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

No elephants: Breakthroughs in image generation

oneusefulthing.org

Post reply on HN
Print view View original

241–250 of 373 posts

Re: No elephants: Breakthroughs in image generation

#241

Post by Garlef »

genewitch wrote: post #179
__loam wrote: post #170

Earlier quoted context omitted.

If you use this technology, you're actively harming creative labor.

Whatever. I wrote and co-wrote ten albums and my total take was $3. The market is saturated and the way it works means ten get rich for every million artists. I feel as though this has been pretty constant throughout history. Of course there's a lot of talent out there, "wasted", but I think that's always been the case. How many William Shakesmans did we lose with all the war, famine, disease? I actually decided I'd…

> How many William Shakesmans did we lose with all the war, famine, disease?

(Just a small comment out of context of the remaining discussion:)

Maybe not many? It could be that "cultural attention" is limited and there's not much space at the top anyways. In other words: It might be that there's always a few famous artists that get remembered and the rest is forgotten. Same as winning the world cup: There's always a team that wins and it says nothing about the quality in a universal way. At best it says something about quality relative to the competition.

(Not sure I'd fully get behind the argument i composed here. But I found it interesting.)

Re: No elephants: Breakthroughs in image generation

#242

Post by fc417fc802 »

satvikpendem wrote: post #231
fc417fc802 wrote: post #230

Earlier quoted context omitted.

Is that not self evident? When people engage in labor for the task itself (as opposed to a heavily abstracted version of not wanting to starve) we generally refer to that as a hobby. So stating that people shouldn't need to worry about starving (metaphorically or otherwise) would be roughly equivalent.

It is not always evident especially when it comes to a site all about capital accumulation like HN, more due to its association with a venture capital firm.

Statistically, Jane Street probably employs at least a few communists.

Re: No elephants: Breakthroughs in image generation

#243

Post by pixl97 »

amazingamazing wrote: post #70
gcanyon wrote: post #34

It's interesting to hear people side with the artists when in previous discussions on this forum I've gotten significant approval/agreement arguing that copyright is far too long. As I've argued in the past, I think copyright should last maybe five years: in this modern era, monetizing your work doesn't (usually) have to take more than a short time. I'd happily concede to some sort of renewal process to extend that p…

> I think copyright should last maybe five years: in this modern era, monetizing your work doesn't (usually) have to take more than a short time. I funny how people who say this kind of stuff are never content creators (in the monetization sense).

I mean, this is about as useful as saying anti-slavery people should become slave owners so they understand the hardships of making money.

My example is extreme to the absurd, so how about we go with

>It's difficult to get a man to understand something when his salary depends on not understanding it.

Re: No elephants: Breakthroughs in image generation

#244

Post by pixl97 »

thwarted wrote: post #186
smusamashah wrote: post #138

Earlier quoted context omitted.

Vortex may be not so much but there are other hard to visualize things. I am on the third book, and I have no idea what Beeblebrox's two heads look like. Second head is often mentioned in passing. Sometimes its mentioned as its always there, other times it feels like its just pops out of somewhere, otherwise, it's like it doesn't exist. There is the scene when they see themselves on the beach on first rescue by the s…

We have alt text for images, you want alt images for text. You can see other people's interpretation of Zaphod's two heads by watching the BBC HHGTTG show (Mark Wing-Davey) or the movie (Sam Rockwell), among other renditions, which offer completely different interpretations, none of them canonical (not the least of which is because there was no canonical version of HHGTTG according to DA). I'm sure there are multitud…

>Hotblack Desiato's ship would just be black

These days we have paint that black, though we can't reproduce the effect on the monitor.

Those superblacks really do mess with your mind. It's like a cutout of the void.

Re: No elephants: Breakthroughs in image generation

#245

Post by echelon »

vunderba wrote: post #206
nowittyusername wrote: post #141

There is circumstantial evidence out there that 4o image manipulation isn't done within the 4o image generator in one shot but is a workflow done by an agentic system. Meaning this, user inputs prompt "create an image with no elephants in the room" > prompt goes to an llm which preprocesses the human prompt > outputs a a prompt that it knows works withing this image generator well > create an image of a room > and th…

As somebody who actually tried to build a multimodal stable diffusion chat agent about a year back using YOLO to build partial masks for adjustments via inpainting, dynamic controlnets, and a whole host of other things, I highly doubt that it's as simple as an agentic process. Using the prompt to detect and choose the most appropriate model checkpoint and LoRa(s) along with rewriting a prompt to most appropriately su…

> Using the prompt to detect and choose the most appropriate model checkpoint and LoRa(s) along with rewriting a prompt to most appropriately suit the chosen model has been pretty bog standard for a long time now.

Which players are doing this? I haven't heard of this approach at all.

Most artistic interfaces want you to visually select a style (LoRA, Midjourney sref, etc.) and will load these under the hood. But it's explicit behavior controlled by the user.

Re: No elephants: Breakthroughs in image generation

#246

Post by pixl97 »

haswell wrote: post #48

> The question isn't whether these tools will change visual media, but whether we'll be thoughtful enough to shape that change intentionally. Unfortunately I think the answer to this question is a resounding “no”. The time for thoughtful shaping was a few years ago. It feels like we’re hurtling toward a future where instead we’ll be left picking up the pieces and assessing the damage. These tools are impressive and w…

>But I think it’s going to be a rough ride, and whatever new equilibrium we reach will be the result of much turmoil.

Honestly visual media just seems to be the start. In the past two years we've seen about as much robotics progress as the last 20. If this momentum keeps up then we're not just talking about artists that are going to have issues.

Re: No elephants: Breakthroughs in image generation

#247

Post by pixl97 »

jsheard wrote: post #159
ziofill wrote: post #156

I usually agree with most of Gary Marcus' points, but I'd really like to hear his take on this. One of his examples is that "the system can't generate a horse riding an astronaut" and in fact I tried a lot in the past but it would always draw the astronaut on top of the horse. Well, here is the result now: https://postimg.cc/QFtRjbHM

Whenever one of these well known gotcha prompts gets "solved" the question is always whether they actually solved the underlying reason it used to fail, or did they just have a bunch of third-world workers tag pictures of horses and astronauts until the model started handling that specific example more reliably. As the saying goes, every measure which becomes a target becomes a bad measure.

Well, what you do is try examples close to the problem space around it. For example a fiddler crab riding a chameleon

https://sora.com/g/gen_01jrbq91wtefjtpb8ceajdh9mt

and then iterate around other combinations to see if it's generalized or not.

Re: No elephants: Breakthroughs in image generation

#248

Post by thot_experiment »

pixl97 wrote: post #236
DeathArrow wrote: post #46

Earlier quoted context omitted.

>Its also not clear for example that Studio Ghibli lost by having their art style plastered all over the internet. Maybe Studio Ghibli is much more than merely a style. Maybe people aren't looking at their production just for the style. Most people dislike wearing fake clothes and the dislike wearing fake watches or fake jewelry. Because it isn't just about the style.

>Most people dislike wearing fake clothes and the dislike wearing fake watches or fake jewelry I'd disagree. Most people don't like buying something 'real' then finding out it's fake. Far more people don't mind an actual fake if it's either high quality or is very low priced.

Yeah ngl I have some fake designer stuff I got as a gift and I love it, and I especially love that it's fake. It feel like I'm pulling one over on the tryhards that care about that stuff being real, but I still get to enjoy the wild LV coat I have and ain't nobody checking the stitching on the lining to make sure it's the real thing. I could see myself buying more fakes in the future, but I'd never ever buy the real thing.

Re: No elephants: Breakthroughs in image generation

#249

Post by AnthonyMouse »

fc417fc802 wrote: post #233
AnthonyMouse wrote: post #209

Earlier quoted context omitted.

That is the definition of capitalism people use when they want to apply the term capitalism to something that sucks. Allowing people to own physical items as business inventory or production equipment and compete with each other for the customer's dollar is entirely possible without the existence of copyright or patents. You would then be relying on some combination of open source, charitable contributions and patron…

> You would then be relying on ... More likely trade secrets, NDAs, non-competes, and increasingly invasive DRM. In addition to the direct financial incentive, part of the logic behind IP law is to foster a more open market because that should be to the benefit of society at large in multiple ways. Patents, for example, ensure that at least some minimal description of the process gets published for others to take ins…

> More likely trade secrets, NDAs, non-competes, and increasingly invasive DRM.

These are all also creatures of the law. If there was no copyright there would be no Digital Millennium Copyright Act. In many cases they can't work, e.g. because of the analog hole or because the mechanism of operation is observable to anyone who buys the product.

The incentives to uncover those things are also much stronger in modern day because of the connectedness of the world. If there were two wheelwrights in your town and one of them had a secret process, no one but the other would have any use for it and if they found out they wouldn't even have any else to tell it to.

If someone had a secret video encoding strategy today, some hobbyists would reverse engineer it and post it on the internet.

> Patents, for example, ensure that at least some minimal description of the process gets published for others to take inspiration from.

Have you read a modern patent? They're inscrutable, and to the fullest extent allowable attempt to claim the overall concept of doing something rather than describing a specific implementation.

Re: No elephants: Breakthroughs in image generation

#250

Post by gcanyon »

another-dave wrote: post #123
gcanyon wrote: post #34

It's interesting to hear people side with the artists when in previous discussions on this forum I've gotten significant approval/agreement arguing that copyright is far too long. As I've argued in the past, I think copyright should last maybe five years: in this modern era, monetizing your work doesn't (usually) have to take more than a short time. I'd happily concede to some sort of renewal process to extend that p…

I'd agree with limiting copyrights but would do it based on money earned rather than time, so something like when you make $X million, the work becomes public domain. As a specific example — _A Game of Thrones_ was released in 1996. It picked up awards early on but only became a NYT best seller in 2011, just before the TV show aired. It would feel harsh for an author to loose all their copyright because their work wa…

It’s a super-interesting idea, but GoT seems highly cherry picked: the vast majority of all works would never leave copyright if the requirement was that they clear even $1000.
Post reply on HN