman_2020
Score : 33 points
Date : 2024-10-07 20:38 UTC (2 hours ago)
(HTM) web link (www.gounfaked.com)
(TXT) w3m dump (www.gounfaked.com)
| spaceman_2020 wrote:
| so a few days back, I discovered that with the new Flux v1.1 pro
| image gen model, if you use a prompt like "IMG_XXXX.HEIC", you
| get some extremely realistic images.
|
| I spent a few hours playing around with it, trying out a ton of
| combinations. Ended up with a very large library of images and
| decided to make a quick website to share it.
|
| Some notes and observations:
|
| 1. Using a prompt like "IMG_XXXX.HEIC" tends to yield the most
| realistic images, but most of these tend to be rather mundane
| images of landscapes, flowers, poorly shot cityscapes
|
| 2. Adding "IMG_XXXX.HEIC posted on Snapchat in [year]" yields
| more realistic, casual images of people. However, a lot of these
| look like screenshots, complete with the Snapchat UI. Most people
| also tend to be attractive.
|
| 3. Adding a [year] in the prompt yields some interesting images.
| Like [2017] will yield blurrier images than [2023]. Adding [2021]
| in the prompt got images with face masks and face shields
|
| 4. The prompt "[firstName] [lastName] selfie" gets real-looking
| selfies of real-looking people. You can use Indian, Hispanic,
| Chinese, European, American, etc. names and get realistic images
| of people with these ethnicities. Example:
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/pc5JnhNRUEq...
|
| 5. There is a decently high failure rate. The ~750 images on the
| site are hand picked. I had to delete around 220 images for not
| meeting the criteria (not real enough) or being just bizarre
|
| 6. If this model is any indication, its soon going to be
| impossible to tell what's real online
| joegibbs wrote:
| Wow that's amazing, you really can't tell. What is it that
| gives most AI images that not-quite-real look? Is it due to
| airbrushed images in the training data, including cartoons, 3D
| renders and illustrations or all of that?
| Hasnep wrote:
| The image linked in that comment has a background that's half
| car and half building, but yeah apart from that minor detail
| it's pretty hard to tell.
| mkl wrote:
| Most of these look very good! Signs, text, clocks, number
| plates, and girders or spindly branches tend to go wrong. There
| are a few mutant hands [0].
|
| Mountain Sheep in Snow [1] looks fake to me - the sheep are
| more like dogs fading back to rocks, and have different scales.
|
| Underground Time Display [2] looks obviously fake as the
| clock's colon is in the wrong place and the sign has fake
| writing.
|
| [0] https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/ozjUKlysLq
| l...,
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/XcNnWM6L54Q...
|
| [1]
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/It9DhumKX7w...
|
| [2]
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/GygiLirdHvq...
| puttycat wrote:
| Given your technique, how can one verify these aren't just
| copies of the training data?
| madamelic wrote:
| I wonder how far into generative AI will have people developing
| "intractable FOMO" where they see a beautiful place but then they
| find out they can't visit it because it doesn't exist.
|
| Are we seeing it already from people who are getting irrationally
| angry about generative AI?
| spaceman_2020 wrote:
| Honestly the output from this model was a little scary. I could
| always tell AI generated people and images prior to this
|
| But most of the images here are just mundane enough that they
| could have been taken by your average smartphone user
| mattgreenrocks wrote:
| I definitely can't tell, even knowing that these are from AI.
|
| GeoGuessr-like sites are going to get trolled hard with AI
| photos of nonexistent locations.
| _sys49152 wrote:
| cityscapes and urban photography - only a handful of examples
| given but those images still got a ways to go
| slau wrote:
| A bunch of the people images are very clearly AI though. I'd
| wager about 30-50% of them could be recognised as generated
| by people with a bit of understanding of how these models
| work.
| ninetyninenine wrote:
| nobody knows how these models work. Not even experts. These
| are black box algorithms where people understand these
| things in terms the analogy of a best fit curve in a series
| of data points. Outside of this analogy... nobody
| understands how generative AI works.
|
| What made a model for a specific situation choose to
| generate a hand with 6 fingers instead of 5? Or 5 instead
| of 6? Nobody knows.
| jprete wrote:
| That's well above the threshold for destroying even the
| pretense of photographs having any information value on the
| Internet.
| ninetyninenine wrote:
| A little scary? You realize all the output generated by AI is
| only going to get more and more and more real right?
|
| Follow the trend line. You'll be seeing stories, movies and
| works of art better than humans in the not too far future.
| anigbrowl wrote:
| [delayed]
| sync wrote:
| Great work! I think you have a business similar to Lummi[0] if
| you:
|
| - Enhance search capabilities
|
| - Add a paid API
|
| - Add a whole lot more images :)
|
| Other royalty free image APIs out there like Unsplash[1] have
| difficult licensing terms. AI is poised to disrupt this space.
|
| [0]: https://www.lummi.ai [1]: https://unsplash.com/developers
| 1024core wrote:
| Throw these into a captioning system to generate captions, index
| those captions with something like ElasticSearch and voila!
| bentocorp wrote:
| Until AI generated imagery has been tested by the legal system it
| may be a bit too optimistic to call this "Royalty-free,
| copyright-free gallery of images".
|
| How different from a source image do these AI generated images
| need to be to be considered "copyright free"?
|
| If I grab a series of photos from shutterstock, run them through
| a generative AI photo enhance process to improve the white
| balance, contrast and levels is that adequate enough to be
| considered "copyright free"?
| ninetyninenine wrote:
| >If I grab a series of photos from shutterstock, run them
| through a generative AI photo enhance process to improve the
| white balance, contrast and levels is that adequate enough to
| be considered "copyright free"?
|
| Hard to say. If I had the generative AI copy the photo but
| change the time of day and angle then would it be copying?
|
| What if I went to the same location and changed the angle and
| the time of day? Would that be copying?
|
| AI is essentially "drawing" the same photo from a different
| time and angle. What if I did the same thing photorealistic-
| ally by hand in photoshop? Would I be copying if I painted the
| picture in the same way the AI did it??
|
| I want you to consider what I'm doing here with my reply. I am
| admitting to a crime right now. What I have done with this
| reply is literally rip off different vocabulary words and
| certain short phrases from books all over the world and mixed
| up those words and phrases to produce the reply here. I am
| ADMITTING to copying those books.
|
| You going to accuse me of a crime even if I admitted to it? No.
| But if I did the same thing with AI.... you going to accuse me
| then?
| amelius wrote:
| Your argument is based on a series of slippery slopes that
| I'm sure a judge would not tread on.
| ninetyninenine wrote:
| I didn't even make an argument. I'm saying it's not clear
| cut.
| jessriedel wrote:
| > Until AI generated imagery has been tested by the legal
| system it may be a bit too optimistic to call this "Royalty-
| free, copyright-free gallery of images".
|
| Although it's conceivable there's a surprise legal finding,
| companies like OpenAI and Anthropic are confident enough in how
| it will go that they are willing to insure you for any
| lawsuits, which would be ruinous for them if they consistently
| lost.
|
| (One can certainly argue that AI means the law _should_ change,
| but that 's a separate question.)
|
| > If I grab a series of photos from shutterstock, run them
| through a generative AI photo enhance process to improve the
| white balance, contrast and levels is that adequate enough to
| be considered "copyright free"?
|
| No, just like it's not enough for me to grab a photo and change
| white balance and contrast. AI doesn't change anything here.
| Copyright infringement is generally tested by comparing the two
| works directly.
|
| > How different from a source image do these AI generated
| images need to be to be considered "copyright free"?
|
| The same way it's always tested: "substantial similarity"
|
| https://en.wikipedia.org/wiki/Substantial_similarity
| jprete wrote:
| > Although it's conceivable there's a surprise legal finding,
| companies like OpenAI and Anthropic are confident enough in
| how it will go that they are willing to insure you for any
| lawsuits, which would be ruinous for them if they
| consistently lost.
|
| I don't think this is the right interpretation, at all.
|
| They can act confidently about this because corporations
| can't go below zero; the downside of the bet is so far in the
| red, in that zone of bankruptcy, that it actually makes the
| bet work even if they internally believe that they're likely
| to lose in court.
| 7874cole wrote:
| Your website is loading forever, is it down?
| mrtksn wrote:
| The vibe I'm getting, they try to make it look real by making it
| dull.
|
| The problem with AI images is that they don't make sense and by
| making the image dull, it reduces the urge to make sense of it I
| guess.
|
| AI images have very low fidelity. You know the "A picture is
| worth a thousand words" phrase? I think AI images fail on that
| because they are not an instance of a very complex system but a
| very concentrated subject if you know what i mean.
|
| When someone captures a picture of a dog, that's actually a
| picture of a story about the past; That is, the surrounding
| environment is arranged in a way that you can tell what just
| happened moments ago or years ago. AI Pictures lack that story
| and that's why I think the dull images are easier to pass as real
| because they don't induce you to think about the moments ago.
| Retr0id wrote:
| AI-generated images aren't worth a thousand words, at least for
| now, because the "prompt space" is just too small.
| mmastrac wrote:
| This trick has been floating around for about a week -- earliest
| ref I could find:
|
| https://x.com/fofrAI/status/1841854401717403944
| lsy wrote:
| I guess the question is: Who cares? What is this for, except
| illustrating blogspam?
|
| It seems that more resources are being poured into verisimilitude
| across generative models, but what is the business model or even
| human use case for it?
|
| A picture of a glorious landscape seems worthless to me without
| any grounding to be able to ask a question like, "where is
| that?", "when do those flowers bloom?", "what is on the other
| side of that mountain?" and receive any kind of interesting
| answer.
| elicksaur wrote:
| 1. Scams. Human deepfakes/fake-fakes to make you believe you're
| communicating with a real person.
|
| 2. Self-image editing. You want a picture of yourself doing
| something you are unable to do. Could be benign, but very
| likely being used as a scam on social media in some way.
|
| 3. Marketing. Putting your product in some setting without
| having to do a photoshoot. People will argue this isn't a form
| of scam, but it seems suspect to me.
| ctrlw wrote:
| Congrats, they do look good at first glance, without the usual
| overly shiny look, and the pure Nature images do look real to me.
| I'd really like to visit some of these places.
|
| However, details are still off, e.g.
|
| * the guy you linked to apparently sits in a car, but the ceiling
| looks like a house (at least I've never seen a vehicle like
| that). Reversed issue with this guy:
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/EeJBCnNsZG1...
|
| * the bicycle guy sits in the air, and the bike is mutated in
| several places:
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/WrfWYZlthe2...
|
| * The face in Yoga in the field is distorted:
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/BUcURAtyzjb...
|
| * Hands are ok-ish but not yet solved:
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/SeO8u2HZ-V2...
|
| * Any text is obviously fake, which also affects urban
| environments. Agree with this caption:
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/oc6eI5w2kQQ...
|
| Bonus points for this portrait where the tower seems to have a
| face as well:
| https://d1l4k1vcf8ijbs.cloudfront.net/fakeimages/6ho0FIV-i2t...
___________________________________________________________________
(page generated 2024-10-07 23:00 UTC)