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

DALL-E 2 generates images of Kermit The Frog in various films

twitter.com

Post reply on HN
Print view View original

141–150 of 198 posts

Re: DALL-E 2 generates images of Kermit The Frog in various films

#141

Post by adamsmith143 »

simiones wrote: post #133
silicon2401 wrote: post #34

Earlier quoted context omitted.

Are you aware that this is how human artists work, too? They make countless works that aren't comparable to their top works. Even more so if you count the practice when they were just starting out. I think some people just refuse to believe that real art can be generated without humans and selectively look for things that confirm their pre-determined conclusion. Witnessing this always feels like witnessing someone be…

There is a crucial difference: the human artist does this choosing themselves. If DALL-E just spits out 1000 images and then a human goes through them and picks the best 2-3, and those are good - it's impressive, but the human was still a crucial part of the process. On the other hand, if DALL-E were to generate 10 billion images, and choose the best 2-3 itself and give those as output, and if at least one of those 2…

Who's to say that Dall-E 3.0 won't do exactly that? This is not the peak of AI art generation and it will only continue to improve.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#142

Post by simiones »

FeepingCreature wrote: post #110
endisneigh wrote: post #67

Earlier quoted context omitted.

If you drew it yourself there’s precedent under fair use. If you made something that drew it when prompted for “The Matrix” presumably it knows what that is and therefore is more ambiguous

For copyright purposes, the tweeter "made it themselves."

That remains to be seen. If I take a photograph of a still from the Matrix and print it, that's not the same as me photo-realistically drawing the same still from memory, which is itself not the same as me photo-realistically drawing it while looking at the still itself.

Copyright law is way more nuanced than you think, especially around fair use.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#143

Post by tgv »

myrmidon wrote: post #59
tgv wrote: post #4

Earlier quoted context omitted.

Yes, and it still feels a lot like Searle's Chinese Room. It's as if it skips a dozen steps. Well, that's exactly what happens, of course. But it does show that the network can match linguistic descriptions to images extraordinarily well.

Do you find the Chinese Room argument convincing? Do you feel that the human mind is more than an "appropriately" trained "biological" neural network? What do you consider the limits of a DALL-E like system compared to a "true" mind? My personal opinion is that the Chinese Room argument is fancy handwaving that crucially relies on never being explicit about what it means by "understanding", combined with an appeal to…

> My personal opinion is that the Chinese Room argument is fancy handwaving

It isn't hand-waving. It's against it, really. It's a thought experiment that encourages a sceptic attitude towards jumps in understanding mental processes. The operator in the Chinese Room doesn't understand Chinese. While the translations are excellent, he or she wouldn't be able to go out in the street and ask for a glass of water if their life depended on it. Hence, a computer that mechanically translates Chinese cannot be automatically assumed to understand Chinese.

The argument doesn't need to explain exactly what understanding means. We all (sort of) know what it means. The same goes for e.g. attention. That's what makes it so hard to define what strong AI is and how to verify it. The Turing Test famously tries to decide this (without defining anything, I might add), and the Chinese Room is a good argument against it being the proper test.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#144

Post by jameshart »

witheld wrote: post #46
tommoor wrote: post #33

Earlier quoted context omitted.

I genuinely can't tell if you're trolling. This isn't impressive because the AI model doesn't accurately capture the "feel" of Kermit!?

The computer was asked to produce photos of Kermit the frog. It failed spectacularly at rendering anything resembling Kermit the frog.

Yet, it did produce things which "look like weird designs for the Ninja Turtles movie in the 90s."

In other words, it has done as good a job of costume design, lighting and photographing a live action Kermit as New Line Cinema paid $13.5m to accomplish for TMNT in 1990.

And you know who they got to do those creature designs?

Jim Henson

So maybe we shouldn't be so dismissive.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#145

Post by bambax »

AnIdiotOnTheNet wrote: post #62
mensetmanusman wrote: post #14

This is amazing. We are at the precipice of someone releasing a $100M blockbuster movie just based on the language in the script with zero cost beyond compute. What will this mean for the future of entertainment…

On the one hand, the ability for Star Trek's Holodeck to create large amounts of content from a few terse natural language instructions is look less and less implausible. On the other hand, I feel like this will ultimately be kinda like traditional procgen algorithms: once you've seen enough of what it produces it all starts feeling very bland and same-y. Sure, the AI may be able to produce a feature-length movie bas…

> The Terminator and Aaron Sorkin wrote the script?

You can't handle the future! We live in a world that has time machines, and those time machines have to be manned by robots! Who's gonna do it? You?

Re: DALL-E 2 generates images of Kermit The Frog in various films

#146

Post by simiones »

PheonixPharts wrote: post #24

These are honestly not very impressive (no sarcasm here) and further convince me that the next AI Winter will come with this coming recession. Don't get me wrong, they are still impressive in the quality of the visual they produce, but just like Markov Chain demos of old, they're neat but way miss the mark. None of these capture the "feel" of Kermit the Frog. Most of them look like weird designs for the Ninja Turtles…

While I think many are over-interpreting the quality of these results, yours is sounding like a clear case of a No True Kermit fallacy.

There are many ways to define what "Kermit the Frog in $MOVIE" means, and the choice the AI made is absolutely valid. There are of course various other valid choices, but this doesn't invalidate the ones presented.

Furthermore, judging by some other examples in this HN thread, it seems that the fact most of the pictures are not puppets is more of a choice of the human choosing the photos, as in other cases DALL-E was indeed adding puppet-like characters in movie-like decors.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#147

Post by treesprite82 »

jonnycomputer wrote: post #79

Not to detract from the accomplishment, but none of these are Kermit. The "Kermit" part of the query seems mostly to have accomplished querying for "humanoid frog"

Seems like it adapted Kermit's features to fit with the world of the movie, as if he was actually a character from that movie.

I don't have access to DALL-E 2, but I wonder if a prompt like "A cameo from Kermit the Frog in ..." would give more literal Kermits.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#148

Post by simiones »

adamsmith143 wrote: post #141
simiones wrote: post #133

Earlier quoted context omitted.

There is a crucial difference: the human artist does this choosing themselves. If DALL-E just spits out 1000 images and then a human goes through them and picks the best 2-3, and those are good - it's impressive, but the human was still a crucial part of the process. On the other hand, if DALL-E were to generate 10 billion images, and choose the best 2-3 itself and give those as output, and if at least one of those 2…

Who's to say that Dall-E 3.0 won't do exactly that? This is not the peak of AI art generation and it will only continue to improve.

Sure, it might. But until then, I wouldn't say it makes sense to consider the AI as "being the artist".

When DALL-E x.0 does that, and when it also generates similar quality from much higher-level prompts ("paint a sad picture", or "social commentary on BLM" or something like this, instead of a description of what the picture should show and in what style), then I for one will be in complete agreement that it's indeed an artist in itself.

Personally, I don't expect this to happen in the next few decades, as I don't think the current approaches are very promising for the type of intelligence that you would need to actually do this type of reasoning, but that remains to be seen, and I am fully confident that it will happen some day.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#149

Post by klik99 »

tdehnel wrote: post #111
tinalumfoil wrote: post #104

The amount of creativity here is astounding. Just imagine all the decisions the AI made in incorporating Kermit into the movies: the clothing it's chosen, how the character wears the clothing, the facial expressions, how to make Kermit himself look similar to the other movies characters. Should he be lanky? pudgy? Even simple decisions like obliviously Kermit in Wall-E is going to be a robot, it has to figure out wha…

Sorry to be this guy but that is not creativity. It’s using what already exists, not conjecturing something new. Contrast with real creativity (what people can do but machines currently cannot) where you conjecture something completely new. For example, Copernicus conjecturing the idea that the Earth revolves around the Sun. No machine learning model would have gotten there because it would have been trained on a bun…

"Good artists borrow, great artists steal"

Creativity is a very vague word, I'm sure we can come up with definitions of it that let humans keep sole domain over it. But breakthroughs often come from combining domains and concepts, very very rarely do we ever jump out of one local maxima into another, and I'm not even convinced that Copernicus counts as that. There's a reason why there are so many examples of the same breakthrough happening in multiple places in the world independently - innovation is a slow gradual collaborative process and not plateaus waiting for men of genius to have a spark of inspiration.

Also I'm not convinced that a computer couldn't have discovered the earth revolves around the sun - it's hard to make machine learning jump out of local maxima, but it does happen, and I can see some hidden layers becoming far more efficient at predicting outcomes by stumbling across a model that centered the sun. That being said - there likely are examples of things that computers couldn't have theoretically figured out the model for, but I'm hard pressed to think of one.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#150

Post by ceejayoz »

bogwog wrote: post #64
akersten wrote: post #49

Earlier quoted context omitted.

Everything that you, a person with a paintbrush, could paint "in the style of" something else is informed by what your model (your brain) has been exposed to. There's no getting around that, and commissioning you to paint something "in the style of postwar authoritarian England" does not infringe the copyright of V for Vendetta (even if I told you "make it look just like the movie"); it's an original painting. Stylis…

> But in any scenario, nothing legally novel about the work being created by machine. …except for the fact that it was created by a machine. Just like copyright law had to be revised to deal with software and the internet, it will need to be revised to deal with AI.

> …except for the fact that it was created by a machine.

We've already had this for years. The photos you take on any modern smart phone are partially the invention of AI (doubly so if you use something like portrait or night mode). It's not just raw CCD output, and yet, the photographer retains the copyright.

DALL-E's terms could require users to assign copyright. If not, I don't see any reason it wouldn't go to the person who came up with the prompt and picked one particular generation.

If I take a picture of a mountain with a camera, neither the mountain nor the camera hold copyright. DALL-E's just another tool in the toolbox.

Post reply on HN