Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

mejorarimagen.org

Post reply on HN
Print view View original

41–50 of 75 posts

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#41

Post by Jaxan »

virtualritz wrote: post #20

Tried it with some typical event photos of people that contain out-of-focus regions. Did a pretty terrible job. I.e. at 10k, you should see some skin structure but instead it was just color banding, eyelids had non-existing wrinkles added though etc. To the author: PM me and I send you some examples, if interested.

Skin texture is very hard it seems. I’m often developing raw photos and the noise reduction often remove skin texture too much. Especially when I was editing photos of our newborn, there is just so much little details that easily gets lost in noise reduction (or compression) that are very clearly visible to the eye.

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#42

Post by pavel_lishin »

After submitting an image, I'm prompted to authenticate with Google - but once I do, and return, I have to re-submit the image.

Also, it does ... not do great with faces, but I also did not expect it to: https://imgur.com/a/GCLbMGp

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#43

Post by pavel_lishin »

thih9 wrote: post #14
jasfi wrote: post #8

Earlier quoted context omitted.

These enhance effects typically use guesswork. That would be useful to gain hints, but not to know for sure what the original looked like.

Unless the rest of the image offers details that the human observer would ignore but the AI would pick up. E.g. low res photo from 1828 of a US president - enhance to John Quincy Adams. Surprisingly there's a daguerreotype of John Quincy Adams from 1843[1], the AI could use that; perhaps "enhance" the time backwards a bit, to make him 15 years younger. [1]: https://en.m.wikipedia.org/wiki/File:John_Quincy_Adams_-_cop…

Isn't that what Samsung was doing with photos of the moon?

https://www.theverge.com/2023/3/13/23637401/samsung-fake-moo...

But I also had a similar thought. Use a combination of an image search engine like TinEye, and something like ClearviewAI, to actually either find a larger image of the submitted photo, or of more photos of the person in question, and reconstruct what they look like based on all of that additional data.

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#44

Post by pavel_lishin »

itishappy wrote: post #27
thih9 wrote: post #14

Earlier quoted context omitted.

Unless the rest of the image offers details that the human observer would ignore but the AI would pick up. E.g. low res photo from 1828 of a US president - enhance to John Quincy Adams. Surprisingly there's a daguerreotype of John Quincy Adams from 1843[1], the AI could use that; perhaps "enhance" the time backwards a bit, to make him 15 years younger. [1]: https://en.m.wikipedia.org/wiki/File:John_Quincy_Adams_-_cop…

Right, and that would be guesswork unless the image had been explicitly tagged.

There are search engines that search for similar images; a small photo of John Quincy Adams may be 99.99% identifiable as such.

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#45

Post by thih9 »

itishappy wrote: post #27
thih9 wrote: post #14

Earlier quoted context omitted.

Unless the rest of the image offers details that the human observer would ignore but the AI would pick up. E.g. low res photo from 1828 of a US president - enhance to John Quincy Adams. Surprisingly there's a daguerreotype of John Quincy Adams from 1843[1], the AI could use that; perhaps "enhance" the time backwards a bit, to make him 15 years younger. [1]: https://en.m.wikipedia.org/wiki/File:John_Quincy_Adams_-_cop…

Right, and that would be guesswork unless the image had been explicitly tagged.

Guesswork, deduction, tomayto, tomahto ;)

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#46

Post by xiconfjs »

tiffanyh wrote: post #37
xiconfjs wrote: post #10

Not as good yet (at least in this case): * original: https://upcdn.io/12a1z2u/image/uploads/2024/07/18/4kU68cBDKF... * "10K" enhanced: https://replicate.delivery/czjl/gFpKKIlEKKZrL1lfqxXlpQrOBbe9...

The "10k" version is no longer available.

re-upload:

* Source: https://up2store.de/file/tFzMzhLASJf0f063/scBeS937Dc1IderR/4...

* „10k“-version: https://up2store.de/file/tFzMzhLASJf0f063/MesMFZTpfqt4qpSt/o...

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#47

Post by Sohcahtoa82 »

pavel_lishin wrote: post #42

After submitting an image, I'm prompted to authenticate with Google - but once I do, and return, I have to re-submit the image. Also, it does ... not do great with faces, but I also did not expect it to: https://imgur.com/a/GCLbMGp

Wow...it made everything worse.

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#48

Post by itishappy »

pavel_lishin wrote: post #44
itishappy wrote: post #27

Earlier quoted context omitted.

Right, and that would be guesswork unless the image had been explicitly tagged.

There are search engines that search for similar images; a small photo of John Quincy Adams may be 99.99% identifiable as such.

An educated guess then, maybe even a good one!

What happens if it's only 80% sure? Do you get a high-res John Quincy Adams or an admission that it can't identify the image content? If I feed it a low-res picture of Michael Faraday or Henry Clay, will I receive the finely sculpted jowls of John Quincy Adams in return?

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#49

Post by godelski »

arcastroe wrote: post #3

Curious, does this use a publicly available model (such as real-esrgan), or is it a custom model? To reach 10x magnification, is 2x magnification simply consecutively repeated?

I'm also curious about this (as a researcher myself). It would be nice to know what model is used (or if this is actually novel[0]).

It is also worth mentioning the legal issues of this, and since you are charging(?) for this, you can be in legal jeopardy[1]. The architecture might be under some license and if you tuned a model that might also be under a license (it is worse if these are not under a license!). Most research software is under MIT licenses, but it is starting to become less common. If you trained or tuned an existing model that does not necessitate you release the checkpoint, which let's be honest, that's the secret sauce.

[0] I don't expect this as even most of the research is not novel. There's so much railroading where things build on top of one another. But that is also the nature of how we create things. Not by giant leaps.

[1] lol, open source is stolen all the time. Legal action is really unlikely. But let's admit this is unethical.

Re: Show HN: I made an AI image enhancer that boosts images 10x to 12k pixels

#50

Post by thih9 »

pavel_lishin wrote: post #43
thih9 wrote: post #14

Earlier quoted context omitted.

Unless the rest of the image offers details that the human observer would ignore but the AI would pick up. E.g. low res photo from 1828 of a US president - enhance to John Quincy Adams. Surprisingly there's a daguerreotype of John Quincy Adams from 1843[1], the AI could use that; perhaps "enhance" the time backwards a bit, to make him 15 years younger. [1]: https://en.m.wikipedia.org/wiki/File:John_Quincy_Adams_-_cop…

Isn't that what Samsung was doing with photos of the moon? https://www.theverge.com/2023/3/13/23637401/samsung-fake-moo... But I also had a similar thought. Use a combination of an image search engine like TinEye, and something like ClearviewAI, to actually either find a larger image of the submitted photo, or of more photos of the person in question, and reconstruct what they look like based on all of that additiona…

Yes. But I'd like to take it one step further.

E.g. if I send a photo of an olympic podium where winners are pixelated and ask the AI to enhance, I'd like it to use other elements of the pixelated photo to recognize the olympic event and year, search some other database to find the winners and enhance the photo so that the people on the podium were those who actually stood on that podium.

Post reply on HN