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

Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

github.com

Post reply on HN
Print view View original

71–80 of 84 posts

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#71

Post by ai_critic »

jtsylve wrote: post #26
a2128 wrote: post #10

You're adding metadata, but what problems does this added metadata solve exactly? If your converter can automatically compute these image features, then AI training and inference pipelines can trivially do the same, so I don't see the point in needing a new file format that contains these. Moreover, models and techniques get better over time, so these stored precomputed features are guaranteed to become obsolete. Eve…

The answer may be in your question. - This is currently solved by inference pipelines. - Models and techniques improve over time. The ability for different agents with different specialties to add additional content while being able to take advantage of existing context is what makes the pipeline work. Storing that content in the format could allow us to continue to refine the information we get from the image over t…

> Each tool that touches the image can add new context or improve existing context and the image becomes more and more useful over time.

This is literally the problem solved by chunk-based file formats. "How do we use multiple authoring tools without stepping on each other" is a very old and solved problem.

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#73

Post by efitz »

Wow so much hate on this article.

Instead of the vitriol and downvotes, maybe next time just point out “you can put arbitrary data in exif”.

But you missed half the point of the article, which was the EXTRA DATA to make the image more LLM-useful.

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#74

Post by kuberwastaken »

efitz wrote: post #73

Wow so much hate on this article. Instead of the vitriol and downvotes, maybe next time just point out “you can put arbitrary data in exif”. But you missed half the point of the article, which was the EXTRA DATA to make the image more LLM-useful.

Haha, that's totally alright honestly, found a couple suggestions that could actually give me constructive criticism to improve it, ignored the ones that hated without reason - I semi-expected this reaction :p

Thanks for the comment! Means a lot :)

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#75

Post by vrighter »

efitz wrote: post #73

Wow so much hate on this article. Instead of the vitriol and downvotes, maybe next time just point out “you can put arbitrary data in exif”. But you missed half the point of the article, which was the EXTRA DATA to make the image more LLM-useful.

you could add anything in a png, and encoders should, unless otherwise instructed, preserve any chunks whose format it doesn't understand

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#76

Post by moritzwarhier »

Why not store metadata, along with a checksum of the png, in myPublicPhoto.png.meow?

Labeling and metadata a separate concerns. "Edge detection maps" etc are implementation details of whatever you are doing with image data, and quite likely to be non-portable.

And non-removability / steganography of additional metadata is not a selling point at all?

So my thoughts are, this violates separation of concerns and seems badly thought-out.

It also mangles labeling, metadata and technicalities, and attempts to predict future requirements.

I don't understand potential utility.

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#78

Post by NBJack »

daeken wrote: post #29

> Python-based image file format This is one of the first lines of the readme. But this is PNG with some metadata encoded using the most naive steganographic technique (just thrown into the LSB of pixels -- no redundancy, no error correction, no compensation for down sampling, etc). Even ignoring everything else, this is just ... Nonsensical. I am very very pro-AI. But this is slop.

It's also not how file formats generally work or get defined. I'm not sure I'd even define a .pickle file that way either, and it's the poster child for a hyper-specific Python format.

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#79

Post by fao_ »

whoisyc wrote: post #63
DanHulton wrote: post #41

You have invented essentially an _incredible way_ to poison AI image datasets. Step 1: Create .meow images of vegetables, with "per-pixel metadata" instead encoded to represent human faces. Step 2: Get your images included in the data set of a generative image model. Step 3: Laugh uproariously as every image of a person has vaguely-to-profoundly vegetal features.

This assumes people training AI are going to put in the efforts to extract metadata from a poorly specified “format” with a barely coherent buzzword ridden README file. Realistically, they will just treat any .meow as opaque binary blobs and any png as regular png file.

Hm, I'm not really sure why this is getting downvoted because — yes, I also had the same impression. The format was only barely specified, and the readme was incredibly sparse with a lot of marketing bs.

Re: Show HN: Meow – An Image File Format I made because PNGs and JPEGs suck for AI

#80

Post by fao_ »

thinkingQueen wrote: post #23
fao_ wrote: post #7

> Instead of storing metadata alongside the image where it can be lost, MEOW ENCODES it directly inside the image pixels using LSB steganography That makes the data much more fragile than metadata fields, though? Any kind of image alteration or re-encoding (which almost all sites do to ensure better compression — discord, imgur, et al) is going to trash the metadata or make it utterly useless. I'll be honest, I don't…

Exactly. Not long ago, someone showed up on Hacker News who had, on his own, begun to rediscover the benefits of arithmetic coding. Naturally, he was convinced he’d come up with a brand-new entropy coding method. Well, no harm done and it’s nice that people study compression but I was surpised how easily he got himself convinced of a discovery. Clearly he knew very little. Overall, I think this is a positive ”problem…

I mean, I think it would be a positive problem to have if people were actually learning things and growing, but... honestly this doesn't seem to be the case, what I see here is AI-generated marketing fluff about a "brand new format" that does something that off-the-shelf software already does, that doesn't actually fit the intended use-case, (all of which would be fine if it wasn't-) generated also by AI.
Post reply on HN