Technology

59534 readers

3195 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 1 year ago

MODERATORS

430

We Asked A.I. to Create the Joker. It Generated a Copyrighted Image. (www.nytimes.com)

submitted 10 months ago by L4s@lemmy.world to c/technology@lemmy.world

412 comments fedilink hide all child comments

We Asked A.I. to Create the Joker. It Generated a Copyrighted Image.::Artists and researchers are exposing copyrighted material hidden within A.I. tools, raising fresh legal questions.

you are viewing a single comment's thread
view the rest of the comments

[–] KinNectar@kbin.run 65 points 10 months ago (22 children)

Copyright issues aside, can we talk about how this implies accurate recall of an image from a never before achievable data compression ratio? If these models can actually recall the images they have been fed this could be a quantum leap in compression technology.

[–] Mirodir@discuss.tchncs.de 34 points 10 months ago* (last edited 10 months ago)

It's not as accurate as you'd like it to be. Some issues are:

It's quite lossy.
It'll do better on images containing common objects vs rare or even novel objects.
You won't know how much the result deviates from the original if all you're given is the prompt/conditioning vector and what model to use it on.
You cannot easily "compress" new images, instead you would have to either finetune the model (at which point you'd also mess with everyone else's decompression) or do an adversarial attack onto the model with another model to find the prompt/conditioning vector most likely to create something as close as possible to the original image you have.
It's rather slow.

Also it's not all that novel. People have been doing this with (variational) autoencoders (another class of generative model). This also doesn't have the flaw that you have no easy way to compress new images since an autoencoder is a trained encoder/decoder pair. It's also quite a bit faster than diffusion models when it comes to decoding, but often with a greater decrease in quality.

Most widespread diffusion models even use an autoencoder adjacent architecture to "compress" the input. The actual diffusion model then works in that "compressed data space" called latent space. The generated images are then decompressed before shown to users. Last time I checked, iirc, that compression rate was at around 1/4 to 1/8, but it's been a while, so don't quote me on this number.

edit: fixed some ambiguous wordings.

load more comments (21 replies)