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

Imagen, a text-to-image diffusion model

gweb-research-imagen.appspot.com

Post reply on HN
Print view View original

481–490 of 661 posts

Re: Imagen, a text-to-image diffusion model

#481

Post by Gigachad »

fumblebee wrote: post #430
davikr wrote: post #132

Interesting and cool technology - but I can't seem to ignore that every high-quality AI art application is always closed, and I don't seem to buy the ethics excuse for that. The same was said for GPT, yet I see nothing but creativity coming out from its users nowadays.

Another consideration here is that hosting a queryable model like this becomes expensive . I remember a couple of years ago lone developer had to take down his site which hosted a freely accessible version of GPT-2 (3?) model because the bills were running to some $20k. (Chump change for Google, but still).

I think a lot of people would be perfectly happy to pay per query to access this.

Re: Imagen, a text-to-image diffusion model

#482

Post by WalterBright »

qz_kb wrote: post #472
kleer001 wrote: post #459

Earlier quoted context omitted.

How would that really happen? It seems to me you're assuming that there's no such thing as extant databases of actual oil paintings, that people will stop producing, documenting, and curating said paintings. I think the internet and curated image databases are far more well kept than your proposed model accounts for.

My hypothetical example is not really about oil paintings, but the fact these models will surely get deployed and used for stock photos for articles, on art pages etc. I think this will introduce unavoidable background noise that will be super hard to fully eliminate in future large scale data sets scraped from the web, there's always going to be more and more photorealistic pictures of "cats" "chairs" etc. in the da…

My first thought on reading the article is generating images for my presentations.

Re: Imagen, a text-to-image diffusion model

#483

Post by astrange »

zarzavat wrote: post #476
astrange wrote: post #410

Earlier quoted context omitted.

In the days when Sussman was a novice Minsky once came to him as he sat hacking at the PDP-6. "What are you doing?", asked Minsky. "I am training a randomly wired neural net to play Tic-Tac-Toe." "Why is the net wired randomly?", asked Minsky. "I do not want it to have any preconceptions of how to play" Minsky shut his eyes, "Why do you close your eyes?", Sussman asked his teacher. "So that the room will be empty." A…

The model makes inferences about the world from training data. When it sees more female nurses than male nurses in its training set, if infers that most nurses are female. This is a correct inference. If they were to weight the training data so that there were an equal number of male and female nurses, then it may well produce male and female nurses with equal probability, but it would also learn an incorrect underst…

> The model makes inferences about the world from training data. When it sees more female nurses than male nurses in its training set, if infers that most nurses are female. This is a correct inference.

No it is not, because you don’t know if it’s been shown each one of its samples the same number of times, or if it overweighted some of its samples more than others. There’s normal reasons both of these would happen.

Re: Imagen, a text-to-image diffusion model

#484

Post by exikyut »

rhacker wrote: post #448
qz_kb wrote: post #437

I have to wonder how much releasing these models will "poison the well" and fill the internet with AI generated images that make training an improved model difficult. After all if every 9/10 "oil painted" image online starts being from these generative models it'll become increasingly difficult to scrape the web and to learn from real world data in a variety of domains. Essentially once these things are widely availa…

Look at carpentry blogs, recipe blogs. Nearly all of it is junk content. I bet if you combined GPT and imagen or dalle2 you could replace all of them. Just provide a betty crocker recipe and let it generate a blog that has weekly updates and even a bunch of images - "happy family enjoying pancakes together" I can see the future as being devoid of any humanity.

"Picture of happy nuclear family enjoying paperclip maximization at the beach"

Re: Imagen, a text-to-image diffusion model

#485

Post by VMG »

qz_kb wrote: post #437

I have to wonder how much releasing these models will "poison the well" and fill the internet with AI generated images that make training an improved model difficult. After all if every 9/10 "oil painted" image online starts being from these generative models it'll become increasingly difficult to scrape the web and to learn from real world data in a variety of domains. Essentially once these things are widely availa…

It will not be limited to the internet. Have you looked at a magazine stand in the last 10 years? The content looks generated (not by AI) even today.

Cheap books, cheap TV and cheap music will be generated.

Re: Imagen, a text-to-image diffusion model

#486

Post by thelittleone »

rhacker wrote: post #448
qz_kb wrote: post #437

I have to wonder how much releasing these models will "poison the well" and fill the internet with AI generated images that make training an improved model difficult. After all if every 9/10 "oil painted" image online starts being from these generative models it'll become increasingly difficult to scrape the web and to learn from real world data in a variety of domains. Essentially once these things are widely availa…

Look at carpentry blogs, recipe blogs. Nearly all of it is junk content. I bet if you combined GPT and imagen or dalle2 you could replace all of them. Just provide a betty crocker recipe and let it generate a blog that has weekly updates and even a bunch of images - "happy family enjoying pancakes together" I can see the future as being devoid of any humanity.

Seeing this a lot on youtube also. Scripts pulling in "news" from a source as a script for a robo voice combined with "related" images stitched together randomly.

Re: Imagen, a text-to-image diffusion model

#487

Post by nearbuy »

jonny_eh wrote: post #94
tines wrote: post #42

Earlier quoted context omitted.

This raises some really interesting questions. We certainly don't want to perpetuate harmful stereotypes. But is it a flaw that the model encodes the world as it really is, statistically, rather than as we would like it to be? By this I mean that there are more light-skinned people in the west than dark, and there are more women nurses than men, which is reflected in the model's training data. If the model only gener…

> But is it a flaw that the model encodes the world as it really is Does a bias towards lighter skin represent reality? I was under the impression that Caucasians are a minority globally. I read the disclaimer as "the model does NOT represent reality".

I don't think we'd want the model to reflect the global statistics. We'd usually want it to reflect our own culture by default, unless it had contextual clues to do something else.

For example, the most eaten foods globally are maize, rice, wheat, cassava, etc. If it always depicted foods matching the global statistics, it wouldn't be giving most users what they expected from their prompt. American users would usually expect American foods, Japanese users would expect Japanese foods, etc.

> Does a bias towards lighter skin represent reality? I was under the impression that Caucasians are a minority globally.

Caucasians specifically are a global minority, but lighter skinned people are not, depending of course on how dark you consider skin to be "lighter skin". Most of the world's population is in Asia, so I guess a model that was globally statistically accurate would show mostly people from there.

Re: Imagen, a text-to-image diffusion model

#488

Post by hn_throwaway_99 »

thelittleone wrote: post #486
rhacker wrote: post #448

Earlier quoted context omitted.

Look at carpentry blogs, recipe blogs. Nearly all of it is junk content. I bet if you combined GPT and imagen or dalle2 you could replace all of them. Just provide a betty crocker recipe and let it generate a blog that has weekly updates and even a bunch of images - "happy family enjoying pancakes together" I can see the future as being devoid of any humanity.

Seeing this a lot on youtube also. Scripts pulling in "news" from a source as a script for a robo voice combined with "related" images stitched together randomly.

Even though it's not AI, this is already happening with a lot of content farms. There was a good video a couple years ago from Ann Reason of "How to Cook That" that basically pointed out how the visually-appealing-but-not-actually-feasible "hands and pans" content farms (So Tasty, 5 Minute Crafts, etc.) were killing genuine baking channels.

Imagine that instead of having cheap labor from Southeast Asia churn out these videos, that instead they are just spit out as fast as possible using AI.

Re: Imagen, a text-to-image diffusion model

#489

Post by bowmessage »

qz_kb wrote: post #437

I have to wonder how much releasing these models will "poison the well" and fill the internet with AI generated images that make training an improved model difficult. After all if every 9/10 "oil painted" image online starts being from these generative models it'll become increasingly difficult to scrape the web and to learn from real world data in a variety of domains. Essentially once these things are widely availa…

I also worry about the potential to further stifle human creativity, e.g. why paint that oil painting of a panda riding a bicycle when I could generate one in seconds?
Post reply on HN